Forthcoming and Online First Articles

International Journal of Computational Vision and Robotics

International Journal of Computational Vision and Robotics (IJCVR)

Forthcoming articles have been peer-reviewed and accepted for publication but are pending final changes, are not yet published and may not appear here in their final order of publication until they are assigned to issues. Therefore, the content conforms to our standards but the presentation (e.g. typesetting and proof-reading) is not necessarily up to the Inderscience standard. Additionally, titles, authors, abstracts and keywords may change before publication. Articles will not be published until the final proofs are validated by their authors.

Forthcoming articles must be purchased for the purposes of research, teaching and private study only. These articles can be cited using the expression "in press". For example: Smith, J. (in press). Article Title. Journal Title.

Articles marked with this shopping trolley icon are available for purchase - click on the icon to send an email request to purchase.

Online First articles are published online here, before they appear in a journal issue. Online First articles are fully citeable, complete with a DOI. They can be cited, read, and downloaded. Online First articles are published as Open Access (OA) articles to make the latest research available as early as possible.

Open AccessArticles marked with this Open Access icon are Online First articles. They are freely available and openly accessible to all without any restriction except the ones stated in their respective CC licenses.

Register for our alerting service, which notifies you by email when new issues are published online.

We also offer which provide timely updates of tables of contents, newly published articles and calls for papers.

International Journal of Computational Vision and Robotics (61 papers in press)

Regular Issues

  • Comprehensive survey on video anomaly detection using deep learning techniques   Order a copy of this article
    by Sreedevi R. Krishnan, P. Amudha, S. Sivakumari 
    Abstract: The rapid increase in violence and crime leads to the use of video surveillance systems. Handling such huge videos and classifying them as abnormal or not are tedious. Therefore, an automatic anomaly detection method is vital for the real-time detection of anomalous events. Advancements in machine intelligence lead to an automatic anomaly detection system for the timely identification of anomalous events and reducing the after-effects. Recent research uses deep learning techniques for faster and automatic detection of abnormal events from an enormous volume of surveillance videos. Reviewing the video anomaly detection system is very relevant and helps to promote future research in this area. The paper performs a comprehensive study of several video anomaly detection methods using deep learning techniques to detect and predict anomalous events. The paper also surveys various methods used for women’s safety. Various methodologies, datasets, and evaluation metrics for detecting video anomalies and comparisons are included.
    Keywords: deep learning; CNN; LSTM; GAN; autoencoder; women safety.
    DOI: 10.1504/IJCVR.2022.10051823
     
  • Robust autonomous detection and tracking of moving objects using hybrid tracking approach   Order a copy of this article
    by Mohamed Akli Bousta, Abdelkrim Nemra 
    Abstract: Detecting and tracking mobile objects in video is among the most prevalent and challenging tasks under realistic motion and climatic conditions such as image occlusion, fast camera movement and natural environmental changes (fog, rain, etc.). In this paper, we propose an improved autonomous visual detection and tracking algorithm, which uses the single shot detection algorithm for initialisation followed by an adaptive kernelised correlation filter (KCF) tracker and combined with a predictor-corrector smooth variable structure filter (SVSF) for target recovery and estimation. It is known that KCF tracker suffers from failure to target recovery after an occlusion and scale variation. To overcome these limitations, the optimal SVSF filter is combined with the KCF tracker in order to maintain suitable target estimation and update the KCF tracker when the target is lost. The obtained results illustrate that the proposed approach achieves the state-of-the-art performance on all tested datasets with many realistic scenarios with different attributes.
    Keywords: visual detection and tracking; single shot multi-box detector; SSD; kernelised correlation filter; KCF; smooth variable structure filter; SVSF.
    DOI: 10.1504/IJCVR.2022.10051959
     
  • Visual place representation and recognition from depth images   Order a copy of this article
    by Farah Ibelaiden, Slimane Larabi 
    Abstract: We propound a new visual positioning method that recognises the previously visited places whose descriptors are stored in a dataset that does not need updates. The descriptor of the unknown location is computed from a depth video acquired by surrounding the depth camera in the scene to build gradually the corresponding 3D map. From which the 2D map is derived and described geometrically based on the architectural features to constitute the query descriptor which is compared to database descriptors in order to deduce the location. The experiments show the efficiency and robustness of the proposed descriptor to scenery changes, light variations and appearance changes.
    Keywords: place recognition; depth image; architecture-based descriptor; three dimensional model; two dimensional map.
    DOI: 10.1504/IJCVR.2022.10052055
     
  • Collation of performance parameters on various machine learning algorithms for breast cancer discernment   Order a copy of this article
    by Mohan Kumar, Sunil Kumar Khatri, Masoud Mohammadian 
    Abstract: In clinical practices machine learning (ML) technology plays an important and rapid growing role as it is likely to help healthcare professionals making decisions and proposing new diagnoses. This research study aims in validating and comparing the performance of various ML models that can help in predicting breast cancer in women. Performance Parameters on various ML Algorithms for breast cancer dataset has been tested. The testing is performed on 116 participants from dataset. The features of dataset including insulin, glucose, resisting, adiponectin, homeostasis model assessment (HOMA), leptin, age, and index of obesity (MCP1). Many clinical features were measured like BMI. This dataset experimented with 11 classification algorithms such as logistic regression (LR), k-nearest neighbour (kNN), support vector machine (SVM), decision tree (DT), random forest (RF), Naive Baise and optimum ML algorithms, etc. The research work detected breast cancer from the published Coimbra breast cancer dataset (CBCD). Each classifier has been utilised for various kinds of parameters tuning and for prediction. These results suggested they could be taken as a very meaningful and useful pair of factors to forecast cancer.
    Keywords: machine learning; ML; optimal algorithms; prediction; breast cancer; support vector machine; SVM.
    DOI: 10.1504/IJCVR.2022.10052056
     
  • Copy move forgery detection by improved SIFT K-means algorithm   Order a copy of this article
    by Kavita Rathi, Parvinder Singh 
    Abstract: The copy move forgery due to its copied features from same image pose toughest challenge in image forgery detection. Key-point-based CMFD techniques outperform the block-based CMFD techniques. SIFT is most used key-point-based techniques. The present algorithm improves upon the SIFT algorithm with improvement in the various steps of the workflow by adding Laplace of Gaussian and multiplying it by the square of Gaussian kernel to make it real scale invariant, applying double level filtering at feature extraction and filtering by using g2NN and K-mean clustering. The results in the form of recall, precision, and F1 measure outperformed the state-of-art key-point-based CMFD techniques over multiple datasets.
    Keywords: copy move forgery; CMF; key-point-based CMFD; SIFT extractor; Laplace of Gaussians; LoGs; K-means clustering.
    DOI: 10.1504/IJCVR.2022.10052099
     
  • Deep multiple affinity model for proposal-free single instance segmentation   Order a copy of this article
    by Isah Charles Saidu, Lehel Csató 
    Abstract: We improve on an existing instance segmentation model with a probabilistic extension to the encoded neighbourhood branch model (Bailoni et al., 2020) - we call it multiple outputs encoded neighbourhood branch (mENB) model. The mENB predicts - for each voxel in a 3D volume, a distribution of central masks, where each mask represents affinities of its central voxel and the neighbouring voxels within the mask. When post-processed using a graph partition algorithm, these masks collectively delineates the boundaries of each instance of the target class within the input volume. Our algorithm is efficient due to active learning, more accurate and it is robust to Gaussian noise and model weights perturbations. We conducted two experiments: 1) the first experiment compared mask predictions of our technique against the baseline (Bailoni et al., 2020) using the CREMI 2016 neuron segmentation dataset and the results showed a more accurate masks predictions with uncertainty quantification; 2) in the second experiment, we tested segmented instances against the popular proposal-based mask-RCNN and the results showed that our technique yields better precision and intersection over union.
    Keywords: segmentation; active learning; affinity model; uncertainty quantification.
    DOI: 10.1504/IJCVR.2022.10052466
     
  • Generic object detection in real-time images under poorly visible conditions: a systematic literature review   Order a copy of this article
    by Perla Sunanda, Dwaram Kavitha 
    Abstract: The invention and usage of CNN in computer vision (CV) have made object detection an emerging task to locate and identify objects in an image or video is facing challenge with poorly visible conditions. This review aims to know the research gap for detecting generic objects, to identify the frameworks needed for working with real-time images, to see the importance of image enhancement and the need for designing nighttime datasets. A systematic literature search of studies were carried out in Scopus and IEEE databases to select object detection studies specifying generic object detection, real-time images, poorly visible or lowlight conditions, image enhancement pre-processing, the type of framework or algorithms needed, and the nighttime datasets. The time frame for the analysis was from January 2010 to the latest month of 2022. The study shows that there is an utmost need for detecting objects in nighttime or lowlight conditions.
    Keywords: computer vision; CV; object detection; obstacle detection; poorly visible; low light condition; nighttime.
    DOI: 10.1504/IJCVR.2023.10053141
     
  • Improving accuracy of arbitrary-shaped text detection using ResNet-152 backbone-based pixel aggregation network   Order a copy of this article
    by Suresh Shanmugasundaram, Natarajan Palaniappan 
    Abstract: CNN-based scene text detection in real-world applications is facing two major issues. The speed-accuracy trade-off is the first issue. Secondly, the arbitrary-shaped text instance is to be modelled. This work solves both issues by using ResNet-152 backbone-based pixel aggregation network. Since ResNet-152 provides better accuracy and performance, ResNet-152 is chosen for backbone. The proposed network has a high speed segmentation head and a learnable post-processing. Feature pyramid enhancement module (FPEM) and feature fusion module (FFM) constitute the segmentation head. For high quality segmentation, multi-level information is introduced by a cascadable U-shaped module that is nothing but FPEM. Different depth features are given by FPEM. FFM will collect these features into a final feature to segment the arbitrary shaped text. Using the predicted similar vectors aggregate precisely text pixels, pixel aggregation (PA) implements this post process which is learnable. The proposed ResNet-152 backbone-based PAN can attain an F-measure of 85.6% on Total-Text dataset.
    Keywords: arbitrary-shaped text detection; scene text detection; curve text detection; text segmentation; DNN.
    DOI: 10.1504/IJCVR.2023.10053234
     
  • Registration of CT and MR image in multi-resolution framework using embedded entropy and feature fusion   Order a copy of this article
    by Sunita Samant, Pradipta Kumar Nanda, Ashish Ghosh, Subhaluxmi Sahoo, Adya Kinkar Panda 
    Abstract: In this paper, a new scheme for the registration of brain CT and noisy MR images is proposed in a multi-resolution framework based on the notions of embedded entropy and nonlinear combination of the mutual information (MI) corresponding to Renyi’s and Tsallis entropy. Gabor and Sobel’s features are fused probabilistically and the registration is carried out in fused feature space. The weights for the fusion of the two distributions are obtained using the Bhattacharyya distance as the similarity measure. Registration parameter is obtained at different resolutions by maximising the combined mutual information obtained at different resolutions. The proposed algorithm is tested with the real patient data obtained from Retrospective Image Registration Evaluation (RIRE) database. It is found that the optimum registration parameter obtained at a low resolution of (64 x 64) has high accuracy. The proposed scheme exhibits improved performance as compared to other existing algorithms.
    Keywords: multi-modal image registration; embedded entropy; mutual information; fused feature space; multi-resolution.
    DOI: 10.1504/IJCVR.2023.10053410
     
  • Wireless underwater channel modelling for acoustic communication   Order a copy of this article
    by Sanapala Umamaheswararao, M.N.V.S.S. Kumar, R. Madhu 
    Abstract: Underwater channel modelling is very essential to establish acoustic communication underwater. It helps AUVs to navigate safely by avoiding collisions. But lot of complexities involved in acoustic communication as there will be reflections from the water surfaces. The main factors that are influencing underwater communication are transmission loss, noise, multipath, Doppler spread, and propagation delay. These parameters made available the acoustic channels bandwidth restricted and drastically subject to both range and frequency. The terrestrial communication parameters are not suitable to the underwater communication and hence require a dictated system design. The underwater channel modelling includes the finding of signal to noise ratio (SNR) at the receiver, transmission path loss and path gain for a particular path due to multipath propagation, and the noise level in the propagation path. An underwater channel communication model for sonar data is developed by considering the case of multipath propagation in shallow water.
    Keywords: channel modelling; multi-path propagation; path loss.
    DOI: 10.1504/IJCVR.2023.10054629
     
  • Integrating Thepade SBTC and Niblack thresholding features for identification of land usage from aerial images using ensemble of machine learning algorithms   Order a copy of this article
    by Sudeep D. Thepade, Sandeep Chauhan 
    Abstract: The aerial images taken by satellites and drones are used to identify different types of land utilisation. Land use identification (LUI) is attempted using several machine learning (ML) algorithms, which are trained with the aerial image features extracted using global or local content. The work here presents a fusion of globally extracted Thepade SBTC (TSBTC) features and local extracted Niblack thresholding features for LUI. Extraction of features from an aerial image using TSBTC is done with ten variations from 2-ary to 11-ary. Nine ML classifiers and ensembles are considered. The UC-Merced-dataset, containing 2100 photos split over 21 different land-use-types, is used for experimentation. The performance metrics alias F-measure, accuracy and MCC performance are used. The fusion of TSBTC and Niblack has given a better LUI. In TSBTC variations, TSBTC 11-ary has given better LUI. The ensembles have given better LUI. The IBK + RF + SL ensemble performs better.
    Keywords: land use identification; LUI; Niblack; Thepade sorted BTC; Thepade sorted BTC N-ary; aerial image.
    DOI: 10.1504/IJCVR.2023.10055668
     
  • Enhancing stock market prediction through image encoding, pattern recognition, and ensemble learning with custom error correction techniques   Order a copy of this article
    by Ravi Prakash Varshney, Dilip Kumar Sharma 
    Abstract: Financial forecasting is a crucial task in the financial sector and is currently being addressed using various technical pricing patterns. However, the conventional techniques suffer from limitations such as time-consuming computations and lower accuracy due to the stochastic dependency between historical and future values. This research aims to bridge the gap in financial forecasting by proposing a hybrid model that combines time series analysis using LSTM with image processing techniques such as Gramain Angular Field, line plot methodology, and error correction techniques. The proposed approach leverages the strengths of both techniques to provide a reliable forecasting solution that can capture the stochastic dependency between past and future values. The study aims to contribute to the field of machine learning by providing a novel approach to financial forecasting and expanding the research on intelligent processing methods. For Apple, when compared the LSTM model result with final model there is ~48% decrease in test RMSE and ~57% decrease in test MAE. For Amazon, when compared the LSTM model result with final model there is ~14% decrease in test RMSE and ~10% decrease in test MAE. Moreover, the proposed model outclasses the state-of-art model and addresses the overfitting in them.
    Keywords: time series forecasting; Gramain Angular field; GAF; computer vision; pattern recognition; image encoding; error correction.
    DOI: 10.1504/IJCVR.2023.10055874
     
  • Experimental and simulation study of a four-degrees of freedom robot arm moving through space planner path   Order a copy of this article
    by Hajar Abd Al-Sattar Ali, Hatem H. Obeid 
    Abstract: In this work, a 4-DOF robot arm manipulator was built and tested using the software programs LABVIEW and SOLIDWORKS. The model tracks a horizontal path at four times periods and is tested in experimental and theoretical environments. The aim study of this work was to make CAD models of the four degrees of a freedom robot arm and then use LabVIEW programming to control how its moves. Find the optimum time for the path and minimum power consumption to accomplish the task. Also, the kinematics and dynamics parameters of the robot arm were calculated and tested through the proposed intervals. Four case studies are utilised to evaluate the modules performance at two, four, six and eight second. By observing the results, it was investigated that the optimum time to complete the task is between two and four seconds and the power consumption reduced by 99.8%.
    Keywords: robotic; arm; power consumption; time periods; kinematics; kinetics; real-time.
    DOI: 10.1504/IJCVR.2023.10055875
     
  • Fuzzy text/non-text classification of document images based on morphological operator, wavelet transform, and strong feature vector   Order a copy of this article
    by Mobina Ranjbar Malidareh, Amir Masoud Molaei 
    Abstract: In text retrieval systems, the classification of textual and non-textual content is known as an introduction to accessing semantic information in document images. In this paper, a new structure based on morphological operator, wavelet transform, and strong feature vector extraction is proposed for classifying textual and non-textual content in document images regardless of text language. In this structure, the image is segmented by an effective mechanism. By training the pattern of textual and non-textual areas in the images, the text and non-text regions are determined by a fuzzy classifier. The texture features such as coarseness, directionality, contrast and roughness, and features extracted from the wavelet transform sub-bands are used to classify and label the regions. The proposed method is evaluated on a database of textual and non-textual images derived from document images available on the Internet. The simulation results show the high efficiency of the proposed method in the segmentation and classification of the image components. It provides an accuracy of 90.1% for the classification of image regions.
    Keywords: fuzzy classification; morphological operator; segmentation; strong feature vector; text/non-text separation; wavelet transform.
    DOI: 10.1504/IJCVR.2023.10056059
     
  • Improved green wireless sensor network using modified prediction oriented distributed clustering   Order a copy of this article
    by Pranati Mishra, Ranjan Kumar Dash 
    Abstract: In this paper, an improved clustering protocol is suggested for WSNs, in which a new cluster head strategy for non-uniformly distributed nodes and network lifespan is introduced the network follows a mess topology of wireless sensor nodes which report to a main station to observing and study. Geographical and contextual analysis and visualisations are provided. It is considered as a green network because the overall network consumes less energy. Main application of this research work includes data observation and communication of data to the base station. It includes multi-level node clustering to efficiently save energy at multiple levels. Priorly the PODC algorithm shows the optimised result in comparison to EADC and SA-EADC algorithm. In this work improved PODC works with the additional multilevel clustering. The result shows the improvement in network lifetime and energy dissipation among sensor nodes and it is observed that the proposed improved PODC performs far better than them. Therefore, it can be safely concluded that proposed protocol improves the network life span while maintaining original sensing coverage level for the network.
    Keywords: green network; improved PODC; EADC; SA-EADC; multilevel clustering.
    DOI: 10.1504/IJCVR.2023.10056160
     
  • Deep learning approach to pedestrian detection and path prediction   Order a copy of this article
    by Ujwalla Gawande, Kamal Hajari, Yogesh Golhar 
    Abstract: Pedestrian detection and path prediction are significant challenges in vision-based surveillance systems. Because of variances in pedestrian postures and scales, backdrops, and occlusion, advanced computer vision applications face many obstacles. To address these issues, we provide an improved YOLOv5 pedestrian recognition and path prediction model. To begin, the revised YOLOv5 model is employed to determine pedestrians of varied sizes and proportions. A pedestrian’s path is estimated using a path prediction approach. The proposed method addresses partial occlusion situations in order to reduce object occlusion-induced progression and loss, as well as linking recognition results to motion properties. The route prediction system then analyses motion and directional data to estimate the direction of pedestrian movement. The results of the experiments significantly enhanced the performance on datasets from Caltech, INRIA, MS COCO, ETH, KITTI, and the proposed pedestrian dataset. Improved YOLOv5 outperforms existing methods. The Caltech dataset has the lowest log-average miss rate (8.32%), followed by the INRIA dataset (7.32%) and the ETH dataset (32.64%). Results from the KITTI dataset were promising, at 76%, 64%, and 60%. 8.69% miss rate on the proposed pedestrian dataset and 8.57% on the MS COCO dataset. Finally, we conclude and look into future research.
    Keywords: convolutional neural network; CNN; deep learning; YOLOv5; pedestrian detection; tracking; path prediction.
    DOI: 10.1504/IJCVR.2023.10056182
     
  • Machine learning approaches for early detection and management of musculoskeletal conditions   Order a copy of this article
    by Pawan Whig, Ebtesam Shadadi, Shama Kouser, Lathifah Alamer 
    Abstract: Musculoskeletal conditions have a significant impact on quality of life. This study explores the use of machine learning algorithms for early detection and management of such conditions. Different models were evaluated using a dataset of musculoskeletal images and clinical information. Results demonstrate accurate classification with high sensitivity and specificity. A neural network was developed for detecting chronic lower back pain, achieving an impressive validation F1 score of 89%-93%. This highlights the potential of artificial intelligence in improving early detection and management. Future research should address data outliers to enhance model performance. Overall, neural networks are a valuable tool for early detection and management of musculoskeletal conditions, leading to improved patient outcomes. These findings suggest promising avenues for future research and implications for early detection and management in this field.
    Keywords: musculoskeletal conditions;arthritis; fractures; spinal problems; machine learning; early detection.
    DOI: 10.1504/IJCVR.2023.10057385
     
  • Localisation and classification of surgical instruments in laparoscopy videos using deep learning techniques   Order a copy of this article
    by Avanti Bhandarkar, Priyanka Verma 
    Abstract: Surgical trainees often use laparoscopic surgery videos to understand the appropriate use of instruments and visualise the surgical workflow better, but these videos may be difficult to interpret without proper annotations. In recent times, neural networks have emerged as an accurate and effective solution for instrument detection and classification in surgical video frames, which can subsequently be used to automate the annotation process. The proposed implementation uses faster-RCNNs and bidirectional LSTMs with (and without) time-distributed layers and attempts to solve some of the problems commonly faced while developing deep learning models for surgical image and video data: severe class imbalance, inaccuracies during multi-label classification and a lack of spatiotemporal context from adjacent video frames. The bidirectional LSTM with time-distributed layers achieved an average accuracy of 80.20% and an average F1 score of 0.7176 on the M2CAI16 tool dataset, while also achieving 63.49% average accuracy and an average F1 score of 0.522 on unseen data. Jaccard distance and Hamming distance have also been used as object detection-specific metrics; the same model registered the lowest values for both distances, implying accurate localisation and identification of surgical instruments.
    Keywords: deep learning; surgical instrument detection; surgical instrument classification; surgical instrument localisation; data augmentation; transfer learning; faster-RCNN; region-based convolutional neural networks; bidirectional LSTMs; long short-term memory networks; Jaccard distance; Hamming distance.
    DOI: 10.1504/IJCVR.2023.10057447
     
  • Holistic knuckle recognition through adept texture representation   Order a copy of this article
    by Neeru Bala, Anil Kumar, Rashmi Gupta, Ritesh Vyas 
    Abstract: In topical years, substantiation of individuals through their finger knuckle patterns has turned into an extremely dynamic area of exploration. Finger knuckle patterns are the inimitable creases existent on the posterior surface of the hand which is more expedient than other hand related modalities like fingerprint and palmprint, as the posterior surface of hand is less abraded in contrast to interior hand. This work presents an effective knuckle-based recognition framework via fusion of base, minor and major finger knuckle patterns of fingers of the individual for boosted recognition. For this, all the finger knuckle patterns are segmented and features are extracted explicitly using an efficient feature descriptor named curvature Gabor filter (CGF). In order to substantiate the proposed methodology, rigorous investigations have been performed on a publicly accessible large hand dorsal database named PolyU-Hand Dorsal (HD) dataset. Knuckles are integrated in three different ways to investigate the effect of their fusion, named fusion over knuckle, fusion over finger and fusion over hand. All the strategies mentioned have supported their magnified performance than individual knuckle recognition framework, whereas fusion over hand outshined with tiniest EER of 0.2009.
    Keywords: information security; multimodal biometrics; information fusion; knuckle recognition; score level fusion.
    DOI: 10.1504/IJCVR.2023.10057530
     
  • A multi-modal image encoding and self-attention-based transformer framework with sentiment analysis for financial time series prediction   Order a copy of this article
    by Ravi Prakash Varshney, Dilip Kumar Sharma 
    Abstract: In this paper, we propose a novel approach for financial time series forecasting using feature selection, image encoding, and a self-attention-based CNN transformer. We use Markov transition field and candlestick chart encoding to extract features from historical stock data. Additionally, we incorporate the sentiment analysis of the financial news data in our model to improve the forecast accuracy. The proposed approach is compared to traditional time series forecasting methods, and the results show that our method outperforms the traditional method in terms of forecasting accuracy. The proposed approach can be used to improve risk management and make more informed trading decisions. Our experiments demonstrate that the proposed framework achieved an improvement of approximately 17.8% in root mean squared error and ~38.7% in mean absolute error for securities lending dataset and ~71.5% improvement in root mean squared error and around ~83.2% improvement in mean absolute error for pricing dataset.
    Keywords: candlestick image encoding; computer vision; convolutional neural network transformer; feature selection; Markov transition field image encoding; multivariate time series; MTS; pattern recognition; long-short term memory; LSTM; sentimental analysis.
    DOI: 10.1504/IJCVR.2023.10057531
     
  • Improved classification of histopathological images with feature fusion of Thepade SBTC and Sauvola thresholding using machine learning   Order a copy of this article
    by Sudeep D. Thepade, Mangesh S. Dudhgaonkar Patil 
    Abstract: Histopathological images play a significant role in selecting effective therapeutics and identifying disorders like cancer. Digital histopathology is a crucial advancement in contemporary medicine. The growth and spread of cancer cells within the body can be significantly controlled or stopped with early identification and therapy. Many machine learning (ML) algorithms are used to study the images in the dataset. Feature extraction is done using Sauvola thresholding and Thepade sorted block truncation code (TSBTC). This paper presents a fusion of the features computed using the TSBTC and Sauvola thresholding method for improved classification of histopathological images. The experimental validation is done using 960 images from KIMIA PATH 960 dataset with the help of performance metrics like sensitivity, specificity, and accuracy. The superior performance is shown in TSBTC 9-ary and Sauvola thresholding feature fusion using logistic model tree (LMT) classifier with 97.6% accuracy in ten cross-fold validation scenarios.
    Keywords: classification; binarisation; histopathological; feature fusion; ensembles; KIMIA_PATH_960; Thepade SBTC; classifiers.
    DOI: 10.1504/IJCVR.2023.10058302
     
  • A primitive analysis of resonance frequency and stability simulation of a 2D SCARA drawing robot system for BCIs   Order a copy of this article
    by Ellis Iver David, James Edward Rowe, Yeon-Mo Yang 
    Abstract: In recent years, selective compliance assembly robot arm (SCARA) manipulators related to brain-computer interfaces (BCIs) have been gaining in popularity in industrial applications owing to their significant adaptability. One popular application concerns commercially available drawing robots. For example, the tip ring sleeve drawbot by Hart and Ragan uses an audio output. Thus, WAV files with pulse width modulation are used to control the servomotors. After constructing a drawing robot prototype and analysing the impulses and responses, structural flaws were noticed in this particular design from the perspective of stability, limiting the quality of the final drawing. Indeed, the robot was designed to follow single-line paths, resulting in very sudden movements (e.g., stop-start motions). This caused vibrations in the arm that were more noticeable at high speeds. To counter or mitigate the shaking of the robot arm, in this study, a kinematic model and stability simulation for a 2D (dimensional) SCARA drawing robot arm were constructed with the aim of improving the overall stability. The eventual aim was to find a model for describing the motions of all two-degree-of-freedom (DOF) rotational arm robots to allow for quick access or derivation of the optimal functional parameters of such robots.
    Keywords: brain-computer interface; BCI; SCARA; drawbot synthesiser; stipple gen; travelling salesman problem; TRS; statistical signal processing; stability; transfer function; impulse response; IR; step response; SR.
    DOI: 10.1504/IJCVR.2023.10058433
     
  • An efficient deep convolutional neural network-based safety monitoring system for construction sites   Order a copy of this article
    by V. Ashwanth, Dhanya Sudarsan 
    Abstract: Worker safety and health are paramount concerns, especially in high-risk occupations such as construction works. Monitoring workers to ensure proper usage of personal protective equipment (PPE) at construction sites is essential. However, manual surveillance via CCTV footage is time-consuming. This paper proposes an automated approach for construction site monitoring without human intervention. Initially, YOLOv4 is employed for construction worker detection, with subsequent division of the bounding boxes into four halves. EfficientNet is then utilised to analyse these cropped sections and identify specific PPE components. Additionally, construction tools and equipment are recognised, and a safety score is assigned based on worker proximity to these objects. Unsafe workers are flagged as danger zone in each frame, alongside the marking of workers. This approach streamlines safety monitoring processes while ensuring worker well-being.
    Keywords: computer vision; YOLOv4; construction safety; EfficientNet-B5; transfer learning; PPE; custom labelling; safety detection; object detection; image classification; machine learning.
    DOI: 10.1504/IJCVR.2023.10058756
     
  • An approach for speaker diarisation using whale-anti coronavirus optimisation integrated deep fuzzy clustering   Order a copy of this article
    by K. Vijay Kumar, Ramisetty Rajeswara Rao 
    Abstract: In this paper, Anticorona whale optimisation (ACWOA) method is developed for speaker diarisation which is then used to train the deep fuzzy clustering (DFC) algorithm for final clustering. To extract relevant characteristics, such as Mel frequency cepstral coefficients (MFCCs), line spectral frequencies, and line prediction cepstral coefficients (LPCCs), the input audios are fed into a feature extraction procedure (LSF). Music and silence removal are used in the speech activity detection (SAD). After identifying speech activities, the speakers are segmented using a Bayesian inference criterion (BIC) score. The ACWOA-based DFC outperformed other methods with best testing accuracy of 0.891, lowest diarisation error, false discovery rate (FDR), false negative rate (FNR) and false positive rate (FPR) of 0.618, 0.289, 0.148, and 0.130. The proposed approach outperforms the existing approaches active learning, DE+K-means, LSTM, MCGAN, and ANN-ABC-LA in terms of testing accuracy for test case 1 by 9.31%, 7.40%, 6.73%, 5.49%, and 3.59%.
    Keywords: speaker diarisation; deep fuzzy clustering; DFC; Bayesian inference criterion; BIC; speech activity detection; SAD; speaker segmentation; Mel frequency cepstral coefficients; MFCCs; line prediction cepstral coefficients; LPCCs.
    DOI: 10.1504/IJCVR.2023.10059523
     
  • A sine-cosine algorithm blended grey wolf optimisation algorithm for partitional clustering   Order a copy of this article
    by Gyanaranjan Shial, Chita Ranjan Tripathy, Sabita Sahoo, Sibarama Panigrahi 
    Abstract: Over last few decades, partitional clustering algorithms have been emerged as one of the most promising clustering algorithms that find groups among data items. Motivated from this, we have proposed a hybrid sine-cosine algorithm (SCA) blended grey wolf optimisation (GWO) algorithm for partitional data clustering. This algorithm selects near-optimal cluster centres using leadership approach of GWO and explorative strategy of SCA. Here, the sine and cosine functions are used to generate more diversified solutions around the mutant wolf of each search agents. Therefore, a tradeoff is maintained between exploration and exploitation which enjoys the benefits from both the algorithms. An extensive simulation work is carried out for clustering 11 benchmark datasets using four performance measures. Additionally, a comparative performance analysis (statistical) is conducted against GWO, PSO, SCA, JAYA and K-means using Duncans multiple range test and Friedman and Nemenyi hypothesis test. The test confirms the supremacy of our proposed algorithm.
    Keywords: grey wolf optimiser; JAYA algorithm; sine-cosine algorithm; SCA; particle swarm optimisation; PSO; partitional clustering; K-means algorithm.
    DOI: 10.1504/IJCVR.2023.10059975
     
  • Machine learning-based iris liveness detection using fusion of Thepade SBTC and Niblack binarisation technique   Order a copy of this article
    by Sudeep D. Thepade, Bhumika Patil, Smita Khade 
    Abstract: Liveness authentication is crucial in the observation environment, especially at border crossings and locations with a combat or buffer zone. It is determined in this study how to assess the liveness of the iris template to avoid fraud. This study uses a handcrafted method called TSBTC and additional binarisation techniques to survey the IIIT Delhi and Clarkson datasets and improve accuracy. A current requirement is to acquire an ILD dataset that covers all typical iris spoofing attempts. Three classifications of eyes are included in the dataset: normal, coloured, and transparent. On every image TSBTC, TSBTC + Niblack binarisation is applied, and further comparison is done on the based-on accuracies. Different classifiers are used for comparison, and Weka software has been used to compare the accuracies of the classifiers used. The study has investigated the method for extracting the local and global features from iris images.
    Keywords: iris liveness detection; ILD; Biometrics; Niblack binarisation; machine learning; feature fusion; Thepade SBTC; security.
    DOI: 10.1504/IJCVR.2024.10061526
     
  • An accurate and efficient multi-task brain tumour detection with segmented MRI images using auto-metric adolescent neural network   Order a copy of this article
    by Amrapali Kishanrao Salve, Kalpana C. Jondhale 
    Abstract: Early diagnosis of a brain tumour (BT) boosts that the patient will survive after medication. Several existing methods for detecting BTs are intrusive, cumbersome, and vulnerable to human errors. This manuscript introduces a novel hybrid method, auto-metric graph adolescent identity neural network (AGAINN), for accurate and efficient human BT segmentation and multi-task detection using magnetic resonance imaging (MRI) images. The input brain MRI images are given to structural interval gradient filtering (SIGF) based preprocessing method for eliminating noise, resizing and increasing the excellence of brain images and then provided into adaptive transfer density peaks search (ATDPS) clustering based segmentation for finding the region of interest (RoI) of the preprocessed image. Then, three types of feature extraction are done using empirical wavelet transform (EWT) and grey-level co-occurrence matrix (GLCM). The extracted image features are transferred into the suggested scheme for detecting tumour and also the types of tumour also performance analyses are compared using several metrics, statistical tests and improved accuracy rate.
    Keywords: benign; malignant; brain tumour; magnetic resonance imaging; MRI; clustering; statistical analysis.
    DOI: 10.1504/IJCVR.2024.10061584
     
  • Machine vision algorithm for MCQ automatic grading - MVAAG   Order a copy of this article
    by Aaron Rasheed Rababaah 
    Abstract: Multiple-choice questions (MCQ) predated the first digital computer. MCQ was created as a response to demands for objective and standardised tests for large populations of test takers as in national tests in education, military assessments, surveys, etc. There has been an evolution in the used technology to automate MCQ grading including optical mark recognition (OMR), optical character recognition (OCR), digital image processing (DIP), etc. In this article, we propose a robust solution for MCQ automatic grading using image processing techniques MVAAG. Our approach uses an unexpansive digital camera or a scanner to scan the answer sheets which are regular A4 papers. The scanned images are then put through a sequence of DIP operations including colour transformation stages, thresholding, morphology, connected components analysis, etc. MVAAG was validated using extensive experimental testing and found to be effective and efficient compared to manual methods as well as current modern technologies.
    Keywords: multiple-choice questions; MCQ; automating MCQ grading; image processing; bubble-based answer sheets processing; machine vision; robust MCQ auto-grading.
    DOI: 10.1504/IJCVR.2024.10061643
     
  • Synergising machine learning and blockchain for enhanced fraud detection   Order a copy of this article
    by Pawan Whig, Rattan Sharma 
    Abstract: The convergence of blockchain technology and machine learning represents a powerful paradigm shift in revolutionising fraud detection within the financial sector. This abstract highlights the synergistic potential of combining these two cutting-edge technologies, emphasising their collective impact on bolstering fraud detection and prevention strategies. Through the utilisation of blockchain’s inherent features, such as transparency, immutability, and real-time monitoring, in conjunction with the predictive capabilities of machine learning, including exploratory data analysis (EDA), XGBoost, and random forest (RF), our research has achieved an outstanding accuracy rate of approximately 99.9% in fraud detection. This fusion empowers the identification of anomalies in real-time, the issuance of proactive alerts, and the development of adaptable models that continuously evolve to address emerging fraud patterns. Furthermore, the decentralised and collaborative nature of blockchain facilitates secure data sharing and leverages collective intelligence, further enhancing the precision of fraud detection. The profound implications of this integration empower financial institutions to significantly elevate transaction security, effectively combat fraudulent activities, and foster greater trust in the ever-evolving digital financial landscape.
    Keywords: blockchain; fraud detection; fraud prevention; financial security; digital transactions; decentralised ledger; data integrity; real-time monitoring; patterns; fraudulent activity.

  • Analysing the performance of Viola-Jones and multi-task convolution neural networks face detection algorithms using real-time video sequences   Order a copy of this article
    by M. Mohana, P. Subashini 
    Abstract: In recent years, face detection has been a hot research area in computer vision, serving as the first step in both face recognition and facial expression detection. However, several challenges exist when detecting faces in real-time, including pose variations, varying lighting conditions, and partial occlusions on face and video images. Despite the existence of numerous face detection algorithms, this study focuses on evaluating the Viola-Jones and multi-task convolutional neural network (MTCNN) algorithms, which have been widely used for face detection in several research studies. The objective of this comparative study is to analyse these two widely used face detection algorithms in the context of the aforementioned challenges using real-time video sequences and benchmark datasets. For this study, video sequences were collected from the LIRIS children spontaneous facial expression video database, and a real-time video dataset was captured in the centre for machine learning and intelligence laboratory. The results show that MTCNN achieved an average true positive rate accuracy of 94.33%, whereas the Viola-Jones algorithm achieved 73.33% accuracy when conducting experiments with various face detection challenge scenarios.
    Keywords: face detection; Viola-Jones; MTCNN; computer vision; face detection challenges.
    DOI: 10.1504/IJCVR.2024.10061831
     
  • Generalised video anomaly detection: a systematic review   Order a copy of this article
    by S. Anjali, S. Don 
    Abstract: The practice of identifying irregularities and outliers in data is known as anomaly detection. Due to the demand for prompt and precise anomaly detection, this is a growing research area in computer vision. The purpose of this paper is to provide a systematic literature review (SLR) on video anomaly detection by creating the pertinent research questions (RQs). We have considered 83 research articles from reputable databases published between 2012 and 2023. After reviewing these publications, we developed a taxonomy of different video anomaly detection strategies and found that deep learning-based algorithms performed better than traditional ones. The two most common applications of video anomaly detection are seen in the surveillance and healthcare domains. We have identified 16 benchmark datasets, including surveillance and medical datasets. Researchers can use this SLR to look into the most recent studies, applications, datasets, methodologies, challenges and future scope of video anomaly detection.
    Keywords: video anomaly detection; visual anomaly detection; computer vision; deep learning; systematic literature review; SLR.
    DOI: 10.1504/IJCVR.2024.10061832
     
  • Personalised video summarisation using video-text multi-modal fusion   Order a copy of this article
    by Rakhi Akhare, Subhash K. Shinde 
    Abstract: Video summarisation techniques have evolved in recent years, mostly focusing on visual material and ignoring user preferences. In this work, the topic of query-focused video summarisation is addressed. Long videos are given as input, and the goal is to produce a query-focused video summary using the user's sentences rather than keywords. The two parts of the proposed personalised video summarisation (PVS) system are the query-relevance computation module and the feature encoding network. In order to provide a customised video summary, the suggested end-to-end approach combines encoded visual and textual information and assigns a query relevance score. The suggested PVS model is tested using the fast-text and Resnet embeddings on the video-query dataset. In comparison to various combinations of language and vision models, the suggested PVS model performs better and achieves an accuracy of 0.53%. This study assists the research community to work in the field of multimodal video summarisation.
    Keywords: personalised video summarisation; PVS; word embedding; feature fusion; multi-modal video summarisation; query based video summarisation.
    DOI: 10.1504/IJCVR.2024.10061911
     
  • Effect of layers on CNN model accuracy for facial emotion recognition   Order a copy of this article
    by M.D. Rakshith, Harish H. Kenchannavar 
    Abstract: Facial expression recognition has become a very tedious task in the domain of image recognition. Image classification involves drastic usage of deep learning techniques. This has resulted in the increased usage of convolutional neural networks (CNNs) for recognising emotions through facial expressions. In deep learning, developing the compact network architecture that achieves high accuracy on the data of interest is a significant challenge. In the presented article, a novel optimised CNN (O-CNN) model consisting of five convolution layers is proposed and the effect of layers on the test accuracy is observed on FER-2013 dataset. The hyperparameters of CNN such as kernel size, number of kernels, activation function, dropout, number of hidden units, batch size and epochs are considered for experimentation. By keeping the constant kernel size, the convolution layers and kernels are varied for the model evaluation. The test accuracy obtained by the O-CNN model on FER2013 dataset without batch normalization and for 50 epochs is 64.17%.
    Keywords: facial expression; convolutional neural network; CNN; hyperparameters; deep learning.
    DOI: 10.1504/IJCVR.2024.10061999
     
  • Deep learning-powered test case prioritisation in continuous integration: a comparative study and efficiency analysis   Order a copy of this article
    by Sheetal Sharma, Swati V. Chande 
    Abstract: The empirical study introduces a deep learning-based approach for prioritising test cases in continuous integration (CI) environments, leveraging historical CI data to optimise resource allocation and reduce testing time. The model achieved a remarkable 100% accuracy in prioritisation, outperforming traditional methods. Compared to decision tree, it achieved perfect accuracy with fewer test cases. Against random forest, it had a higher fault detection rate while maintaining efficiency. When compared to neural network, it struck a balance between fault detection and execution time. This research highlights deep learning’s potential in transforming CI/CD testing strategies and software development practices.
    Keywords: test case prioritisation; continuous integration; CI; deep learning; comparative analysis; efficiency; accuracy; fault detection; software development.
    DOI: 10.1504/IJCVR.2024.10062000
     
  • Prediction of fine-grained human activities in videos using pose-based and object-based features   Order a copy of this article
    by Ashwini S. Gavali, S.N. Kakarwal 
    Abstract: Human activity prediction in videos deals with anticipating the intention of human activity before it is fully observed. Activity prediction becomes more challenging when fine-grained details are to be considered. This paper presents a deep learning-based approach for predicting complex, fine-grained, and long-duration human actions in videos. Along with prediction, our approach also localises human action spatially with bounding boxes. This approach works by considering the sequential nature of the activities in the video. Each high-level activity is represented as a sequence of local actions (low-level activities). Given a partially observed video, local actions are detected and tracked first, and then these local detections are used for predicting future high-level actions. Fine-grained activity involves interactions with different objects, so we used a combination of the human pose feature and the object feature to predict fine-grained activity more accurately. We evaluated results on the publicly available MPPI cooking activity dataset.
    Keywords: activity prediction; fine-grained activity; local actions; ResNet-50; YOLO object detection; compact prediction tree; convolutional neural network.
    DOI: 10.1504/IJCVR.2024.10062050
     
  • A deep learning framework for disaster recognition and classification of the damaged regions   Order a copy of this article
    by Jaychand Loknath Upadhyay, Himanshu Gharat, Reetik Gupta, Pallav Savla 
    Abstract: Natural disasters are rare, but when they occur, they generally cause colossal damage. Due to climate change, the number of disasters is increasing which demands enhancement in disaster response to reduce and recover the amount of devastation caused due to disasters. A rapid assessment of the situation could facilitate an improved strategy for disaster management and recovery. However, these disasters often cause infrastructural destruction which makes the affected regions inaccessible. In such difficult conditions, aerial images captured through drones can be momentous to identify the regions of damage. This study provides a methodology to classify the disaster images using deep learning which could help to identify the regions of damage. To perform this classification a CNN model was used which was trained on various disaster images through transfer learning. The model was trained on the AIDER dataset and provided an F1-Score of 96.8%. The performance of the proposed model is also verified with real-time videos covering the recording of various disasters. The results obtained in the experiment emphasise disaster response management and ways by which the proposed model could assist the role of deep learning to expedite rescue operations.
    Keywords: disaster management; disaster recognition; damaged region classification; deep learning; convolution neural network; CNN; transfer learning.
    DOI: 10.1504/IJCVR.2024.10062177
     
  • Using fuzzy similarity measure in content-based video retrieval based on image query   Order a copy of this article
    by Fatemeh Taheri, Kambiz Rahbar 
    Abstract: The primary challenge of video retrieval systems is to retrieve videos with the highest similarity to user queries. The process of feature extraction and similarity measurement plays a crucial role in the results of content-based video retrieval. This article introduces a fuzzy similarity metric for comparing and retrieving similar videos using image-queries to address the issue of uncertainty in the similarity between queries and video frames. To this end, features are extracted from both image-query and each video frame using a pre-trained VGG-16. Similarity metrics, including frequency and continuity in similar frames to the image-query, form the basis for calculating the similarity for retrieving videos. The proposed method compensates for uncertainty in image-query and dataset videos’ similarity measurements, leading to improved retrieval results. The best evaluation results with the mean accuracy metric on the UCF-11 dataset for retrieving one and ten top samples are reported as 0.862 and 0.689 respectively.
    Keywords: fuzzy similarity; content-based video retrieval; image query; VGG-16 neural network.
    DOI: 10.1504/IJCVR.2024.10062185
     
  • Orthogonal opponent colour local binary patterns: a new colour-texture descriptor for content based-image retrieval   Order a copy of this article
    by Rahima Boukerma, Bachir Boucheham, Salah Bougueroua 
    Abstract: Opponent colour local binary patterns (OCLBP) is one of the first extensions of greyscale LBP to colour images, which has been proven to be an effective descriptor for extracting colour texture features. In order to improve the OCLBP performance for image retrieval and increase its invariance to illumination change, we propose in this paper a new scheme for computing the OCLBP’s inter-channel features. Unlike OCLBP, where the inter-channel features are computed by considering the circular neighbouring of the centre pixel, our proposed descriptor named orthogonal OCLBP (O-OCLBP) is constructed by considering the orthogonal neighbouring of the centre pixel. Moreover, the proposed scheme is applied to the improved version of OCLBP (IOCLBP) to derive a new descriptor named orthogonal IOCLBP (O-IOCLBP). Experiments performed over eight databases demonstrate that the proposed descriptors significantly improve retrieval performance on almost all databases, and show generally better results compared to some of the state-of-the-art descriptors.
    Keywords: CBIR; IOCLBP; LBP; multichannel feature extraction; OCLBP; orthogonal-IOCLBP; orthogonal-OCLBP.
    DOI: 10.1504/IJCVR.2024.10062221
     
  • Recent security challenges and robust techniques in colour image watermarking   Order a copy of this article
    by Chandan Kumar, Dinesh Dinu 
    Abstract: Digital image watermarking is a widely used technique for ensuring the authenticity and security of digital images on the internet. While greyscale and colour image watermarking are both commonly used techniques, however this paper specifically reviews the most recent security issues related to colour image watermarking. Colour image watermarking poses unique security challenges, including vulnerability to attacks that can remove or alter the watermark, compromising the image’s authenticity and security. To address these challenges, researchers have developed robust watermarking techniques that embed the watermark in multiple colour channels of the image, making it difficult to remove or alter without affecting the image quality. Despite ongoing security challenges, the continued development of these techniques will help to enhance the security of digital images on the internet. This paper provides a comprehensive review of the latest developments in colour image watermarking, including security and robust techniques to address these challenges.
    Keywords: spatial and transform domain techniques; image watermarking; embedding and extraction; colour images.
    DOI: 10.1504/IJCVR.2024.10062255
     
  • Motion control of 3-DoF delta robot using adaptive neuro fuzzy inference system   Order a copy of this article
    by Riyadh A. Sarhan, Zaid H. Rashid, Mohammed S. Hassan 
    Abstract: Delta robot are widely used to achieve positioning tasks with high speed and accuracy, which require a control model to move the platform of delta robot along a specific coordinate. This paper presents a control system based on fuzzy controller to achieve the motion control and applies this system on the model of delta robot, which is capable of carrying out the motion with three translational degrees of freedom. The proposed control system evaluates the applied angular position on the motor’s joint depended on the output of inverse kinematics and ANFIS then move the end effector in the translation coordinates (X, Y and Z). Results from both inverse kinematics equations and from the delta robot after applied proposed control system show that there is a difference in the translation coordinates by around 5 cm in X direction, 2 cm in Y direction and 1 cm in Z direction. This difference due to the effect of the friction in the joint of the delta robot, which is negligible in the inverse kinematics analysis. Finally, the validation of proposed control system foe a delta robot is verified with minimum errors.
    Keywords: delta robot; inverse kinematics; fuzzy control; adaptive neuro fuzzy interference system; ANFIS.

  • Investigating dementia: an analysis on machine learning strategies   Order a copy of this article
    by Tanvi Kapdi, Apurva Shah 
    Abstract: Dementia, an ongoing and moderate mental declination of cerebrum capability brought about by disability, is turning out to be more pervasive because of the maturing populace. A significant challenge in dementia is accomplishing exact reasonable determination. Lately, neuroimaging with PC helped calculations and has made surprising advances in tending to this test. The outcome of these techniques is generally ascribed to the application of AI strategies for neuro-imaging. In this review paper, we present a meticulous overview of robotised indicative methodologies for dementia utilising clinical picture examination. Given the thorough survey of the current efforts, it has been observed that, while a large portion of the examinations zeroed in on common mental illness, late exploration has shown sensible execution in the ID of disparate strains of dementia stays a significant challenge. Multimodal imaging assessment profound research draws near has shown optimistic sequel in the conclusion of the strains of dementia.
    Keywords: artificial intelligence; machine learning; deep learning; mental health; dementia.
    DOI: 10.1504/IJCVR.2024.10062322
     
  • Optimisation of weed management by image segmentation in precision agriculture   Order a copy of this article
    by Mohammed Habib, Salma Sekhra, Adil Tannouche, Youssef Ounejjar 
    Abstract: Accurate weed detection remains crucial for ultra-localised control in robotic solutions, simulating manual weeding in agriculture. Although many studies have been conducted in the field of weed detection using machine learning, most have focused mainly on direct detection, which can present challenges in the face of weed diversity. In this study, we propose an integrated approach based on vegetation/soil segmentation, followed by discrimination between crops and weeds using an object detector. Segmentation models such as UNet, FPN, and LinkNet have been thoroughly trained to discriminate efficiently between vegetation and soil. The results obtained are promising, with the trained models being able to generate binary images (masks) with an accuracy (Jaccard and Dice similarity indices) of over 89%. In addition, the execution speed reached 217 frames per second (Fps). The integration of the localisation results from the detection model with the segmented images provides a robust method for accurately determining the position of weeds in the agricultural context, opening up new prospects for automated, targeted weed control solutions.
    Keywords: images segmentation; computer vision; convolutional neural networks; agricultural images; weed detection; smart farming; precision farming; deep learning.
    DOI: 10.1504/IJCVR.2024.10062366
     
  • Enhanced licence plate detection using YOLO framework in challenging environments   Order a copy of this article
    by Sahil Khokhar, Deepak Kedia 
    Abstract: The need for monitoring and controlling traffic for applications such as toll collection, parking, and law enforcement has grown significantly in the last few years. ALPR systems are accomplishing the monitoring of vehicles on a massive scale. The ALPR systems have been a research topic for many years, yet the ground deployment has yet to catch up. The primary reason for this issue has been the systems poor efficiency in real-world scenarios compared to the lab testing conditions. The focus of this paper has been on the license plate detection part of the ALPR system. The deep learning-based YOLO frameworks have been employed to detect license plates. The effect of using different datasets for training the network and the efficiency of various versions of the YOLO framework has also been tested in diverse conditions such as low-light low-contrast environments and partial or obstructed plates. The YOLOv7 algorithm achieved an F-score of 98.62% on the AOLP dataset with an average processing time of 15.43 ms. The implemented techniques are accurate and fast enough for real-time applications such as toll collection, traffic monitoring, etc.
    Keywords: automatic license plate recognition; ALPR; object detection; deep learning; machine learning; computer vision; intelligent transportation system.
    DOI: 10.1504/IJCVR.2024.10062468
     
  • The evolution of humanoid robots   Order a copy of this article
    by Tejas Deshpande, Bhumeshwar Patle, Virendra Bhojwani 
    Abstract: The recent development in the field of robotics has expanded the horizons for humans to make autonomous robots work with better accuracy and speed without human intervention in multiple industries. The introduction of bio-mechanics with Leonardo da Vinci’s model widened the scope of robotics leading to the concept of human-shaped robots or humanoids. Today, humanoid robots work alongside humans as well as work without any human intervention. Humanoids study their external environment using multiple sensors and accordingly use artificial intelligence which helps them analyse the situation and develop an appropriate response to external stimuli. From being extremely heavy and inefficient to becoming lightweight, sturdy, efficient, and possessing human-like intelligence, humanoids have been developed in previous years. In this review paper, we discuss the evolution and development of robotics which caused advancements leading to the current generation of humanoids while simultaneously classifying robots from each other using parameters like technological advancements and tasks performed which will help other researchers.
    Keywords: robotics; humanoids; artificial intelligence.
    DOI: 10.1504/IJCVR.2024.10062527
     
  • Node anomaly detection in social networks using cohesive non-local graph convolutional network   Order a copy of this article
    by Yallamanda Rajesh Babu, G. Karthick, V.V. Jaya Rama Krishnaiah 
    Abstract: Users connect with one another and develop relationships on social media platforms. These users have a collection of personal information about themselves on these platforms and communicate with one another. Social networks are becoming more prevalent all across the globe. With all of its advantages, criminality and fraudulent conduct in this medium are on the rise. As a result, there is an urgent need to detect abnormalities in these networks before they do substantial harm. Social network analysis uses graph data structure to represent and manage data. Graphs store data and capture relationships that exist between the nodes. Graphs are a complicated kind of data representation in which each data entry contains attributes and is also connected to other data entries traditional non-deep learning approaches are failing to perform effectively when the size and scope of real-world social networks rise in numbers.
    Keywords: anomaly detection; graph; node anomaly; graph convolutional network; GCN; auto-encoder; CNLGCN.
    DOI: 10.1504/IJCVR.2024.10062528
     
  • Real-time interpretation of American Sign Language using SSD-MobileNet   Order a copy of this article
    by Youssef Farhan, Zineb Haimer, Abdessalam Ait Madi 
    Abstract: Individuals with hearing impairments may struggle with integrating into society because the general population does not understand sign language. Consequently, this can lead to isolation and exclusion from social and professional opportunities. To address this issue, this paper proposes a system for the real-time interpretation of American Sign Language (ASL) using computer vision technology. This system uses a normal webcam to detect and interpret 26 letters of the English alphabet and three auxiliary signs. To achieve this goal, the pre-trained lightweight single-shot multibox detection network model, from the TensorFlow object detection application programming interface (API), SSD-MobileNet was used. After the training phase of the proposed model with a personally collected dataset, the obtained results in testing are promising, with a precision of 82.8% and a recall of 85%. The proposed system represents a forward step in sign language translation. Furthermore, it can be adapted to interpret other sign languages.
    Keywords: American Sign Language; ASL; SSD-MobileNet; TensorFlow object detection API; computer vision.
    DOI: 10.1504/IJCVR.2024.10062706
     
  • Spatial attributes-based segmentation and topological attributes-based recognition algorithm for Myanmar OCR   Order a copy of this article
    by Nwe Nwe Htay Win 
    Abstract: In this paper, we propose a novel segmentation and character recognition algorithm for printed offline Myanmar documents. The main contribution of this paper is threefold: 1) it firstly presents a segmentation algorithm based on spatial attributes of the characters; 2) it then extracts the most relevant features from segmented images using determinant and trace values of Hessian feature matrix. The feature vectors are fed into fully connected self-organisation map (SOM) computational network for recognition of those segmented images; 3) the system finally assembles partially recognised characters into a complete compound character depending on their topological attributes. To prove the performance of the system, we have conducted experiments with a dataset with 40,878 images and evaluate the performances in terms of accuracy, error rate and computational time by comparing with contemporary works CNeT and OCRMPD. Our system proves that we outperform 97.5% in overall accuracy than those in compared works.
    Keywords: character segmentation; recognition; topological attributes; spatial attributes; Hessian feature matrix; self-organisation map; SOM.
    DOI: 10.1504/IJCVR.2024.10062781
     
  • Classification of the sentiment using African vultures spider monkey optimisation based SqueezeNet technique   Order a copy of this article
    by Konda Adilakshmi, Malladi Srinivas, Anuradha Kodali, Srilakshmi Vellanki 
    Abstract: Sentiment classification is a precise chore in the categorisation of text, which intends to categorise the documents by their reviews. Analysation of sentiment is a process of extracting emotional content from the texts. An analysis of sentiment is a fundamental task, which is necessary for an understandable user. Therefore, an effective technique is proposed called the AVSMO_SqueezeNet technique for the classification of sentiment Firstly, the Amazon review document is assumed as input and then it is given to the tokenisation phase, where BERT is used. After the phase of tokenisation, the feature extraction is completed for extracting appropriate features for the classification of sentiment. Lastly, sentiment classification is performed utilising Squeeze Net which is tuned by the proposed AVSMO approach. However, the newly AVSMO technique is devised by an amalgamation of AVOA and SMO techniques. Furthermore, the proposed technique achieved maximum precision of 0.878, recall of 0.887, and F-measure of 0.883.
    Keywords: SqueezeNet; aquila optimiser; AO; African vultures optimisation algorithm; AVOA; SailFish optimiser; SFO; and spider monkey optimisation; SMO.
    DOI: 10.1504/IJCVR.2024.10062782
     
  • Experimentative analysis of artificial immune system algorithms for intrusion detection in IoT networks   Order a copy of this article
    by Syed Ali Mehdi, Syed Zeeshan Hussain 
    Abstract: Intrusion detection systems (IDS) are the basic security line for any network. Internet of things (IoT) networks have been in trend and usage. It thus raises security challenges in IoT networks, and thus there is a requirement for IDS for IoT. There has been promising research on artificial immune system (AIS) algorithms for intrusion detection. In this paper, AIS algorithms, namely negative selection algorithm (NSA) and clonal selection algorithm (CSA), for intrusion detection in IoT are compared. These algorithms are evaluated using Python on a popular public BoT-IoT-L01 dataset. Various performance metrics like detection rate, classification accuracy, false-positive rate, and falsenegative rate are used for comparison. The results of the research show that the CSA is better than the NSA-based intrusion detection for IoT in terms of accuracy. CSA achieved an overall detection rate of 91% in comparison to NSA’s, with 79%. It was found that NSA was more efficient than CSA in detecting rare kinds of attacks. The research findings indicate that AIS can be a powerful tool for IoT-based IDS. The selection of an appropriate AIS algorithm for IDS in IoT depends on the specific requirements and characteristics of the IoT network.
    Keywords: internet of things; IoT; artificial immune systems; AIS; intrusion detection system; IDS.

  • An image-based system for monitoring pregnant womens sleep posture   Order a copy of this article
    by S. Mohanram, J. Sathyamoorthy, A. Sargunal, P. Seran, M.S. Yogiramkumar, C. Elakshme Devi, M.R. Dharshini, S. Dharshan, G. Chandru 
    Abstract: Pregnancy is an important period for both mother and child, and the quality of sleep plays a vital role in ensuring their health a sleep position monitoring system designed to aid pregnant women in maintaining a healthy posture during sleep, crucial for maternal and fetal well-being. Leveraging computer vision and machine learning techniques, the system detects four sleep positions based on shoulder coordinates obtained from the MediaPipe pose model. Employing SVM and random forest algorithms, two models are developed to enhance accuracy, and their results are averaged for robust sleep position identification. Upon detecting prolonged undesired positions, the system triggers a call via a GSM modem for timely intervention. Offering a non-invasive, automated, and cost-effective solution, this system facilitates proactive monitoring of pregnant women's sleep posture, potentially preventing harm to the fetus. By promoting healthy sleep habits throughout pregnancy, it aims to improve maternal and fetal health outcomes.
    Keywords: GSM module; MediaPipe; Open CV; random forest algorithm; support vector machine; SVM.
    DOI: 10.1504/IJCVR.2024.10062865
     
  • Enhanced faster R-CNN based subcutaneous and visceral adipose tissue segmentation from abdominal MRI   Order a copy of this article
    by B. Sudha Devi, D.S. Misbha 
    Abstract: Obesity has emerged as a significant global problem that exposes both adults and children at risk for developing chronic diseases. The overall quantity of abdominal adipose tissue is frequently divided into two primary components, which are visceral adipose tissue (VAT) and subcutaneous adipose tissue (SAT), with the former being more directly linked to health concerns. Many computer based techniques are developed for segmenting the VAT and SAT, which are poor in feature extraction using the MRI and CT images. In this proposed model, the collected MRI and CT images of datasets 1 and 2 are enhanced using the pre-processing techniques consisting of image resizing, CLAHE, and median filter. Finally, the pre-processed images are segmented and classified using the enhanced faster R-CNN based on ResNet-5.0 and ROI (grab cut). The proposed model performance is evaluated using the performance metrics including error, accuracy, precision, specificity, etc., for datasets 1 and 2. The Enhanced Faster R-CNN model performs better by accurately segmenting and classifying the VAT and SAT from the abdominal region.
    Keywords: visceral adipose tissue; VAT; subcutaneous adipose tissue; SAT; faster R-CNN; ResNet-50; grab cut; CLAHE; median filter.
    DOI: 10.1504/IJCVR.2024.10062951
     
  • Deep neural learned bipolar sigmoid association rule mining for discovering high frequent and utility itemsets   Order a copy of this article
    by R. Savitha, V. Baby Deepa 
    Abstract: This paper presents a new deep neural learned bipolar sigmoid association rule mining (DNLBSARM) algorithm to improve the mining performance of frequent and utility itemsets (FUI) when considering large transactional data as input. The DNLBSARM is introduced by combining the deep neural learning and bipolar sigmoid association rule generation concepts. Initially, the input layer in DNLBSARM gets large number of items as input to perform mining process. Subsequently, hidden layers in DNLBSARM perform deep analysis where the support and utility value of each itemsets in big database is significantly measured. Finally, output layer in DNLBSARM used bipolar sigmoid association rule with the aiming at accurately discovering and mining top frequent and maximum profited itemsets in massive dataset with minimal amount of time utilisation. From that, DNLBSARM obtained improved extraction performance to find the top user interested and profited itemsets as compared to existing works. The experimental evaluation of DNLBSARM is conducted using parameters such as accuracy, time complexity, and false positive rate by considering various numbers of input items. The testing results demonstrated that the proposed DNLBSARM provides better performance in terms of higher accuracy and lower complexity for extracts the FI and HUT when compared to conventional research works.
    Keywords: association rule; bipolar sigmoid activation function; BSAF; deep learning; frequent itemsets; utility itemsets.
    DOI: 10.1504/IJCVR.2024.10062952
     
  • Design of low power low area SRAM cell at 180 nm, 90 nm and 45 nm technology nodes   Order a copy of this article
    by Seerapu Venkatesh, Krishna Veni Sahukara 
    Abstract: In this paper, a new SRAM topology cell is proposed with low power and low area in different technology nodes those are 180 nm, 90 nm and 45 nm. The power consumption results of the new SRAM topology is compared with the conventional 6T SRAM cell and SRAM cell implemented with LECTOR technique. The schematic design of these SRAM cells are implanted in the S-Edit, for generating spice code of the circuit T-Spice is used and the wave forms are observed in the W-Edit of the tanner tool software. The proposed SRAM cell at 45 nm technology node has got better power consumption compared to the remaining SRAM topologies.
    Keywords: LECTOR; SRAM; read; write; hold; power.
    DOI: 10.1504/IJCVR.2024.10063007
     
  • An internet of things-edge paradigm-enabled vision-based driving assistance for blind corners: a V2I application   Order a copy of this article
    by Goutam Kumar Sahoo, Rashmiranjan Nayak, K. L. Sanjeev Tudu, Umesh Chandra Pati, Santos Kumar Das, Poonam Singh 
    Abstract: The proposed work detects moving vehicles using unsupervised methods and estimates their speed as well as distance using surveillance cameras mounted in road infrastructure for collision avoidance at sharp corners. The goal is to develop IoT-based computer vision-assisted vehicle-to-infrastructure (V2I) communication for autonomous vehicles. Information like the availability of vehicles in the blind zone, speed, and distance of the upcoming vehicle can be shared with the drivers beforehand for safety purposes. Computer vision-based lightweight algorithms using simple morphological operations have been proposed to detect the incoming vehicle and estimate the associated speed and distance. Further, an IoT-edge paradigm-enabled computing platform is developed to facilitate efficient computation for latency-sensitive real-time applications. An auto-generated audio-visual alarm guides the driver by a fixed roadside unit near the turning point when the approaching vehicle crosses the predefined threshold zone decided for a particular turning point. Hence, it enables the vehicle to prevent a collision.
    Keywords: blind corners; camera; edge computing; internet of things; IoT; vehicle detection; warning generation; vehicle-to-infrastructure; V2I; advanced driver assistance systems; ADAS.

  • Predictive modelling of carbon nanotube structures using machine learning techniques   Order a copy of this article
    by Pawan Whig, Imran Ahmed Khan, Amrita Rai, Owais Ahmad Shah, M. Nasim Faruque, Jaishanker Prasad Keshari, Mudit Wadhwa 
    Abstract: This paper explores predictive modelling techniques applied to the structural analysis of carbon nanotubes (CNTs) using a dataset encompassing 10,721 initial and calculated atomic coordinates, alongside their intricate chiral networks. Derived from simulation software, BIOVIA materials studio CASTEP, this dataset serves as the foundation for employing advanced machine learning methodologies. Our research aims to decode the nuanced complexities inherent in CNT structures. By leveraging cutting-edge machine learning approaches, we seek to revolutionise the understanding and predictive capabilities regarding CNT architectures. The significance of our findings resonates deeply within materials science and nanotechnology, promising to streamline the comprehension and utilisation of CNTs across diverse domains, spanning electronics to materials engineering. This study marks a pivotal stride towards automating and expediting the development of nanomaterials, fostering innovation in a field where precision and efficiency are paramount. Our work showcases the potential for transformative advancements in harnessing CNTs for practical applications, propelling the integration of these nanostructures into real-world technologies.
    Keywords: carbon nanotubes; CNTs; predictive modelling; machine learning; structural analysis; materials studio CASTEP; nanomaterials; atomic coordinates; chiral networks; nanotechnology; materials science; simulation data.
    DOI: 10.1504/IJCVR.2024.10063137
     
  • Applied-behavioural analysis therapy for autism spectrum disorder students through virtual reality   Order a copy of this article
    by T. Subetha, Kayal Padmanandam, L. Lakshmi, S.L. Aruna Rao 
    Abstract: Autism spectrum disorder (ASD) is a neurological disorder that contracts one's social engagements and suffers from mind blindness, leading to a lack of social-emotional reciprocity. The most unravelling solution for them to learn social behaviour is using interactive virtual reality technologies. This study aims to develop an applied behaviour analysis therapy through virtual reality (VR)-based training to learn the necessary social-communication skills. The proposed system consists of two sessions. First, the training session, where the students are trained with VR content, developed to exhibit social-communication skills. Next, the students enter the practice session where the student will be given a chance to practice the lessons taught during the training session. Student gestures are recognised using a multimodal gesture recognition system, and deep neural network is employed to identify the student's speech. The successful video snippets are stitched into a video using automatic video self-modelling (VSM) and it allows the learner to improve a particular target social behaviour. The system has been evaluated using a comparative study with and without the proposed study and the results evidence that students have improved learning and communication in the real world, which seems to be the dream of their parents and family.
    Keywords: virtual reality; augmented reality; gesture detection; voice recognition; video self-modelling.
    DOI: 10.1504/IJCVR.2022.10051122
     
  • Acute myelogenous leukaemia detection in blood microscope images using particle swarm optimisation   Order a copy of this article
    by Abdullah Mohan, Kedir Beshir, Alemayehu Kebede 
    Abstract: The acute myelogenous leukaemia (AML) is one of the types of acute leukaemia that is seen in adults. Nowadays, people use manual tests of blood smear to diagnose leukaemia. This manual method requires more time and the operator's ability to diagnose the diseases. In this article, a new hybrid technique that detects AML in blood smears is presented. The proposed method uses a texture-based method - local binary pattern (LBP) and a statistical-based method - grey-level co-occurrence matrix (GLCM) to extract the features from WBC cells. The best features are selected by using a PSO algorithm and their accuracy is measured using nearest neighbour (NN)-classifier and extreme learning machine (ELM). The proposed method was tested using American Society of Hematology (ASH) public datasets and achieved promising results. The ASH database consists of 80 images, where 40 images are taken from AML patients and the remaining 40 are from non-AML patients. The proposed method, LBP+GLCM+PSO along with the ELM classifier achieved an accuracy of 90.44%. The experiment shows that the proposed method outperforms the existing methods in the detection of AML.
    Keywords: NN-classifier; particle swarm optimisation; PSO; acute myelogenous leukaemia; AML; acute lymphoblastic leukaemia; ALL.
    DOI: 10.1504/IJCVR.2022.10051333
     
  • Deep learning method for human activity recognition using heaped LSTM and image pattern of activity   Order a copy of this article
    by P. Rajesh, R. Kavitha 
    Abstract: Deep learning is the most spelt word and habitually used technology of the researchers around the globe of technical arena. With the tremendous growth of technologies like data analytics, data mining, machine learning methods and IoT applications like health monitoring, safety and security, and smart control, human movement acknowledgement has become a more noteworthy achievement in the field of science. Utilising the most booming technology, we propose a unique approach for monitoring human activities who aspire to live and lead an independent life, mostly the elderly people. In this experiment we discovered a novel method in identifying the human activities and the forte of this approach is the privacy of the monitored person is ensured. This investigation is moved forward by utilising an improved convolution neural network (CNN) with enriched bi-directional LSTM (BLSTM). The activity recognition model is still optimised by using a heaped LSTM (HLSTM) and a fine trained data clustering algorithm. Our proposed approach, when trained and tested with a prominent dataset that contains sensor data, achieved overall accuracy of 99.43% for all the considered nine activities.
    Keywords: activity recognition; bi-directional LSTM; BLSTM; clustering; convolution neural network; CNN; heaped LSTM.
    DOI: 10.1504/IJCVR.2022.10050893
     
  • Efficient masked face identification biometric systems based on ResNet and DarkNet convolutional neural networks   Order a copy of this article
    by Freha Mezzoudj, Chahreddine Medjahed 
    Abstract: The COVID-19 pandemic has caused death and serious illness in the entire world. During humanity's fight against this disease, the wearing of face masks has become and remains a necessity in our daily life. This critical fight encourages us to generate a rich masked face database (noted FEI-SM) with different variations of poses and different emotions. We also employed several robust convolutional neural network systems based on three ResNet and two DarkNet models (ResNet18, ResNet50, ResNet101, DarkNet19, and DarkNet53) to measure the accuracy of biometric identification of masked and un-occluded faces on the challenging masked face database FEI-SM. In general, the compared results are showing good accuracies with many used biometric systems. Through experimental runs, the obtained outputs show clearly that the scheme model based on ResNet18 is the most effective model to recognise individuals with masks in different scenarios in terms of rate recognition and testing time.
    Keywords: biometric; masked face identification; ResNet; DarkNet; FEI-SM database; convolutional neural networks; CNN.
    DOI: 10.1504/IJCVR.2022.10052153
     
  • A new approach to detect cardiovascular diseases using ECG scalograms and ML-based CNN algorithm   Order a copy of this article
    by Lanka Alekhya, P. Rajesh Kumar 
    Abstract: Convolutional neural networks (CNNs) have gained popularity in the classification of cardiovascular diseases using ECG signals. This paper uses a pre-trained CNN model Visual Geometry Group16 (VGG16) network with the transfer learning process is used for feature extraction with SVM, k-NN and RF algorithms to classify the signals. The input to VGG16 net were ECG signals that are considered from the MIT-BIH database for four classes of heart ailments. Around 27 min and 42 sec of elapsed time is engaged to train the network. The study evaluates that this hybrid model of CNN performs on test data and gives an overall model accuracy and mean of MCC for SVM as 95.83% and 94.52%, for k-NN as 96.67% and 95.60% and for Random Forest as 96.94% and 95.96% respectively which gives a better performance when compared with only pretrained CNN-VGG16Net with an overall accuracy of 95.3% and 93.75% as mean MCC.
    Keywords: electrocardiogram; ECG; convolutional neural network; CNN; Visual Geometry Group16; VGG16; support vector machine; SVM; k-nearest neighbour; k-NN; random forest; RF; Mathew's correlation coefficient; MCC.
    DOI: 10.1504/IJCVR.2022.10051429
     
  • An implementation of searchable video player   Order a copy of this article
    by Kitae Hwang, In Hwan Jung, Jae Moon Lee 
    Abstract: This paper introduces an Android app, SVPlayer, that searches for scenes in a video. To search for scenes in a video, SVPlayer extracts voice from the video, converts it into text, and searches for words in the text. Voice is converted to text in units of ten seconds, and both voice and text are made into a timeline text. When the user enters a word, the word is searched and a timeline list of all scenes that contains the word is displayed, and the user can select a desired time from the list. The performance was variously evaluated through actual measurement, and as a result, it took only 2-3 minutes to create 10-second timeline text from a 20-minute video. SVPlayer processes this task in the background, so the user can jump directly to the desired scene in the middle of watching 2-3 minutes after starting to play the video.
    Keywords: voice; search scene; text.
    DOI: 10.1504/IJCVR.2023.10053409