International Journal of Computational Vision and Robotics (36 papers in press)
Performance Evaluation on Image Fusion Techniques for Face Recognition
by Aniruddha Dey, Shiladitya Chowdhury, Jamuna Kanta Sing
Abstract: In face recognition, a feature vector usually represents the salient characteristics that best describe a face image. However, these characteristics vary quite substantially while looking into a face image from different directions. Therefore, by accumulating these directional features into a single feature vector will certainly lead to superior performance. This paper addresses this issue by means of image fusion and presents a comprehensive performance analysis of different image fusion techniques for face recognition. Image fusion is done between the original captured image and its true/partial diagonal images. The fusion is made by three different ways by placing the images (i) one-over-other (superimposed), (ii) side-by-side (horizontally) and (ii) up-and-down (vertically). The empirical results on publicly available AT&T, UMIST and FERET face databases collectively demonstrate that superimposed image between the original and its true diagonal images actually provides superior discriminant features for face recognition as compared to either original or its diagonal image.
Keywords: Face recognition; Generalized 2DFLD; Image fusion; Projection vector; Diagonal image.
Random Neighborhood Dynamic Clustering
by Gaurav Tyagi, Nilesh Patel, Pawel Marcinek
Abstract: Recognition of arbitrary shaped clusters is highly active research topic in data mining and cluster analysis. In this paper we consider the problem of data clustering of arbitrary shaped clusters as a random evolutionary process. We propose a new algorithm RNDC which uses the random process for cluster analysis. RNDC assumes that an object contains information only about the characteristic values of its local neighborhood. It explores the local cluster structures to determine the global partitions of data set. It is of significance that RNDC evolve randomly among the objects of data set, while other well known partitioning clustering algorithms used the techniques of sequential propagation through the nearest connected/reachable objects. Our method is, in principle, applicable for any arbitrary shaped clusters. Since randomness is an essential part of RNDC, it makes this algorithm suitable for multiprocessing parallel computation.
Keywords: Dynamic Clustering; Neighborhood Based Method; Random propagation.
Motion Planning and Coordination of Multi-Agent Systems
by Nirmal B. Hui, Buddhadeb Pradhan, Diptendu Sinha Roy
Abstract: Development of navigation scheme for a group of cooperative mobile robots is attempted in this paper. Potential field method is used to generate collision-free movement of a robot while it encounters other robots as obstacles. Finally, a cooperation scheme is proposed based on human behaviour to optimize motion strategies of robots treating each other as their obstacles. Computer simulations have been conducted for three different cases with four, eight and twelve robots negotiating a common dynamic environment. In each case, 100 different scenarios are considered and travelling times of all the robots are computed separately. The scenes in which the robots meeting collision is treated as a failure scenario and travelling time is not calculated. Performance of cooperation scheme has improved with the increase in a number of robots.
Keywords: Multi Agent Systems; Coordination; Potential Field Method; Navigation.
Labeling and evaluation of 3D objects segmentation using multiclass boosting algorithm
by Omar Herouane, Lahcen MOUMOUN, Mohamed CHAHHOU, Taoufiq GADI
Abstract: 3D objects segmentation has become a fundamental task in computer vision and digital multimedia. Evaluating the automatic 3D segmentation algorithms quality and comparison of their performances are important topics, some metrics are proposed in the literature. However, these metrics are not too prominent for evaluating the automatic segmentation algorithms in general. The aim of this paper is to introduce a simple and efficient approach to evaluate the automatic segmentation of a 3D object. This new evaluation scheme is based on learning 3D mesh and on the Minkowski metric. Machine learning is used to learn a function that assigns the appropriate label to each part of a segmented 3D object of the database; then, the error committed by each labeled segment is computed using the Minkowski norm. The best performance and high quality of the quantitative results demonstrated the efficiency of the proposed approach.
Keywords: Boosting algorithm; Adaboost; Machine learning; Minkowski metric; Segmentation; Labeling; Evaluation; Shape index; Shape Spectrum Descriptor; 3D object; computer vision.
A neural-based method for optical flow estimation using phase correlation
by Khalid Ghoul, Mohamed Berkane, Mohamed Chaouki Batouche
Abstract: Motion estimation for image sequences is one of the most important tasks in computer vision. Thus, many methods have been proposed to solve this problem, but even so, it still lacks a generic method that determines motion in all situations and for all types of objects. In this work, we propose a two-phase connectionist neural method for motion estimation in the frequency domain that takes discontinuities into account. In the first phase, the most probable motion of each pixel is estimated using self-organizing maps principles and the phase correlation method. The second phase consists in regularizing the displacement field that considers the discontinuities. When tested and compared with other approaches on both synthetic and real image sequences, our method showed good performances according to the following criteria: precision, regularity, resistence to noise and running-time. Moreover, it could estimate the motions in cases where rotation and scaling are required.
Keywords: Keywords: Motion estimation; neural network; frequency domain; Fourier transform; phase correlation method.
Script invariant Handwritten Digit Recognition using a Simple Feature Descriptor
by Pawan Kumar Singh, Supratim Das, Ram Sarkar, Mita Nasipuri
Abstract: Handwritten digit recognition is still considered as a difficult task because of the large variability of the digits shapes written by individuals. A lot of work has been done towards digit identification with excellent performance but mostly these works have been made focusing on digits written in a particular script. Hence, in a multilingual country like India, where different scripts are prevalent, methods which recognize numerals written in single script may not always serve the purpose. To address this issue, we propose a script invariant handwritten digit recognition scheme in this paper. A novel feature extraction technique named as Quadrangular transition count has been introduced. Experimentations performed using five conventional classifiers advocate that Multi Layer Perceptron (MLP) is best among them which yields recognition accuracies of 98.13%, 97.85%, 96.72%, and 95.35% on four popularly used scripts of the world namely, Arabic, Bangla, Devanagari, and Roman respectively.
Keywords: Handwritten digit recognition; Quadrangular transition count features; Arabic script; Bangla script; Devanagari script; Roman script; ADBase; HDRC 2013.
Intelligent Plankton Image Classification with Deep Learning
by Abhishek Verma
Abstract: Plankton are extremely diverse groups of organisms that exist in large water columns. They are sources of food for fishes and many other marine life animals. The plankton distribution is essential for the survival of many ocean lives and plays a critical role in marine ecosystem. In recent years, intelligent image classification systems were developed to study plankton distribution through classification of the plankton images taken by underwater imaging devices. Due to the significant differences in both shapes and sizes of the plankton population, accurate classification poses a daunting challenge. The mixed quality of the collected images adds more difficulty to the task. In this paper, we present an intelligent machine learning system built on convolutional neural networks (CNN) for plankton image classification. Unlike most of the existing image classification algorithms, CNN based systems do not depend on features engineering and they can be efficiently extended to encompass newclasses. The experimental results on SIPPER image datasets show that the proposed system achieves higher accuracy compared with the state-of-the-art approaches. The new system is also capable of learning a much larger number of plankton classes.
Keywords: SIPPER Plankton Image; Convolutional Neural Network; Machine Learning; Image Classification.
Configuration of a Min-Cost Flow Network for Data Association in Multi-object Tracking
by Chanuk Lim, Jeonghwan Gwak, Moongu Jeon
Abstract: In this paper, we mainly describe how to formulate a network flows optimally for multi-object tracking. The network flows can be used to construct trajectories of objects (between frames) to achieve multi-object tracking. The most important issue to establish such network is to design nodes and edges in the network. In this work, we propose a method to fuse the object detector with object trackers in order to efficiently design the nodes and edges. The object trackers can give the information on robust classifiers or features of objects through training, which helps to design the edges. This approach is significant when a detector fails due to occluded objects. If an object is failed to be detected, the object tracker will be substituted to the object detector. In this way, we employ the object tracker and the object detector to formulate a sophisticated network depending on the condition. The proposed approach enables to eliminate the clutters and thus overcome the heavy occlusion situations. We evaluated performance of the proposed method through several experiments using real-world video sequences. The experimental results demonstrated good performance of the proposed approach compared to state-of-the-art methods.
Keywords: Multi-object Tracking; Data association; Min-Cost Flow Network.
Normalization of handwriting speed for online Arabic characters recognition
by Bougamouza Fateh, Hazmoune Samira, Benmohammed Mohamed
Abstract: In this paper, we propose a new solution for the problem of the unevenly distributing points along the stroke curve, in online Arabic handwriting recognition, due to the variation in writing speed. An algorithm based on linear interpolation is generally used to solve this problem. The main weakness of this algorithm is the missing of some information related to point density distributions in different stroke parts. This limitation is due to the use of only one resampling distance. In our approach, we propose to segment the stroke trajectory into several parts according to their densities and to classify them into three classes: high, medium and low density. For this purpose, two thresholds are chosen: the first one defines the maximum distance between two successive points belonging to high-density class, and the second threshold characterizes the minimum distance between two successive points into low-density class. The interval from the first to the second threshold covers distances between any two successive points in the medium-density class. Three resampling distances, instead of one, are also suggested, each of them is associated to one class of densities. This solution is evaluated using NOUN dataset and it gives an excellent improvement in the recognition rate, up to 4%, compared to linear interpolation method.
Keywords: online Arabic handwriting recognition; HMM; writing speed variation; linear interpolation; trace segmentation; point density distributions.
Features selection for offline handwritten signature verification: state of the art.
by Anwar Yahya Ebrahim, Hoshang Kolivand, Amjad Rehman, Mohd Shafry Mohd Rahim, Tanzila Saba
Abstract: This research comes out with an in-depth review of widely used techniques to handwritten signature verification based, feature selection techniques. The focus of this research is to explore best features selection criteria for signature verification to avoid forgery. This paper further present pros and cons of local and global features selection techniques, reported in the state of art. Experiments are conducted on benchmark databases for signature verification systems (GPDS). Results are tested using two standard protocols; GPDS and the program for rate estimation and feature selection. The current precision of the signature verification techniques reported in state of art are compared on benchmark database and possible solutions are suggested to improve the accuracy. As the equal error rate is an important factor for evaluating the signature verifications accuracy, the results show that the feature selection methods have successfully contributed toward efficient signature verification.
Keywords: Handwritten Signature Verification; Feature Extraction; Feature Reduction Methods; Feature Selection.
3D OBJECTS CLASSIFICATION BASED ON $P RECOGNISER
by Safae El Houfi, Maha Jazouli, Aicha Majda, Arsalane Zarghili
Abstract: In this paper, we propose a method for 3-dimensional (3D) model recognition based on 2-dimensional (2D) views. The goal of this method is to provide a selection of 2D views from a 3D model, by using the $P method for 3D model retrieval from these views. So, in order to extract the necessary information, we study the different multi-view indexing methods; characterizing the shape of the 3D image using 2D projection. With regard to the shape descriptor, we propose using the Fast Fourier Transform to provide spectral rendering for each extracted view. The method is based on the $P point-cloud recognizer. Our approach allows comparing either directly with a query image or with another 3D object by comparing their sets of views. We demonstrate the potential of this approach in a set of experiments, which prove that our system achieves a recognition rate ranging from 91.5% to 93.5%.
Keywords: $P; classification; 3D/2D indexing; 3D retrieval; views; VRML.
An Image analogy approach for multi-scale Image segmentation
by Asma Bellili, Slimane Larabi
Abstract: Image segmentation is one of the challenging tasks in image processing. This paper introduces a novel method for image segmentation based on image analogy principle. First, contours of source image are located using 14 pairs of stereo patches. Next, elementary regions, considered as areas between contours located using to successive pairs of patches. Finally, we define borders stability of neighbouring regions which constitutes the measure for regions merging. Three scales are defined giving three segmentation at three resolutions (low, intermediate and high). Experiments conducted on Wiezmann dataset, the obtained results are presented and compared to the state-of-the-art.
Keywords: image analogy; image segmentation; merging; contour detection; computational vision; multi scale; Wiezmann.
Enhancing the Laws filter descriptor on DTCWT coefficients by thresholding approach for texture classification
by Sonali Dash, Uma Ranjan Jena
Abstract: In this paper, we propose a new approach of combining dual-tree complex wavelet transform with traditional Laws filter descriptor for texture classification using thresholding method. The dual-tree complex wavelet transform (DTCWT) is a recent technique to discrete wavelet transform, with important additional properties. It has been observed that the thresholding is a method to keep significant information of the image while discarding the unimportant part. On this basis for further enhancement of texture classification, we have acquired the texture images by applying thresholding technique to the entire texture database. These thresholded images are then applied to the fusion model of DTCWT with Laws filter descriptor. We verify the effectiveness of the proposed method by utilizing two texture databases such as Brodatz and UIUC. The proposed methods are also compared with the classical laws filter descriptor. Results demonstrate that the proposed method greatly enhanced the classification accuracies by using k-NN as classifier.
Keywords: Texture feature; Texture classification; Laws’ mask; Dual-tree complex wavelet; Thresholding;.
Automated Identification and Counting of Proliferating Mesenchymal Stem Cells in Bone Callus
by Samer Awad, Rula Abdallat, Othman Smadi, Thakir AlMomani
Abstract: The assessment of cell count is essential for the evaluation of biological cell proliferation development. Manual counting can be time consuming and subject to human error as it depends on visual inspection. On the other hand, automated counting using software based morphological analysis can eliminate or reduce these disadvantages and provide statistical reliability. In this study, we employ a software-based method for the automated counting of mesenchymal stem cells (MSCs) proliferation in the bone callus of Wistar rats to evaluate fracture healing. The proposed method started with extracting the green component of the digital image acquired using a light microscope. The subsequent stages involved: contrast enhancement, adaptive thresholding and false detection reduction. This method was tested using 48 MSCs images and the results were evaluated by a specialist. The average of precision, recall and F-measure were found to be 87.14%, 88.04%, and 87.50% respectively.
Keywords: Automated cell counting; Biological cell counting; Image processing; Image segmentation; Pattern recognition; Automated thresholding; Light microscopic images; Mesenchymal stem cells; MSC; False detection minimization.
Content-Based Image Retrieval (CBIR): A deep look at features prospectus.
by Mohammed Suliman Haji, Amjad Rehman, Tanzila Saba
Abstract: Currently rapid growth of digital images on the internet is observed, accordingly, the need for content-based image retrieval systems are in high demand. Content-Based Image Retrieval (CBIR) is an image search technique that does not depend on manually assigned annotations; rather, CBIR uses discriminative features to search an image. By refining features, an efficient retrieval mechanism could be achieved. The aim of this research is to review features extraction and selection that have an impact on Content-Based Image Retrieval (CBIR) and information extraction from images using global and local features such as shape, texture, and color. In order to extract most appropriate features for Content-Based Image Retrieval (CBIR), several feature extraction and selection techniques are analyzed and their efficiency is compared. Additionally, shortcomings of current content-based image retrieval techniques are addressed and possible solutions are suggested to enhance accuracy.
Keywords: CBIR; Discrete Wavelet Transform; Low-level Features and High-level Features.
Bio-inspired visual attention process using spiking neural networks controlling a camera
by André Cyr, Frédéric Thériault
Abstract: This study introduces virtual and physical implementations of a bottom-up visual attention mechanism using a spiking neural network(SNN) controlling a camera. The SNN is able to focus simple stimuli of various length that appear randomly in the camera's view. This is accomplished with an overt process based on a competitive choice according to a stimulus quadrant location. After focusing a selected stimulus toward the center of its view, the SNN scans it from one edge to the other. Since the spike train of dedicated neurons reflects the duration of each scan, it allows the extraction of the stimulus length. Upon the completion of a scan, the SNN has the ability to switch to another stimulus. This preliminary work on spatial visual attention intends to be a step toward the study of the concept size learning process in a robotic context.
Keywords: Spiking neurons; Robotics; Overt process; Visual Attention.
Fast Binary Shape Categorization for Intelligent Vehicles
by Insaf Setitra, Slimane Larabi
Abstract: In this paper we propose a novel method for shape categorization suitable
for video surveillance and intelligent vehicles applications. Binary shape is
convoluted with a Gaussian filter at different scales and curvatures are detected
for each scale. Shape is then described using arclength and radius of curvatures.
This descriptor allows differentiating between shapes particularly for objects
that may appear in front of intelligent vehicle or in monitored scene such as
pedestrian, car, cyclist, animal (horse, cow, dog, cat). Conducted experiments
show that our method compete the state-of-the-art methods in term of accuracy
and surpasses them in term of time processing.
Keywords: Binary shape; categorisation; Intelligent vehicles; Matching; Categorisation; Curvature; Scale space.
Enhancing Proximity Measure Between Residual and Noise for Image Denoising
by Gulsher Baloch, Junaid Ahmed
Abstract: Sparse representation and dictionary learning based image denoising algorithms approximate the clean image patch by linear combination of few dictionary atoms. Clearly, residue after completion of denoising must be similar to the contaminating noise. Ideally, clean image patch is perfectly recovered if residue is exactly contaminating noise. Hence, for better denoising residue must be enforced to possess characteristics similar to the contaminating noise. In this paper, we model residue such that proximity between residue and contaminating noise is increased. The proposed mathematical model makes sure that the residue is as random in nature as contaminating noise. This is achieved by unique sparse coding and dictionary update stages developed based on modeling of randomness in residue. The proposed algorithm is tested on Additive White Gaussian Noise (AWGN), Additive Colored Gaussian Noise (ACGN) and Laplacian Noise. Since performance of the image denoising algorithms also depend on image effective bandwidth, therefore, in this paper we have generated synthetic images with known effective image bandwidths. These images are generated using the Discrete Cosine Transform (DCT). The proposed algorithm is also tested on these images. The proposed algorithm is compared with state-of-the-art algorithms. The comparison on the bases of peak signal-to-noise ratio (PSNR), structure similarity index measure (SSIM) and feature similarity index measure (FSIM) indicate that the proposed algorithm is able to produce often better and competitive results.
Keywords: Additive Colored Noise; Laplacian Noise; Residual Correlation; Image Denoising.
Push Recovery System and Balancing of a Biped Robot on Steadily Increasing Slope of an Inclined Plane
by Pravat Kumar Behera, Ravi Kumar Mandava, Pandu R. Vundavilli
Abstract: The present research paper demonstrates the push recovery system and balancing on an inclined plane by a 20 degrees of freedom (DOF) small sized biped robot. Here, the authors developed an algorithm to balance the posture of the biped robot while standing (that is, stationary mode), and balancing on an inclined plane with steadily increasing slope. To maintain stability of the biped robot, stability controllers are integrated into the walking controller. This enable the robot to sense any disturbance, and perform necessary action to maintain its stability. For measuring the external disturbances and orientation of the ground, an inertial measurement unit sensor is fitted inside the robot. Further, the robot is allowed to generate internal torque by the movement of its body parts to resist external disturbances. This principle is extended to test the balance of the biped robot on an inclined plane with increasing inclination angle. The robot is seen to successfully exhibit the two tasks, such as push recovery and maintaining the balance on the steadily increasing slope of a sloping surface in real time.
Keywords: Push recovery; external disturbances; balance on an inclined plane.
Ethiopian Maize Diseases Recognition and Classification using: Support Vector Machine
by Enquhone Alehegn
Abstract: Currently, there are around 72 maize diseases found in Ethiopia that attack different part of maize. From the maize diseases, maize common rust, maize leaf blights and maize gray leaf spot are the commonest diseases that attack maize leaf in all over Ethiopian farm area. There are different traditional mechanisms to identify and classify maize leaf diseases by chemical analysis or visual observation. But, the traditional mechanisms have their own drawbacks: inconsistent, costly, take more time, prone to error, and require professional staff. Therefore, many researchers have been doing a lot in identifying and classifying the different types of diseases that attack maize using model-based image processing and computer vision to support experts across the world. However, as far as the researchers knowledge is concerned, no attempt has been done for Ethiopian maize diseases data set. In this study an attempt has been made to develop maize leaf diseases recognition and classification using both support vector machine model and image processing. To evaluate the recognition and classification accuracy, from the total data set of 800 images, 80% used for training and the remaining 20% for testing the model. Based on the experiment result using combined (texture, colour and morphology) features with support vector machine an average accuracy of 95.63% achieved.
Keywords: Maize Disease; image pre-processing; features; feature extracted; image segmentation; image enhancement; noise removal; binarization; SVM.
An Integrative Approach for Tracking of Mobile Robot with Vision Sensor
by Sangarm Keshari Das, Sabyasachi Dash, B.K. Rout
Abstract: Current work addresses an experimental approach which incorporates feature based object detection, KLT Algorithm based tracking method and Kalman filter based de-noising technique in a real-time environment. In the detection phase, the mobile robot is detected using Viola-Jones algorithm which extracts detectable features. Then the position of the mobile robot is computed with homography constraints and a region of interest window is set up to accommodate the mobile robot. In the tracking phase, the region of interest window is dealt with using KLT algorithm. The proposed method is of practical importance when the mobile robot is tracked while moving on a predetermined (specified) path as the size of the image of the mobile robot is small relative to the captured image of the environment. Thus the analysis of captured image of environment becomes unnecessary for tracking and thereby the approach reduces computational load. The proposed approach accurately detects and tracks the mobile robot with error percentage ranging from 0.5% to 10% in different parts of the specified path.
Keywords: Mobile robot; Viola Jones algorithm; KLT algorithm; Kalman Filter; Vision based Tracking.
Visual Cues based Deception Detection Using Two Class Neural Network
by Sabu George, Manohara Pai M.M, Radhika M. Pai, Samir Kumar Praharaj
Abstract: The deception detection technique which helps to analyse a person without his knowledge is convenient and effective than other methods of deception detection. In this paper facial visual cues based deception detection study is performed. In this study, an experiment was conducted with the participation of 62 subjects. Facial muscle variations of lie and truth responses of the subjects were recorded using a high speed camera and the corresponding Action Units (AUs) were trained and then tested for truth and lie prediction using 2 class neural networks. The prediction performance was analysed using 5 different sets each having 10%, 20% and 30% test samples.
Keywords: Lie face analysis; AU analysis; deception detection.
Images-to-Images Person ReID Without Temporal Linking
by Thuy-Binh Nguyen, Thi-Lan Le, Ngoc-Nam Pham
Abstract: This paper addresses images-to-images person re-identification in which there are multiple images for each individual on both gallery and probe. Most existing approaches that try to extract/learn features require temporal linking between frames. This paper proposes a novel framework to overcome this requirement by formulating images-to-images person re-identification as fusion function of image-to-images. First, a ranked list of candidates corresponding to each query image is determined. Then, these lists are fused to determine the matched person. The contributions of the paper are two-fold: (1) an extra feature (Gaussian of Gaussian) is used for representing person; (2) a new images-to-images scheme that does not require temporal linking and features the benefit of image-to-images scheme is proposed. Extensive experiments on CAVIAR4REID (case A and B) and RAiD datasets prove the effectiveness of the framework. The proposed scheme obtains + 20.88%, +10.23% and +10.39% improvement in rank-1 over image-to-images scheme on these datasets.
Keywords: Multi-shot; person re-identification; late fusion; images-to-images person re-identification.
A Technique to Validate Automatic Generation of B
by Nabil Messaoudi, Allaoua Chaoui, Bettaz Mohamed
Abstract: Several approaches have been proposed in the literature to transform UML models to formal methods for verification reason. However, few of these approaches take into account the validation of such transformations. This paper is a proposal in this context. It has two parts; first, we propose a technique to control the output of a transformational tool, in order to obtain safe transformational rules, and second, we propose a way to generate the formal model B
Keywords: UML 2 Sequence diagrams; Semantics; Model Transformations Validation; Büchi automata; AGG.
A framework for automatically constructing a dataset for training a vehicle detector
by Changyon Kim, Jeonghwan Gwak, Moongu Jeon
Abstract: Object detection based on a trained detector has been widely applied to diverse tasks such as pedestrian, face, and vehicle detection. In such approach, detectors are learned offline with an enormous number of training samples. However, the approach has a significant drawback that heavy intervention and effort, as well as domain knowledge, of a human are essentially required to construct a reliable training dataset. To remedy this drawback, we propose a framework to collect and label training samples automatically. By analyzing information of foreground blobs obtained from background subtraction results, a training dataset can be constructed without any humans effort. Also, condition investigation of scenes is performed periodically to check the suitability of sample candidates. As a result, it generates an accurate vehicle detector. With the proposed method, training samples can be automatically collected only when vehicle blobs in the given scene provide suitable appearance information. The effectiveness of the proposed framework is demonstrated from vehicle detection tasks under real traffic environments.
Keywords: Object detection; Optimal vehicle detector; Appearance model; Scene condition investigation; Automatic sample collection.
Effective scene change detection in complex environments
by Hui Fuang Ng, Chee Yang Chin
Abstract: One of the fundamental operations in computer vision applications is change detection, in which moving foreground objects are segmented from a static background. A common approach for change detection is the comparison of an image frame with the stored background model using a matching algorithm, a process known as background subtraction. However, such techniques fail in environments with dynamic backgrounds, illumination changes, or shadow and camera jitters. This study focuses on effectively detecting scene changes in complex environments. To this end, we proposed a new colour descriptor named Local Colour Difference Pattern (LCDP) that is insusceptible to shadow and is able to capture both colour and texture features at a pixel location. Furthermore, a scene change detection framework was proposed to handle dynamic scenes based on sample consensus that integrates LCDP and a novel spatial model fusion mechanism. Experiments using the CDnet benchmark dataset demonstrated the effectiveness of the proposed approach to change detection in complex environments.
Keywords: change detection; background subtraction; moving object segmentation; foreground segmentation; local descriptor; video signal processing; CDnet.
3D Image Reconstruction from Different Image Formats Using Marching Cubes Technique
by Abdou Shalaby, Mohammed Elmogy, Ahmed AboElfetouh
Abstract: Structure from motion (SFM) is the problem of reconstructing the 3D image from 2D images. The main problem of 3D reconstruction is the quality of the 3D image that depends on the number of 2D slices input to the system. A large number of 2D slices may lead to high processing time. This paper introduces a new model to reconstruct the 3D image from any 2D image by using marching cubes algorithm. We use the LABVIEW program to build the system and use the Biomedical Toolkit to read and registered any 2D images. Our main goal is to implement the 3D reconstruction system to produce a high-quality 3D image with a minimum number of 2D slices and to decrease the execution time as possible. We apply our system on two datasets; all the experimental results have proved the efficiency and effectiveness of this system in 3D image reconstruction from any 2D image type. As shown in results, changing iso_value, image type and a number of images, affects the quality of 3D image reconstruction, and the processing time.
Keywords: 3D image reconstruction; Marching cubes; Lab VIEW; 2D image registration; computed tomography(CT); Magnetic Resonance(MR); Single-photon emission computed tomography(SPECT).
Use of Radial Basis Function Network with Discrete Wavelet Transform for Speech Enhancement
by Rashmirekha Ram, Mihir Narayan Mohanty
Abstract: Neural Network has occupied a very good position in the field of detection, recognition and classification. However the use of these models for signal enhancement is a new direction of research. In this paper, Neural Network is used to enhance the quality of the speech. The efficient model Radial Basis Function Network (RBFN) is chosen for enhancement of the noisy signals. Wavelet Transform is used for decomposition of signal. It works in both the ways. In first stage, the noise from the input signal is reduced.Next to it, these coefficients are used as weights of the RBFN model that makes faster processing as compared to use of random weights. The output of the proposed model is measured in terms of Signal to Noise Ratio (SNR), Segmental Signal to Noise Ratio (SegSNR) and Perceptual Evaluation of Speech Quality (PESQ).The performance of the proposed method found excellent and is exhibited in the result section.
Keywords: Speech Enhancement; Discrete Wavelet Transform; Radial Basis Function Network; Signal to Noise Ratio; Segmental Signal to Noise Ratio; Perceptual Evaluation of Speech Quality.rnrn.
Crypto-compression Scheme based on the DWT for Medical Image Security
by Med Karim Abdmouleh
Abstract: Ensuring the confidentiality of exchanged data is always a great concern for any communication. Also, the purpose of compression is to reduce the amount of data while preserving important information. This reduction leads to the archiving of more information on the same storage medium and minimizes the transfer times via telecommunication networks. Indeed, the combination of encryption and compression guarantees both confidentiality and authentication of information. In addition, it reduces processing time and transmission on public channels and increases storage capacity. In this paper, we propose a new approach of a partial or selective encryption for medical Images based on the Discrete Wavelet Transform (DWT) coefficients and compatible with the norm JPEG2000. The obtain results prove that, the proposed scheme provides a significant reduction of the processing time during the encryption and decryption, without tampering the high compression rate of the compression algorithm.
Keywords: Crypto-compression; Encryption; Compression; Discrete Wavelet Transform; RSA; JPEG2000; Telemedicine.
Non-Invasive Technique of Diabetes Detection using Iris Images.
by Kesari Verma, Bikesh Kumar Singh, Neelam Agrawal
Abstract: Alternative medicine techniques are important in improving the quality of life, disease prevention and better to the conventional invasive method of diseases detection. This paper addresses a non-invasive approach of diabetic detection using iris images. The proposed technique evaluate the use of iridology to diagnose diabetes using modern digital image processing techniques that analyses structural properties of the iris and classifies the patterns accordingly. The system analyses the broken tissues of the iris by extracting significant textural features using Gabor filter bank and Gray Level Co-occurrence Matrix (GLCM) from the subsection of the iris. The extracted textural features help to categorize the diabetic and non-diabetic irises using benchmarks Artificial Neural Network (ANN) and Support Vector Machine (SVM) classifiers. The promising results of extensive experiments demonstrate the effectiveness of the proposed method.
Keywords: diabetes detection; image processing; iris images; support vector machine; artificial neural network; SVM; ANN; gabor features; gray level co-occurrence matrix; GLCM; Non-Invasive Technique.
Special Issue on: Research in Virtual Reality
Real time sign language recognition using depth sensor
by Jayesh Gangrade, Jyoti Bharti
Abstract: Communication via gestures is a visual dialect utilized by deaf and Hard-of-Hearing (HoH) people group. This paper proposed a system for sign language recognition utilizing human skeleton data provided from Microsofts Kinect sensor to recognizing sign gestures. The Kinect sensor generates the skeleton of a human body and distinguishes 20 joints in it. The proposed method utilizes 11 out of 20 joints and extracts 35 novel features per frame, based on distances, angles and velocity involving upper body joints. Multi-class Support Vector Machine classified the 35 Indian sign gestures in real time with accuracy of 87.6%. The proposed method is robust in cluttered environment and viewpoint variation.
Keywords: Kinect sensor; Indian sign gesture; Multi class support vector machine; Human computer interaction; Pattern recognition.
Adaptive Multi-Threshold Based De-noising Filter for Medical Image Applications
by Ramya A, Murugan D, Murugeswari G, Nisha Joseph
Abstract: Medical image processing is the emerging research area and many researchers contributed to medical image processing by proposing new techniques for medical image enhancement and abnormality detection. Interpretation of medical images is a challenging problem because of the unavoidable noise produced by the medical imaging devices and interference. In this work, a new framework is proposed for noise detection and reduction. This framework comprises two phases. First phase is the noise detection phase which is performed using the newly proposed Adaptive Multi-Threshold scheme (AMT). In second phase, modification of noisy pixel is done using Edge Preserving Median filter (EPM), which conserves the edge component and controls the blurring effect with preservation of fine details of interior region. The proposed work is tested with benchmark images and few medical images. It produces promising result and the results are compared with existing two-stage noise reduction techniques. Popular performance metrics such PSNR and SSIM are used for evaluation. Quantitative analysis and experimental results demonstrate that the proposed method is more efficient and suitable for medical image pre-processing.
Keywords: Noise removal; Noise Detection; Impulse noise; Multi-Threshold; Edge Preserving.
Crowd detection and counting using a static and dynamic platform: State of the Art
by Huma Chaudhry, Mohd Shafry Mohd Rahim, Tanzila Saba, Amjad Rehman
Abstract: Automated object detection and crowd density estimation are popular and important topics in visual surveillance research area. The last decades witnessed many significant publications in this field and it has been and still is a challenging problem for automatic visual surveillance. The ever increase in research of the field of crowd dynamics and crowd motion necessitates a detailed and updated survey of different techniques and trends in this field. This paper presents a survey on crowd detection and crowd density estimation from moving platform and surveys the different methods employed for this purpose. This review category and delineates several detections and counting estimation methods that have been applied for the examination of scenes from static and moving platforms.
Keywords: Crowd; Counting; Holistic and Local Motion Features; Estimation; Visual Surveillance; Moving Platform.
Real time vision-based hand gesture recognition using depth sensor and a stochastic context free grammar
by Jayesh Gangrade, Jyoti Bharti
Abstract: This paper presents a new algorithm in computer vision for the recognition of hand gestures. In the proposed system, Kinect sensor is used to track and segment hand in the clutter background and feature extracted by finger and an angle between them. Classify the hand posture using multi-class support vector machine. The hand gesture is recognised by stochastic context free grammar (SCFG). Stochastic context free grammar uses syntactic structure analysis and by this method, recognises hand gestures by set of production rules which consists of a combination of hand postures. The proposed algorithm is able to recognise various hand postures in real time with more than 97% accuracy.
Keywords: hand gesture; stochastic context free grammar; SCFG; multi-class support vector machine; Kinect sensor.
Special Issue on: MIWAI 2017 Computational Intelligence and Deep Learning for Computer Vision
Attention-Based Argumentation Mining
by Derwin Suhartono, Aryo Pradipta Gema, Suhendro Winton, Theodorus David, Mohamad Ivan Fanany, Aniati Murni Arymurthy
Abstract: This paper is intended to make a breakthrough in argumentation
mining field. Current trends in argumentation mining research use handcrafted
features and traditional machine learning (e.g., Support Vector Machine).
We worked on two tasks: identifying argument components and recognizing
insufficiently supported arguments. We utilize deep learning approach and
implement attention mechanism on top of it to gain the best result. We do also
implement Hierarchical Attention Network (HAN) in this task. HAN is a neural
network that gives attention to two levels, which are word-level and sentencelevel.
Deep learning with attention mechanism models can achieve better result
compared with other deep learning methods. This paper also proves that on
research task with hierarchically-structured data, HAN will perform remarkably
good. We do present our result on using XGBoost instead of a regular nonensemble
classifier as well.
Keywords: argumentation mining; hand-crafted features; deep learning; attention mechanism; hierarchical attention network; word-level; sentence-level; XGBoost.
SEGMENTATION AND RECOGNITION OF CHARACTERS ON TULU PALM LEAF MANUSCRIPTS
by Antony P.J., Savitha C.K.
Abstract: This paper proposes an efficient method for segmentation and recognition of handwritten characters from Tulu palm leaf manuscript images. The proposed method uses an automated tool with a combination of thresholding and edge detection technique to binarize the image. Further projection profile with connected component analysis is used to line and character segmentation. Deep convolution neural network (DCNN) model used here to extract features and recognize segmented Tulu characters efficiently with a recognition rate of 79.92 %. The results are verified using benchmark dataset, the AMADI_LontarSet to generalize our model to handwritten character recognition task. The results showed that our method outperforms from the existing state of art models.
Keywords: Handwritten Character Recognition; Palm Leaf; Segmentation; DCNN; Tulu.