Forthcoming and Online First Articles

International Journal of Biometrics

International Journal of Biometrics (IJBM)

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 Articles will not be published until the final proofs are validated by their authors.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 Biometrics (29 papers in press)

Regular Issues

    by Sameera Khan, Megha Mishra, Vishnu Kumar Mishra 
    Abstract: Use of forged signatures for fraudulent practices has become extremely common in recent days. Therefore, a significant role is performed by the automatic signature verification (SV) process. Such verifiers need large number of specimens of a person’s signature to establish the intrapersonal variability adequately. It is important to deal with the problem of data unavailability for training. A method to train with a single reference signature is proposed here to minimise the aforementioned limitation. This methodology is analysed by utilising a novel Gaussian gated recurrent unit neural network (2GRUNN) classifier. The single signature image is retrieved from database. Then, by using sinusoidal transformation, the signature duplication is performed. Next, pre-processing, feature extraction (FE), and feature selection (FS) are conducted. By employing linear chaotic shell game optimisation (LCSGO), the FS is executed. Extracted feature is fed to the proposed 2GRUNN for classification. Lastly, the results are compared with the existing methodologies.
    Keywords: offline signature verification; signature duplication; sinusoidal transformation; shell game optimisation; SGO; synthetic signature; synthetic signature database.
    DOI: 10.1504/IJBM.2023.10047175
  • A Comprehensive Study of Machine Learning Approaches for Keystroke Dynamics Authentication   Order a copy of this article
    by Tanya Teotia, Mridula Sharma, Haytham Elmiligi 
    Abstract: The most popular behavioural biometrics that is currently being considered as a second factor of authentication is keystroke dynamics. However, the adoption of this authentication technology faces several challenges, such as lack of a standard benchmark and evaluation methodology that could be used to compare the accuracy and performance of different frameworks. In this paper, we provide a comprehensive design space exploration of various machine learning frameworks to authenticate users based on keystroke dynamics. The paper also studies the machine learning design flow, discusses details of every single step in the process, and provides comparative analysis of possible options available for developers. The paper presents a comparative analysis of various machine learning frameworks supported by experimental analysis. Our experimental work analyses the efficiency of various machine algorithms, compares the impact of filter-based and wrapper-based feature selection techniques, and compares the accuracy of machine learning classifiers by using different feature sets.
    Keywords: machine learning; keystroke dynamics; classification; feature extraction; feature selection.
    DOI: 10.1504/IJBM.2023.10048651
  • Surface curvature based Completed Local Ternary Pattern for Texture Image Classification   Order a copy of this article
    by Xi Chen, Yunfei Zhang, Zaihong Zhou 
    Abstract: The curvature of two-dimensional function can describe the degree of surface curvature. When an image is treated as a discrete two-dimensional function, image curvature describes the structural relationship between local pixels of the image. Local ternary pattern is an effective image texture descriptor to encode shape index based on image curvature. In this paper, the completed local ternary pattern, which contains the symbol characteristics, amplitude characteristics and central pixel characteristics of the local ternary pattern of shape index (completed local ternary pattern based on shape index, SI-CLTP) are all considered at the same time. Experiments on two texture databases and one palmprint database fully show that shape index based completed local ternary pattern is an effective image texture descriptor.
    Keywords: image curvature; shape index; completed local ternary pattern; texture feature extraction.
    DOI: 10.1504/IJBM.2023.10049728
  • A Robust watermarking technique for biometric image authentication   Order a copy of this article
    by Mohamed Radouane, Nadia Idrissi Zouggari 
    Abstract: Biometric authentication data is becoming a crucial challenge to ensure copyright protection of digital images. A person’s biometric data is very sensitive; if exposed, it can pose a threat to a person’s identity and system security. Due to advances in watermarking, the most research is aimed at improving robustness to prevent attacks of biometric image. In this paper, we have proposed an invisible watermarking scheme for biometric image authentication using Gabor filter, contourlet transform, discrete wavelet transform (DWT) and singular value decomposition (SVD). Features are extracted from biometric image and an iris watermark is embedded. The proposed method was tested on CASIA-v5 and CASIA-Palmprint-v1 datasets. The evaluation performance is done by different measuring metrics. The proposed approach is compared with different methods in the literature. It is found that the watermarked images are robust over different attacks. Results show that the proposed method provides protection to biometric images and gives better results in terms of PSNR and NC.
    Keywords: copyright protection; authentication; Gabor filter; Contourlet transform; watermarking; discrete wavelet transform; DWT; singular value decomposition; SVD.
    DOI: 10.1504/IJBM.2023.10049905
  • A liveness detection system for sclera biometric applications   Order a copy of this article
    by Sumanta Das, Ishita De Ghosh, Abir Chattopadhyay 
    Abstract: Liveness detection is an essential security measure in biometric systems to determine whether the source of a biometric sample is a live person or a fake representation Sclera recognition has evolved as a promising biometric modality in recent years But liveness detection for sclera biometric applications has limited exploration till date We propose a two-phase liveness detection system to identify presentation attacks on mobile handset based sclera biometric applications A gaze detection model LivGaze is proposed in the first phase to verify whether the actual gaze direction matches with the requested gaze direction A mismatch indicates an incorrect user response, and hence a probable spoofing attack A deep model LivDense is proposed in the next phase to classify real and fake images The combined system LivSclera is efficient and cost-effective We have achieved an average-case AUC of 0 987, Accuracy of 0 99, and in the best-case 100% correct classifications.
    Keywords: Liveness detection; Presentation attack; Sclera biometric; LivGaze; LivDense; LivSclera; MASDUM; SBVPI.
    DOI: 10.1504/IJBM.2023.10050762
  • Use of Synthetic Signature Images for Biometric Authentication and Forensic Investigation   Order a copy of this article
    by Sameera Khan, Megha Mishra, Vishnu Kumar Mishra 
    Abstract: Handwritten signatures are one of the widely used biometric traits for authentication, and are constantly questioned as a forgery for this behavioural biometric is very common. Also due to privacy concerns, biometric databases are not easily available for training purposes. Due to this efficiency of automatic authentication systems is highly compromised. The use of biometric data in forensic investigation also suffers from the problem of inadequate data. One of the solutions to this problem is the use of synthetic datasets in place of real datasets. Such datasets suffer from a high risk of generating unrealistic specimens. Generating high-quality synthetic biometric images is still a challenge. This paper discusses some of the basic requirements for synthetic signature generation and also proposes an algorithm to generate synthetic images for handwritten signatures using sinusoidal transformation.
    Keywords: synthetic signature; synthetic biometric; synthetic databases; forensic investigation.
    DOI: 10.1504/IJBM.2023.10050915
  • PPG and Fingerprint : Robust Bimodal Biometric System   Order a copy of this article
    by Akhil Walia, Amit Kaul 
    Abstract: Technological advancements in the field of biometrics have resulted in development of completely automatic methods for human recognition leading to better and secure lifestyle. However, even though the biometric traits like fingerprint exhibit high degree of permanence, still certain security issues exist The main objective of this work is to tackle spoofing attacks by introducing some liveness property in the biometric system PPG signal possesses various properties such as inherent liveness, ease of acquisition and low development cost. A robust biometric system, immune to direct attacks, using a combination of PPG and fingerprint has been suggested in this work Score level fusion has been employed for integration of two modalities in parallel mode by optimizing the scores of individual traits using interior point algorithm. This bimodal biometric with PPG and fingerprint as two modalities seems quite practical. A CRR of 100% has been achieved in experiments conducted on 38 subjects.
    Keywords: Fingerprint; Photoplethysmogram (PPG); Score level fusion; Optimization.
    DOI: 10.1504/IJBM.2023.10051187
  • Iris Recognition System Using Deep Learning Techniques   Order a copy of this article
    by Amer Sallam, Hadeel Al Amery, Ahmed Y. A. Saeed 
    Abstract: Deep learning has been used and demonstrated intensively as a vital technique in data mining that can accurately and effectively evaluate enormous amounts of data for various applications. Iris recognition is one of those applications that necessitate complex algorithms for analysing and perfectly detecting the hidden patterns among its data in order to effectively distinguish one person from another. In this paper, an iris recognition system based on various deep learning techniques has been proposed. Through many experiments that were conducted on CASIA-V1 and ATVS datasets. The proposed system based on the Xception model was able to achieve significant results with 99.9% accuracy on CASIA-V1 dataset.
    Keywords: biometrics; deep learning; transfer learning; segmentation.
    DOI: 10.1504/IJBM.2023.10051537
  • Deep Learning with Spectrogram Image of Eye Movement for Biometrics   Order a copy of this article
    by Antônio Ricardo A. Brasil, Patrick M. Ciarelli, Izabella Rodrigues, Jefferson O. Andrade, Karin S. Komati 
    Abstract: Biometric studies are being used worldwide for a large variety of purposes, here we used eye movements (EM) from observers of natural images. Since some EM are involuntary, these prevent spoofing attacks. While prior research requires feature extraction manually from EM data to identify a person, we use a deep convolutional architecture that processes it as an image. The eye movements were treated as a signal, then transformed as a spectrogram of frequencies, and its image is the input for a convolutional architecture. We investigated two types of signals: Cartesian coordinates, and gaze angle over time. The proposal consists of a convolutional network architecture applied to the DOVES dataset, where stimuli are natural images. We obtained the accuracy for the eye angle spectrogram, on DOVES, about 73%, and for the eye coordinates spectrogram, 65%. These results indicated that EM can be treated as spectrogram images for biometric identification.
    Keywords: DOVES dataset; eye angle; natural image stimuli.
    DOI: 10.1504/IJBM.2023.10052380
  • Fingerprint Template Protection Using Snl Approach Based Pattern Transformation   Order a copy of this article
    by Joycy K. Antony, Kanagalakshmi K. 
    Abstract: This paper proposes Snake and Ladder (SNL)-based cancellable biometric model with two-phase, such as enrolment along with the authentication phase using Snake and Ladder approach. Here, the combination of two fingerprints is given as input for generating virtual identity. Moreover, the fingerprints are given as input to the enrolment phase. From one fingerprint, minutiae positions are obtained and from another one, orientation is obtained. The extracted information is further used to generate the combined minutiae template. Then, the SNL is applied which comprises certain strategies like intermixing, swapping, and simulated values insertion for providing a new virtual identity. Meanwhile, the authentication phase is implemented wherein the model needs two queries as fingerprints for confirmation. The proposed SNL-based cancellable biometric technique shows superior performance having maximal accuracy of 91.332%, minimal FAR of 5.434%, minimal FRR of 3.504%, and maximal GAR of 94.565%.
    Keywords: biometric system; fingerprint images; Snake Ladder approach; virtual identity; pattern transformation.
    DOI: 10.1504/IJBM.2023.10053554
  • A Secure Finger vein Recognition System using WS-Progressive GAN and C4 Classifier   Order a copy of this article
    by Sreemol R., Santosh Kumar M. B, Sreekumar A 
    Abstract: This paper proposes a secure finger vein reconstruction and recognition system utilising a novel weight standardisation-based progressive generative adversarial networks (WS-progressive GAN) as well as ' he' initialised chimp optimisation-based convolutions neural network (he-ChOA-CNN) classifier for overcoming security issues. Initially, the input images are pre-processed, and the reflection-based contrast limited adaptive histograms equalisation (RCLAHE) enhanced the pre-processed images. Next, bias locality-sensitive hashing (BLSH) generates hash values, through which the ameliorated images are secured. Next, the secured images are augmented and applied for WS-progressive GAN, which encodes and decodes the image for reconstructing the synthetic images. Then, the he-ChOA-CNN accepts the imperative features extracted as of the synthetic images as input for training. Amid testing, the identity of the person is recognised utilising the classifier output and the query image by detecting the gaps. Analogised to the prevailing methods, more accurate outcomes are attained by the proposed model, which is illustrated through the experimental outcomes.
    Keywords: reflection-based contrast limited adaptive histogram equalisation; finger vein; bias locality-sensitive hashing; BLSH; he initialisation; chimp optimisation-based CNN; generative adversarial network.
    DOI: 10.1504/IJBM.2024.10053719
  • Recent trends and challenges in human computer interaction using automatic emotion recognition: a review   Order a copy of this article
    by Sukhpreet Kaur, Nilima Kulkarni 
    Abstract: Automatic emotion recognition (AER) using facial expressions and electroencephalogram (EEG) signals is an interesting and booming area of research in the field of human computer interaction. This paper aims to identify the key state-of-art methodologies, understanding the standard workflow pipeline and knowing the existing findings. Different machine learning & deep learning approaches used recently for information preprocessing, feature extraction, feature classification and fusion schemes have also been explored. Furthermore, the purpose of this review work is to discuss the aspects motivating researchers to move from unimodal to multimodal AER systems. Also, this surveyed information is summarized in tabular forms to investigate the recent methods used and the results obtained. This comprehensive literature survey identifies the key points for inclusion of facial expressions and EEG signals over other channels. Also, the benefits of automated features which are being leveraged over hand crafted features for building improved real time emotion recognition systems.
    Keywords: Emotion recognition; Human computer interaction; Affective computing; Facial expressions;  EEG signals; Multimodal system.
    DOI: 10.1504/IJBM.2024.10053960
  • Arabic Offline writer identification on a new version of AHTID/MW database   Order a copy of this article
    by Anis Mezghani Mezghani, Mongi Kherallah 
    Abstract: Handwriting is considered to be one of the commonly used biometric modality to verify and identify persons in commercial, governmental and forensic applications. In order to test and compare the accuracy of a computer vision system, in general, and a biometric system in particular, standard rich databases must be publicly available. In this paper and for this purpose, we expose the different works of writer identification of Arabic handwritten text carried out on our already published database AHTID/MW. As researchers have achieved high identification rates, we propose to extend the AHTID/MW database with new Arabic native writers and raise the level of difficulty. A baseline is drawn on each text-line image, and ground truth information is provided for each text image. In addition we present our experiments on the database using a new approach based on combining a CNN for feature extraction with GMM-based emission probability estimates for classification.
    Keywords: Arabic writer identification; handwritten text image; AHTID/MW database; convolutional neural network; Gaussian mixture model; GMM.
    DOI: 10.1504/IJBM.2024.10054549
  • Exemplar-Based Facial Attribute Manipulation: A Review   Order a copy of this article
    by Padmashree G, Karunakar A.K 
    Abstract: Facial attribute manipulation gained a lot of attention when deep learning algorithms made amazing achievements during the last few years. Facial attribute manipulation is the process of combining or removing desired facial characteristics for a given image. Recently, generative adversarial networks (GANs) and encoder-decoder architecture have been used to tackle this problem, with promising results. We present a comprehensive overview of deep facial attribute analysis from the perspectives of manipulation using exemplars in this study. The model construction approaches, datasets, and performance evaluation measures that are frequently utilized are discussed. Following this, a review of various homogeneous and heterogeneous exemplar-based facial attribute manipulation algorithms is presented in detail. Furthermore, several other facial attribute-related issues and related applications in the real world, are also discussed. Lastly, we go over some of the issues that can arise as well as some interesting future research directions.
    Keywords: Facial attribute manipulation; Image generation; Deep Learning; Generative Adversarial Networks(GAN); Facial attributes; Generator; Discriminator.
    DOI: 10.1504/IJBM.2024.10054948

Special Issue on: Investigation of Robustness in Image Enhancement and Pre-processing Techniques for Biometrics and Computer Vision Applications

  • Computer succoured vaticination of multi-object detection and histogram enhancement in low vision   Order a copy of this article
    by Ramakant Chandrakar, Rohit Raja, Rohit Miri, Raj Kumar Patra, Upasana Sinha 
    Abstract: In this day and age, area calculation and detection methods are always in need of training data. Although, labelling objects are not volatile approaches to solve the detection problem. Recently, natural images contain multi-objects which are coming in one frame. To get a particular edge, this research performs object solarisation and also posterisation. This research mainly indicates the edge of objects by which we can separate an object by removing outside noises. The effectiveness of the proposed techniques can be proven by comparing with different methods. The novelty of the proposed method is demonstrated by experimental results and on the basis of different performance parameters. In the video frame, object detection is a challenging task, when the background changes, lighting conditions vary, and even in the presence of occlusion and clutter. The proposed algorithms detect and classify the moving objects (MO) in the given video frame. Lastly, the outcomes are proffered to corroborate the proposed method's effectiveness.
    Keywords: object; edge-enhancing; histo-channel; multi-object detection; posterisation.
    DOI: 10.1504/IJBM.2023.10053324
  • Human footprint biometrics for personal identification using artificial neural networks   Order a copy of this article
    by Kapil Kumar Nagwanshi, Amit Kumar Gupta, Tilottama Goswami, Sunil Pathak, Maleika Heenaye-Mamode Khan 
    Abstract: The philosophy of this study focuses on human footprint identification applicable for high-security applications such as the safety of public places, crime scene investigation, impostor identification, biotech labs and blue-chip labs, and identification of infants in hospitals. The paper proposes one of the low-cost hardware to scan the biometric human footprints that utilise image pre-processing and enhancement capabilities for obtaining the features. The algorithm enhances the footprint matching performance by selecting the three sets of local invariant feature detectors - histogram of gradients, maximally stable external regions, and speed up robust features; local binary pattern as texture descriptor, corner point detector, and PCA. Furthermore, descriptive statistics are generated from all the above mentioned footprint features and concatenated to create the final feature vector. The proposed footprint biometric identification will correctly identify or classify the person by training the system with patterns of the interested subjects using an artificial neural network model specially designed for this task. The proposed method gives the classification accuracy at a very encouraging level of 99.55%.
    Keywords: artificial neural networks; ANNs; biometric; classification; footprint; segmentation.
    DOI: 10.1504/IJBM.2023.10043092
  • Pulmonary lung nodule detection and classification through image enhancement and deep learning   Order a copy of this article
    by Nuthanakanti Bhaskar, Tumkur Sureshkumar Ganashree, Raj Kumar Patra 
    Abstract: In the medical image capturing process, the noise will be added in images and to analyse these images, proper enhancement and pre-process is required. Most of the researchers considered the same on CT lung images by using ROI selection, morphological operations, histogram equalisation, and binary thresholding methods, and they achieved around 95% of accuracy. To get better accuracy in the pre-processing stage of this present work resampling, morphological closure and image denoising techniques have been applied. In the image segmentation stage: for labelled nodule regions, the LIDC dataset is used, and for cancer/non-cancer labels, the KDSB17 dataset is used. In the segmentation stage: the U-net model has been applied. To minimise false positives of detected nodules, CNN is applied which converges to an 84.4% validation accuracy. The AUC of the CNN model was 0.6231, with a validation loss of 0.5646 and accuracy of 96%.
    Keywords: image enhancement; deep learning; lung cancer; U-net; CNN.
    DOI: 10.1504/IJBM.2023.10044525
  • MR image enhancement and brain tumour detection using soft computing and BWT with auto-enhance technique   Order a copy of this article
    by Nilesh Bhaskarrao Bahadure, Nagrajan Raju, Prasenjeet D. Patil 
    Abstract: In this research work new algorithm using soft-computing is presented for medical image enhancement with auto-enhance technique. Image enhancement is one of the most important classes of image analysis in image processing. This paper presents the complete review of the different performance parameters of popular image enhancement techniques and proposes a new methodology for improvising visualisation with preserving high-intensity value. The images with the colour intensity value cannot be processed directly by most of the enhancement techniques, hence a suitable colour model is chosen for processing and the proposed algorithm for the same are implemented. Accurate analysis of information from the region of interest area from the images is always a central issue in the image analysis, so with the help of this improved algorithm based on the soft computing technique, it is possible to enhance the images with best in the class, clarity, and visualisation. Simulation and experimental result on the different test images proves that the proposed algorithm gives better result as compared to other state of the art image enhancement techniques.
    Keywords: Berkeley wavelet transformation; BWT; fuzzy clustering means; FCMs; magnetic resonance imaging; MRI.
    DOI: 10.1504/IJBM.2023.10043342
  • Investigation of COVID-19 symptoms using deep learning based image enhancement scheme for x-ray medical images   Order a copy of this article
    by V. Pandimurugan, A.V. Prabu, S. Rajasoundaran, Sidheswar Routray, Nilesh Bhaskarrao Bahadure, D. Ratna Kishore 
    Abstract: Image enhancement is the inevitable technique for investigating various biological features. The biological image data can be obtained from computer tomography (CT), magnetic resonance imaging (MRI), and X-ray imaging. X-ray imaging is useful for getting the information from lungs and respiratory system. COVID-19 is a life-threatening contiguous disease for the past two years in the world. Patient's chest images playing an important role in the diagnosis of early detection of disease intensity. We propose a generative adversarial network (GAN) method that identifies COVID-19 from medical images and improves diagnostic sensitivity. Here we used virtual colouring methods and a platform for training the images by using a deep parental training method. Similarly, it gives optimal classification results with the help of well-defined image enhancement techniques and image extraction approaches. In our method, the accuracy level lies between 87.8% and 89.6% correspondingly for the dataset and synthetic dataset.
    Keywords: COVID-19; image classification; medical image enhancement generative adversarial network; deep learning.
    DOI: 10.1504/IJBM.2023.10044238
  • Vehicle recognition using convolution neural network   Order a copy of this article
    by Maleika Heenaye-Mamode Khan, Chonnoo Abubakar Siddick Khan, Rengony Mohammad Oumeir 
    Abstract: A significant challenge in the development of automatic vehicle make and model recognition (VMMR) is the distinguishing features between the different shapes based on the appearance of objects. The automatic recognition of vehicles based on their geometric shapes is in high demand. The diversity of make and model of vehicles further complicates this process. There are few applications that can recognise vehicles based on their geometric shape. To bridge this gap, convolution neural network (CNN) was adopted to predict the make and model of a car from either the rear view or front view of the vehicle using the pre-trained MobileNet. First, YOLOV3 has been used to detect the vehicle. The colour and the license plate of the vehicles are also extracted. An accuracy of 94.1% in the recognition of make of cars, 98.7% for the model, 99.1% for car plate registration number, and 90.3% for the colour was achieved.
    Keywords: convolution neural network; CNN; deep learning; segmentation; vehicle make and model recognition; VMMR.
    DOI: 10.1504/IJBM.2023.10044757
  • A hybrid approach for face recognition using LBP and multi level classifier   Order a copy of this article
    by Mukesh Kumar Gupta, Pankaj Dadheech, Ankit Kumar, Ashok Kumar Saini, Neha Janu, Sanwta Ram Dogiwal 
    Abstract: General face recognition, a task performed by humans in daily activities, is derived from a virtually uncontrolled environment. This paper presents a facial recognition system based on random forest and support vector machine. When compared to previous methods, this approach achieves high accuracy. In this paper, we proposed a hybrid method using SVM and random forest classification. The RF+SVM method predicts rapid growth in popularity. This combined method aids in high recognition speed with a wide range of faces and emotions. We also compared the algorithm to previous techniques. Each experiment made use of a free internet database. In the experiment, 400 photographs of 40 people are used. The reason for the improved results in this paper's hybrid vehicle classification methodology is that it combines the advantages of both traditional SVM and RF class methods. The proposed system has an accuracy of 98.6%.
    Keywords: biometrics; database; face recognition; SVM classifier; random forest.
    DOI: 10.1504/IJBM.2023.10045053
  • Performance optimisation of face recognition based on LBP with SVM and random forest classifier   Order a copy of this article
    by Ashutosh Kumar, Gajanand Sharma, Rajneesh Pareek, Satyajeet Sharma, Pankaj Dadheech, Mukesh Kumar Gupta 
    Abstract: Face recognition requirements are well described, as many industrial applications rely on them to achieve one or more goals. The local binary pattern is used for feature extraction, and the support vector machine (SVM) classifier is used for classification. To recognise faces or objects, we first offer the system with a testing database for training purposes. After that, we send an object image to the system, and the system extracts only relevant information or a portion of the face and processes it using LBP and SVM. When the illumination of the object image varies, the accuracy of facial recognition drops, and when just one training sample is provided, it does not provide the best matching results. In this paper, we describe a model that works by extracting local binary patterns from distinct sample photos, training the SVM classifier for the same, and then categorising input probe images using binary and multiclass SVM. In this case, the accuracy for 80% training and 20% testing ratio is 97.5%.
    Keywords: face recognition; PCA; LBP; support vector machine; SVM; random forest.
    DOI: 10.1504/IJBM.2023.10046520
  • M-ary modulation-based medical image watermarking for accessing quality of service of communication channel   Order a copy of this article
    by Ritu Agrawal, Manisha Sharma 
    Abstract: In an e-health environment, medical image protection is of prime importance as patient data is interleaved with medical images and broadcasted over the public internet. This paper presents a new electronic patient record (EPR) watermarking scheme for medical images in the mid-band discrete cosine transform using M-ary modulation. Robustness of EPR is enhanced by using a convolution encoder before embedding into the medical cover image. The imperceptibility and robust performance of the proposed watermarking scheme is tested on standard brain imaging modality using measures such as peak signal to noise ratio (PSNR), structural similarity index measure (SSIM), normalised cross-correlation (NCC) and bit error rate (BER) parameters. The proposed method achieves high PSNR and SSIM values, respectively at different watermark embedding factors for different modalities, which indicates better visual quality. The NCC and BER values of the scheme are high, indicating that the watermarking technique is appropriate for the protection of patient information and secure medical record dispersal over the public network. Furthermore, quality of service (QoS) of the communication channel is evaluated in terms of the embedded EPR, thus any separate mechanism is not required to evaluate the QoS of the communication channel.
    Keywords: medical image watermarking; MIW; EPR data hiding; region of non-interest; RONI; error control coding; ECC; M-ary modulation; quality of service; QoS; electronic patient record.
    DOI: 10.1504/IJBM.2023.10049800
  • Enhancement of retinal fundus image using multi-scale tophat transformation   Order a copy of this article
    by Meenu Garg, Sheifali Gupta, Gurjinder Kaur, Deepika Koundal 
    Abstract: In biomedical image processing, enhancement of fundus image is the challenging problem to reveal the hidden features of a retinal image. To enhance the features of retinal images, different image enhancement techniques are used. This paper presents a multi-scale tophat transformation technique for retinal image enhancement. Simulation is performed on the DRIVE dataset of fundus image using MATLAB. Various performance metrics have also been measured for checking the efficacy of the proposed method like CII, PSNR, clarity index (PL), mean square error (MSE), NAE. Comparative analysis of proposed transformation technique is made with existing techniques like HE, CLAHE, and BPDFHE in terms of different performance metrics. The proposed method achieved improvement in CII, PSNR, PL and reduction in MSE and NAE when compared with the previous existing techniques.
    Keywords: retinal fundus image; enhancement; multi-scale tophat transformation; white tophat; black tophat.
    DOI: 10.1504/IJBM.2023.10053323
  • Optimised denoising sparse autoencoder for the detection of outliers for face recognition   Order a copy of this article
    by X. Ascar Davix, D. Judson, R. Jeba 
    Abstract: Face recognition is a challenging research in the area of biometric applications due to the variations of input data such as not well centred faces, different pose, occlusions and poor resolution images. Detection and removal of outliers from the input data is essential to improve the performance of the face recognition algorithm. In this deep learning era, deep networks performed well in image classification. Deep networks extract features automatically from the data and updates the weights to reduce loss function. In this paper, we have presented optimised denoising sparse autoencoder (ODSAE) system to detect and remove the outliers in the input dataset. The autoencoder technique performs well in nonlinear transformations. It deals with convolutional layers for learning and provides meaningful information from the input. Softmax classifier is used for the classification of images. The experiment is carried out on Yale and AR face datasets and the results revealed better accuracy in removing outliers.
    Keywords: outlier; face recognition; denoising sparse autoencoder; biometric; deep learning.
    DOI: 10.1504/IJBM.2023.10048650
  • An empirical analysis of deep ensemble approach on COVID-19 and tuberculosis X-ray images   Order a copy of this article
    by Aakanksha Sharaff, Madhur Singhal, Arham Chouradiya, Pavan Gupta 
    Abstract: COVID-19 is a pandemic and a highly contagious disease that can severely damage the respiratory organs. Tuberculosis is also one of the leading respiratory diseases that affect public health. While COVID-19 has pushed the world into chaos and tuberculosis is still a persistent problem in many countries. A chest X-ray can provide plethora of information regarding the type of disease and the extent of damage to the lungs. Since X-rays are widely accessible and can be used in the diagnosis of COVID-19 or tuberculosis, this study aims to leverage those property to classify them in the category of COVID-19 infected lungs, tuberculosis infected lungs or normal lungs. In this paper, an ensemble deep learning model consisting of pre-trained models for feature extraction is used along with machine learning classifiers to classify the X-ray images. Various ensemble models were implemented and highest achieved accuracy among them was observed as 93%.
    Keywords: ensemble learning; COVID-19; tuberculosis; machine learning; MobileNet; Xception; ResNet50.
    DOI: 10.1504/IJBM.2023.10048929
  • Application of revised firefly algorithm and grey wolf optimisation on keystroke dynamics   Order a copy of this article
    by Purvashi Baynath, Maleika Heenaye-Mamode Khan 
    Abstract: In this digitalised world, to countermeasure computational threats, keystroke dynamics (KD) is one potential biometric feature that is used to enforce security over a network. Feature subset selection (FSS) process further aid for the increase of security by selecting the appropriate features, which make the replication of pattern difficult. For this purpose, two commonly known algorithms namely firefly algorithm (FA) and grey wolf algorithm (GWA) are being enhanced by incorporating chaos and pheromone in the network architecture. The experimental results have shown the robustness of the revised algorithms of firefly and grey wolf where optimum values for false acceptance rate (FAR) are being achieved. Besides, this study has shown that the revised FA fits better as a FSS technique by outperforming previous proposed solutions in terms of recognition rate (RR), where above 95% has been achieved, which shall aid in the reduction of attacks.
    Keywords: biometric; feature subset selection; FSS; firefly algorithm; FA; grey wolf optimisation; GWO; keystroke dynamics; KD; machine learning; ML.
    DOI: 10.1504/IJBM.2023.10051967
  • Deep learning-based lightweight approach to thermal super resolution   Order a copy of this article
    by Shashwat Pandey, Darshika Sharma, Basant Kumar, Himanshu Singh 
    Abstract: In this paper, we propose a thermal image super-resolution (SR) technique using a lightweight deep learning model which we refer to as thermal lightweight network (TherLiNet). We refine interpolated images using convolutional layers interleaved with different activation functions along with residual learning in the network. The effectiveness of the proposed architecture is evaluated against widely used deep learning-based super resolution models namely, super-resolution convolutional neural network (SRCNN), thermal enhancement network (TEN) and very deep super resolution (VDSR). Training and testing is done with different thermal datasets using different scale factors. To further explore the possibilities, red green blue (RGB) guided training is also performed and evaluated on the thermal image datasets. Peak signal to noise ratio (PSNR) and structural similarity index (SSIM), the most widely accepted parameters have been used for evaluation of the proposed model. The model is also compared to other models based on computation time to generate results. We also demonstrate the results in terms of qualitative values of the model compared to other super-resolution (SR) techniques.
    Keywords: thermal images; super resolution; deep learning; RGB guidance; thermal lightweight network; TherLiNet; thermal super resolution.
    DOI: 10.1504/IJBM.2023.10048267
  • Identification based on feature fusion of multimodal biometrics and deep learning   Order a copy of this article
    by Chahreddine Medjahed, Freha Mezzoudj, Abdellatif Rahmoun, Christophe Charrier 
    Abstract: This paper proposes a novel methodology for individuals identification based on convolutional neural network (CNN) and machine learning (ML) algorithms. The technique is based on fusioning biometric modalities at the feature level. For this purpose, several hybrid multimodal-biometric systems are used as a benchmark to measure accuracy of identification. In these systems, a CNN is used for each modality to extract modality-specific features for pattern of datasets. Machine learning algorithms are used to identify (classify) individuals. In this paper, we emphasise on performing fusion of biometric modalities at the feature level. We propose to apply the proposed algorithms on two challenging databases: FEI face database and IITD Palm Print V1 dataset. The results are showing good accuracies with many proposed multimodal biometric person identification systems. Through experimental runs on several multi-modal systems, it is clearly shown that best identification performance is obtained when using ResNet18 as deep learning tools for feature extraction along with linear discrimination machine learning algorithm.
    Keywords: biometrics; multi-biometric system; feature level fusion; score level fusion; deep learning; machine learning.
    DOI: 10.1504/IJBM.2022.10047593