Biometric authentication especially using face recognition, is still a big, challenging problem. The face exhibits various semantic information with its numerous expressions. The exhibitions of dynamic expressions of faces are the main challenges for the biometric system. However, researchers are continuously trying to enhance facial recognition robustness. This work proposes a multi-classifier-based ensemble system for effective face recognition. Our proposed system has two modules: 1) an optimisation module that decreases computational cost using feature sets; 2) a fusion module with multiple classifiers to advance accuracy. The feature set is extracted using local descriptors named LBP, DS-LBP, and LGS. Feature sets are optimised using a genetic algorithm (GA). Optimised feature sets are classified distinctly, and results are united using decision-level fusion methods like AND-rule, OR-rule, and majority voting. Experiments accomplished on LFW, BioID, and LAG datasets and it shows that the proposed ensemble system is more efficient and robust.

Fingerprint recognition has become a cornerstone technology in various applications, ranging from law enforcement to smartphone security. However, the quality of fingerprint images can significantly affect the performance of recognition systems. Traditional methods of assessing fingerprint image quality (FIQ) often rely on handcrafted features and simplistic models, which cannot capture the complexity of real-world scenarios. This research proposes an enhanced machine learning- based approach for fingerprint image quality assessment (FIQA) to address this limitation. Collecting and pre-processing a dataset of 6,000 fingerprint images from 600 individuals, each with varying clarity, contrast, illumination, and noise levels, from the Sokoto Coventry Fingerprint (SOCOFing) dataset. Apply image enhancement techniques such as Gabor filtering for texture feature enhancement and minutiae extraction to extract distinctive features. Authors perform feature extraction using the histogram of oriented gradients (HOG) descriptors. Next, divide the dataset into training and testing sets, and design and train various machine learning models such as convolutional neural networks (CNN), support vector machines (SVM), and multi-layer perceptron's (MLP) for the proposed model classification. Evaluate the performance of model on the testing dataset using accuracy and other relevant metrics to ensure robust performance estimation. Implementation results shows that the proposed model has higher accuracy in comparison to the existing conventional methods.

Occlusion plays a critical role in accurate image analysis and feature identification in face recognition. Occlusions caused by random objects on an image can make it challenging to match the occluded image with the registered image in a database. To the best of the authors' knowledge, all well-known methods have focused on the problem of single occlusion in biometrics. To address the issue of multi-level occlusion, a novel feature-oriented GAN-based multi-occlusion removal framework (GMORF) is proposed. It consists of four components: face alignment using a spatial transformer network, a binary map generation with QUnet++, multi-occlusion removal through pixel-level similarity, and feature-level similarity enforcement using ResNet for improved inpainting. All components are integrated into an end-to-end network, and extensive experiments demonstrate GMORF's effectiveness in biometric verification with occluded faces.

This paper makes a literature survey on biometric image quality assessment (BIQA) techniques focusing on physiological traits. It covers a wide range of methodologies, metrics and evaluation techniques. Objective image quality assessment (IQA) methods primarily focus on quantifying image quality using computational algorithms, while subjective IQA methods rely on human observers to provide quality ratings based on visual perception. The paper categorises the existing IQA techniques based on their characteristics and applications. It explores different types of distortion models, such as noise, blur, compression artefacts, and colour inconsistencies that are commonly encountered in digital images. Additionally, it investigates the influence of various factors on image quality, including image content, context and viewer preferences. The survey concludes by summarising the key findings and identifying the current trends and future directions in BIQA research.

Face recognition system have gained significant attention from last few years due to its applications in several domains such as security, authentication, and surveillance. The performance of face recognition is affected by analysing facial quality with a single property. However, there are still some attributes, such as occlusion and entropy, that are not well studied but play a significant role in face recognition. Measuring the quality of images is likely to filter out poor-quality images, which can improve the performance of downstream tasks. This paper presents a comparative study of various face image quality assessment (FIQA) techniques to select the best image for better recognition. In this study, the author’s measure some image quality factors to estimate the technique in the context of a face recognition system, which is followed by proposing an efficient fusion technique to combine all these factors to get a single face image quality index. The proposed technique has been tested statistically to obtain the confidence level between the FIQA technique and human observers, and it has demonstrated better performance in face recognition techniques.

In this paper, we develop an efficient mutual information based similarity metric for 3D medical image registration. The efficiency of the metric lies in the computation of mutual information, which uses modified algorithms for calculating entropy and joint entropy. We implemented the newly developed Efficient Entropy Mutual Information (EEMI) metric in SimpleITK, which is an open source image registration and segmentation toolkit. We designed 24 medical image registration frameworks using four similarity metrics, namely Mean Squares (MS), Joint Histogram Mutual Information (JHMI), Mattes Mutual Information (MattesMI) and our proposed EEMI, and six optimizers namely, Gradient Descent (GD), Conjugate Geadient Line Search (CGLS), 1+1 Evolutionary, Powell, Nelder-Mead (Amoeba) and Limited Memory Broyden Fletcher Goldfarb Shannon (LBFGS2). Using these frameworks, we performed elaborate comparative evaluation and analysis of EEMI in terms of registration accuracy and computation time. We used four different medical image data sets for our experiments. Data consisted of intra-modal and inter-modal image pairs of the brain and thorax obtained from different medical institutions as well as publicly available databases. Registration results prove the superiority and consistency of performance of EEMI compared to MS and JHMI. When compared with the benchmark MattesMI metric, performance of EEMI is on a par with respect to Dice score, Jaccard score and Hausdorff distance. With respect to computation time, EEMI is faster with GD, CGLS and Amoeba optimizers with 61.29

The widespread usage of mobile devices and social media has led to a growing interest in face recognition technology. This study introduces a novel deep ensemble method designed to enhance facial recognition accuracy on a mobile selfie dataset by integrating three pre-trained models, viz. Inception-v3, ResNet-50, and EfficientNet B7 for automatic feature extraction and representation. The approach utilizes feature-level fusion through concatenation, followed by dimensionality reduction via principal component analysis (PCA). Feature optimization is carried out using the Firefly algorithm, and classification is achieved through a soft voting ensemble of classifiers, including Support Vector Machine (SVM), Random Forest, and a Deep Neural Network (DNN). When evaluated on the LFW, UTK face, and Wild Selfie datasets, the proposed method achieved recognition accuracies of 99.76%, 98.92%, and 98.73%, respectively, demonstrating competitive and significantly improved performance over existing models. The results indicate that the system performs effectively in real-world conditions, especially in environments with varying conditions.

Face recognition systems are crucial in security and surveillance. However, their effectiveness depends on the quality of input face images. This paper introduces a novel Face Image Quality Assessment (FIQA) framework to enhance recognition accuracy. It evaluates image quality using various factors and combines them to classify the face quality index. The technique is evaluated on the Color-Feret dataset, outperforming existing methods with a strong correlation (0.95) between system and human scores.

Recent developments in IoT (Internet of Things) and its importance are significantly accepted in different applications of medical research, automobile sector, robotics, national security, and real-life usage. Securing the interface between IoT and the real-world is one of the challenging tasks for every researcher. This paper presents a watermarking scheme to protect the image database used in the presentation layer of IoT applications. The host image is decomposed using the Lifting wavelet transform (LWT) and fixed-size blocks of low-frequency components are obtained. Procedurally selected blocks of frequency components called a significant set of blocks (SSB) are used to quantize the watermark bits into it. Considering each block similar to the node of wireless networks an algorithm for block selection is proposed. Watermark extraction from an attacked watermarked image is performed using an adaptive thresholding approach. Key-based randomization at various levels provides the security feature to the proposed scheme. The LWT is used to make the algorithm more robust and computationally fast. However, randomly selected root based SSB generation leads the scheme more secure from an external intruder. The scheme performs significantly well under various signal processing operations; and outperforms in comparison with other existing schemes.

Signature is a biometrics trait widely used for personal verification in financial and most other organizations where financial and relevant types of transactions are done manually with signed authorized papers. A signature verification system aims to verify the minor structural differences between genuine and forged signatures, as most skilled forgery signatures look similar to their respective genuine signatures with specific deformations. Signature verification in a multi-cultural country like India is challenging in both writer-independent and script-independent scenarios where the Indian population uses multiple scripts to write their signatures. This paper reports a writer-independent offline signature verification system that uses Convolutional Neural Network (CNN) architecture for feature extraction and classification. The objective of the proposed work is to model a CNN-based adaptable system to verify multi-scripted offline signatures. The model has been trained and tested on two publicly available databases, viz. CEDAR and BH-Sig260, which consist of Hindi, Bengali, and English signatures. Individual signature classes of unique scripts and a combination of these scripts have been considered for testing the proposed model that determines verification accuracies of 90%, 95%, 98.33%, and 93.33%, respectively. Experimental results are compelling, and the proposed model outperforms the verification accuracies of some well-known models.

Authenticating important documents by identifying individuals using handwritten signatures make signature verification a critical task. Interpersonal similarity and intrapersonal variation of individuals along with high skilled imitation of signature structure make automatic signature verification a challenging task. In such scenarios, a signature verification system should detect the small differences between genuine and forged signatures with high efficacy. This paper proposed a novel approach towards offline signature verification where a hybrid deep learning network, consisting of a Convolutional Neural Network and a Bidirectional Long Short Term Memory network is used. Signature written with freehand and an imitation of it are almost identical structurally. Deep Neural Network is used to recognize skilled forgery from genuine signatures because of its capability to learn critical details and subtle patterns from the image pixels. A Convolutional Neural Network is trained, and the trained network is then used to extract diverse features of the signature images. The generated feature vectors are then used for classification using Bidirectional Long Short Term Memory. The hybrid deep learning network classifies the input signature as skilled forgery or genuine with high accuracy. For this work, state-of-the-art datasets, such as, GPDS-300, GPDS-Bengali, GPDS-Devanagari, CEDAR, BHSig260-Bengali, BHSig260-Hindi, and a local dataset, Meitei Mayek signature are used. In order to verify the robustness of the system, different multi-scripted offline signatures belonging to multi-lingual Indian society, are used for evaluation. The experimental results determined from multi-scripted signatures, exhibit that the proposed system is found comparable to many state-of-the-art systems and in some specific cases, it out performs some of the existing systems.

Human face detection along with its localization is a difficult task when the face is presented in the cluttered scene in an unconstrained scenario that might be with arbitrary pose variations, occlusions, random backgrounds and infrared (IR) environment. This paper proposes a novel face detection method which can address some of these issues and challenges quite successfully during face detection in unconstrained as well as infrared environments. It makes use of Fast Successive Mean Quantization Transform (FastSMQT) features for image enhancement and feature representation to deal with illumination and sensor insensitiveness. A split up Sparse Network of Winnows (SNoW) with Winnow updating rule is then exploited to speed up the original SNoW classifier. Finally, the features and classifiers are combined together with skin detection algorithm for face detection in crowd image and head orientation correction of near infrared faces. The proposed face detector is robust in handling pose, occlusion, illumination, blur and low image resolution. The experiment is performed on six challenging and publicly available databases, viz. BIOID, LFW, FDDB, UFI, WIDER FACE and IIT Delhi near infrared. The experimental results depict that the proposed method outperforms traditional as well as some advanced methods in detecting unconstrained and infrared faces under challenging situations.

Fractional calculus is an abstract idea exploring interpretations of differentiation having non-integer order. For a very long time, it was considered as a topic of mere theoretical interest. However, the introduction of several useful definitions of fractional derivatives has extended its domain to applications. Supported by computational power and algorithmic representations, fractional calculus has emerged as a multifarious domain. It has been found that the fractional derivatives are capable of incorporating memory into the system and thus suitable to improve the performance of locality-aware tasks such as image processing and computer vision in general. This article presents an extensive survey of fractional-order derivative-based techniques that are used in computer vision. It briefly introduces the basics and presents applications of the fractional calculus in six different domains viz. edge detection, optical flow, image segmentation, image de-noising, image recognition, and object detection. The fractional derivatives ensure noise resilience and can preserve both high and low-frequency components of an image. The relative similarity of neighboring pixels can get affected by an error, noise, or non–homogeneous illumination in an image. In that case, the fractional differentiation can model special similarities and help compensate for the issue suitably. The fractional derivatives can be evaluated for discontinuous functions, which help estimate discontinuous optical flow. The order of the differentiation also provides an additional degree of freedom in the optimization process. This study shows the successful implementations of fractional calculus in computer vision and contributes to bringing out challenges and future scopes.

The process of aligning one image, in the coordinate system of another is called registration. Image registration is vital in the medical domain and is used for diagnosis, therapy planning, and treatment of diseases. Due to its huge applicability and importance, medical image registration has emerged to be a separate domain of research. Beginning from the invasive landmark based registration, innumerable algorithms have been proposed to register two images of the human physiology. However, a breakthrough in the literature occurred when an information theory based measure, mutual information was used to register two images. Since then a large number of new algorithms have developed, which use mutual information for fully automatic registration of medical images. This paper is a survey of these algorithms. Beginning from its development, it discusses about some of the major works done on mutual information based image registration. Some comparative studies with other algorithms have also been discussed. The paper ends with a discussion of the developments in medical image registration algorithms post mutual information, which primarily include deep neural network (DNN) based algorithms.

This paper presents an efficient pattern matching method which makes use of the local-region-based light-weight feature descriptor, called Symmetric Neighbour Local Pattern (SNLP). It relies on the spatial relationship between reference pixel and its neighbours located symmetrically in horizontal, vertical and diagonal directions. SNLP is proved to be invariant to scale, illumination, image distortion and partial occlusion. Efficacy of the proposed method has been evaluated on two publically available databases and the results are found to be convincing under several challenges.

Low resolution (LR) and very low resolution (VLR) face images captured by surveillance cameras make automatic face recognition (AFR) a challenging task. The performance of an automatic face recognition system (AFRS) degrades when these types of face images are compared with high resolution (HR) gallery images. This paper has presented a face identification system called Cross-Resolution Face Identification System, to address this issue. It makes use of the Deep Convolutional Neural Network (DCNN) having different pooling operations to extract resolution robust features from high resolution, low resolution and very low resolution face images. The proposed system is evaluated on four face databases, namely, the ORL, the extended Yale face B, the LFW, and the Georgia Tech under three cross resolution environmental conditions based on resolution of probe images (i.e., high resolution to high resolution, low resolution to high resolution, and very low resolution to high resolution).The experimental outcomes exhibit the effectiveness of the proposed face identification system.

The purpose of this paper is to give an overview of various well known medical image registration techniques with a special focus on registration between anatomical and functional medical images. Examples of anatomical medical images (AMI) are Computer Tomography (CT), Magnetic Resonance Images (MRI), X-ray radiographs and ultrasound etc. whereas Positron Emission Tomography (PET), Single Photon Emission Tomography (SPECT) and fMRI are examples of functional medical images (FMI). Irrespective of such types (AMI or FMI), every case can be considered as a medical imaging modality. All these modalities are widely used by clinicians to study the structure/functionality of human body parts for diagnosis and treatment. It is frequently required to combine PET/SPECT with CT/MRI to simultaneous study the metabolic and molecular information received through PET/SPECT with fine anatomical details observed by CT/MRI. This concurrent study will help in the diagnosis and localization of many diseases like cancer, blockage in coronary arteries and brain-related diseases like Parkinson, Alzheimer etc. Further, in many cases, clinicians are required to co-register one or more anatomical images with functional images, for example, ultrasound-guided biopsy fused with PET and MRI. This registration can be done either at the hardware level or at the software level. The introduction of integrated PET-CT machine increases the acceptability of hardware-based registration systems as compared to software-based methods among the medics. One possible reason for this is the lack of validation of results achieved through software-based registration methods. On the other hand, software-based registration methods also have many advantages over the hardware-based registration systems like lesser exposure to radiation and no need for new investment on hardware etc. In this paper, both the methods with their merits and demerits are discussed in detail.

Background Statin-associated muscle symptoms (SAMS) are the major side effects reported for statins. Data from previous studies suggest that 7–29% of patients on statin had associated muscle symptoms. In the UK, there is a lack of corresponding data on SAMS and factors associated with the development of SAMS. Objective This analysis is aimed at establishing the prevalence of SAMS and identifying major contributory risk factors in patients attending a lipid clinic. Methods Clinical records of 535 consecutive patients, who visited the lipid clinic in the University Hospitals of Leicester, were studied retrospectively between 2009 and 2012. SAMS were defined by the presence of muscle symptoms with two or more different statins. Patients who reported muscle symptoms to statin with one or no rechallenge were excluded. The association of SAMS with clinical characteristics such as age and BMI, sex, smoking, excess alcohol, comorbidities, and medications was tested for statistical significance. A binomial logistic regression model was applied to adjust for risk factors significantly associated with SAMS. Results The prevalence of SAMS was found to be 11%. On unadjusted analysis, the mean age of patients who had SAMS was significantly higher than those without SAMS (59.4 ± 10.5 years vs. 50.3 ± 13.4 years, respectively, P < 0.001). Nonsmokers were more likely to develop SAMS in comparison to active smokers (P = 0.037). Patients taking antihypertensive medications were more likely to develop SAMS (P = 0.010). In binomial logistic regression analysis, only age was positively and significantly associated with SAMS after adjusting for other risk factors (β = 0.054, P = 0.001). Conclusion To the best of our knowledge, this study is the largest cohort of patients with SAMS in the United Kingdom. Our data suggest that the prevalence of SAMS is 11% and increased age is a risk factor associated with the development of SAMS in our cohort of patients.

Background: Concurrent chemo-radiation is the standard treatment worldwide for locally advanced squamous Cell carcinoma cervix. However, conventional chemo-radiotherapy is also associated with unacceptable local and systemic failure rates for locally advanced disease. Biologically squamous cell carcinoma of head- neck cancer and cervical cancer behaves quite similarly in response to radiotherapy. So, it can be expected that, altered fractionation can increase the local control in case of squamous cell carcinoma cervix than conventional radiotherapy. There is no randomised control trial for carcinoma cervix till date, which compares conventional chemo-radiation with hypo-fractionated chemo-radiation. Aims And Objectives: The present study was planned to compare local disease control and acute toxicity of conventional chemo-radiation with hypo-fractionated chemo-radiation in locally advanced carcinoma cervix. Materials And Methods: In Conventional Chemo-radiation Arm A patients (n=30) received external beam radiotherapy 50 Gy in 25 fractions in 5 weeks accompanied by weekly intravenous Cisplatin 40mg/m2 followed by intracavitary brachytherapy 7 Gy per fraction once in a week for 3 weeks. The second group of hypo-fractionated Arm B received external beam radiotherapy 45 Gy in 20 fractions in 4 weeks accompanied by weekly intravenous Cisplatin 40mg/m2 followed by intracavitary brachytherapy 9 Gy per fraction once in a week for 2 weeks. Results: Grade II diarrhea were seen more in Arm B 17 (56.66%) compare to Arm A 12(40%) and grade III diarrhea was seen 4 (3.33%) in Arm B and 2(6.66%) in Arm A. At 2 months and 6 months after completion of treatment Complete response were 25 (83.4%) in Arm A compare to 22 (73.3%) in Arm B and 20 (74.1%) in Arm A and 18 (72%) in Arm B respectively. Conclusion: Hypo-fractioned radiotherapy may be used as an alternate protocol for treatment of locally advanced carcinoma cervix with acceptable toxicities.

Visible face recognition systems are subjected to failure when recognizing the faces in unconstrained scenarios. So, recognizing faces under variable and low illumination conditions are more important since most of the security breaches happen during night time. Near Infrared (NIR) spectrum enables to acquire high quality images, even without any external source of light and hence it is a good method for solving the problem of illumination. Further, the soft biometric trait, gender classification and non verbal communication, facial expression recognition has also been addressed in the NIR spectrum. In this paper, a method has been proposed to recognize the face along with gender classification and facial expression recognition in NIR spectrum. The proposed method is based on transfer learning and it consists of three core components, i) training with small scale NIR images ii) matching NIR-NIR images (homogeneous) and iii) classification. Training on NIR images produce features using transfer learning which has been pre-trained on large scale VIS face images. Next, matching is performed between NIR-NIR spectrum of both training and testing faces. Then it is classified using three, separate SVM classifiers, one for face recognition, the second one for gender classification and the third one for facial expression recognition. It has been observed that the method gives state-of-the-art accuracy on the publicly available, challenging, benchmark datasets CASIA NIR-VIS 2.0, Oulu-CASIA NIR-VIS, PolyU, CBSR, IIT Kh and HITSZ for face recognition. Further, for gender classification the Oulu-CASIA NIR-VIS, PolyU,and IIT Kh has been analyzed and for facial expression the Oulu-CASIA NIR-VIS dataset has been analyzed.