Presentation attack detection for iris recognition using deep learning
01 Jul 2020-International Journal of Systems Assurance Engineering and Management (Springer India)-Vol. 11, Iss: 2, pp 232-238
TL;DR: Deep Convolutional Neural Networks are used to detect spoofing techniques with superior results as compared to the existing state-of-the-art techniques on iris recognition.
Abstract: Iris recognition is used in various applications to identify a person. However, presentation attacks are making such systems vulnerable. Intruders can impersonate an individual to get entry into a system. In this paper, we have focused on print attacks, in which an intruder can use various techniques like printing of iris photographs to present to the sensor. Experiments conducted on the IIIT-WVU iris dataset show that print attack images of live iris images, use of contact lenses and conjunction of both can play a significant role in deceiving the iris recognition systems. The paper makes use of deep Convolutional Neural Networks to detect such spoofing techniques with superior results as compared to the existing state-of-the-art techniques.
••01 Jan 2021
TL;DR: An overview of some systems and applications that applied deep learning for biometric systems and classifying them according to biometrics modalities is provided and a detailed analysis of several existing approaches that combine biometric system with deep learning methods is drawn.
Abstract: Deep learning is an evolutionary advancement in the field of machine learning. The technique has been adopted in several areas where the computer after processing volumes of data are expected to make intelligent decisions. An important field of application for deep learning is the area of biometrics wherein the patterns within the uniquely human traits are recognized. Recently, many systems and applications applied deep learning for biometric systems. The deep network is trained on the vast range of patterns, and once the network has learnt all the unique features from the data set, it can be used to recognize similar patterns. Biometric technology that is being widely used by security applications includes recognition based on face, fingerprint, iris, ear, palm-print, voice and gait. This paper provides an overview of some systems and applications that applied deep learning for biometric systems and classifying them according to biometrics modalities. Moreover, we are reviewing the existing system and performance indicators. After a detailed analysis of several existing approaches that combine biometric system with deep learning methods, we draw our conclusion.
06 Oct 2021
TL;DR: In this article, an exhaustive survey of papers on the biometric ILD was performed by searching the most applicable digital libraries, where papers were filtered based on the predefined inclusion and exclusion criteria.
Abstract: Biometrics is progressively becoming vital due to vulnerabilities of traditional security systems leading to frequent security breaches. Biometrics is an automated device that studies human beings’ physiological and behavioral features for their unique classification. Iris-based authentication offers stronger, unique, and contactless identification of the user. Iris liveness detection (ILD) confronts challenges such as spoofing attacks with contact lenses, replayed video, and print attacks, etc. Many researchers focus on ILD to guard the biometric system from attack. Hence, it is vital to study the prevailing research explicitly associated with the ILD to address how developing technologies can offer resolutions to lessen the evolving threats. An exhaustive survey of papers on the biometric ILD was performed by searching the most applicable digital libraries. Papers were filtered based on the predefined inclusion and exclusion criteria. Thematic analysis was performed for scrutinizing the data extracted from the selected papers. The exhaustive review now outlines the different feature extraction techniques, classifiers, datasets and presents their critical evaluation. Importantly, the study also discusses the projects, research works for detecting the iris spoofing attacks. The work then realizes in the discovery of the research gaps and challenges in the field of ILD. Many works were restricted to handcrafted methods of feature extraction, which are confronted with bigger feature sizes. The study discloses that dep learning based automated ILD techniques shows higher potential than machine learning techniques. Acquiring an ILD dataset that addresses all the common Iris spoofing attacks is also a need of the time. The survey, thus, opens practical challenges in the field of ILD from data collection to liveness detection and encourage future research.
TL;DR: The authors present their own approach to iris-based human identity recognition with DFFT components selected with principal component analysis algorithm, and show that satisfactory results can be obtained with the proposed method.
Abstract: One of the most important modules of computer systems is the one that is responsible for user safety. It was proven that simple passwords and logins cannot guarantee high efficiency and are easy to obtain by the hackers. The well-known alternative is identity recognition based on biometrics. In recent years, more interest was observed in iris as a biometrics trait. It was caused due to high efficiency and accuracy guaranteed by this measurable feature. The consequences of such interest are observable in the literature. There are multiple, diversified approaches proposed by different authors. However, neither of them uses discrete fast Fourier transform (DFFT) components to describe iris sample. In this work, the authors present their own approach to iris-based human identity recognition with DFFT components selected with principal component analysis algorithm. For classification, three algorithms were used—k-nearest neighbors, support vector machines and artificial neural networks. Performed tests have shown that satisfactory results can be obtained with the proposed method.
TL;DR: A comprehensive analysis ofDeep learning techniques developed for two main sub-tasks in iris biometrics: segmentation and recognition and delve deep into deep learning techniques for forensic application, especially in post-mortem iris recognition.
Abstract: Inthissurvey, we provide a comprehensive review of more than 200 papers, technical reports, and GitHub repositories published over the last 10 years on the recent developments of deep learning techniques for iris recognition, covering broad topics on algorithm designs, open-source tools, open challenges, and emerging research. First, we conduct a comprehensive analysis of deep learning techniques developed for two main sub-tasks in iris biometrics: segmentation and recognition. Second, we focus on deep learning techniques for the robustness of iris recognition systems against presentation attacks and via human-machine pairing. Third, we delve deep into deep learning techniques for forensic application, especially in post-mortem iris recognition. Fourth, we review open-source resources and tools in deep learning techniques for iris recognition. Finally, we highlight the technical challenges, emerging research trends, and outlook for the future of deep learning in iris recognition. very large VGGFace2 dataset, and fine-tuned for iris recognition using triplet loss. The paper is oriented towards postmortem iris analysis, so the methods use a mixture of live and postmortem images for training and evaluation.
TL;DR: A segmentation method for extracting the hemorrhage out of CT (computed tomography) images of brain by using the features of fuzzy clustering together with the level-set segmentation methods, which eradicates the requirement of manual initialization and re-initialization process and speeds up the process related with evolution of function associated with level- set.
Abstract: The paper presents a segmentation method for extracting the hemorrhage out of CT (computed tomography) images of brain by using the features of fuzzy clustering together with the level-set segmentation method. The fuzzy clustering is utilized for initialization of level-set function that evolves to extract the desired hemorrhagic region. In addition, the fuzzy clustering has also been utilized for estimating the parameters which control the propagation of level set function. The proposed method eradicates the requirement of manual initialization and re-initialization process which is very much time inefficient, as required by majority of conventional level-set segmentation methods and thus speeding up the process related with evolution of function associated with level-set. The proposed method has been implemented over a dataset containing 300 CT images of brain with hemorrhages of various sizes and shapes and the performance of proposed method is compared with existing techniques like fuzzy c- mean (FCM) clustering and region growing. The results of this method are observed to have highest values related with similarity indices such as overlap metric, accuracy, specificity and sensitivity with values as 87.46%, 85.40%, 98.79% and 79.91% respectively for given dataset of 300 images.
01 Aug 1988-Graphical Models \/graphical Models and Image Processing \/computer Vision, Graphics, and Image Processing
TL;DR: This survey will provide a useful guide to quickly acquaint researchers with the main literature in this research area and it seems likely that the Hough transform will be an increasingly used technique.
Abstract: We present a comprehensive review of the Hough transform, HT, in image processing and computer vision. It has long been recognized as a technique of almost unique promise for shape and motion analysis in images containing noisy, missing, and extraneous data but its adoption has been slow due to its computational and storage complexity and the lack of a detailed understanding of its properties. However, in recent years much progress has been made in these areas. In this review we discuss ideas for the efficient implementation of the HT and present results on the analytic and empirical performance of various methods. We also report the relationship of Hough methods and other transforms and consider applications in which the HT has been used. It seems likely that the HT will be an increasingly used technique and we hope that this survey will provide a useful guide to quickly acquaint researchers with the main literature in this research area.
01 Jan 1999
TL;DR: A survey of Hough Transform and its variants, their limitations and the modifications made to overcome them, the implementation issues in software and hardware, and applications in various fields is done.
Abstract: In 1962 Hough earned the patent for a method 1], popularly called Hough Transform (HT) that efficiently identifies lines in images. It is an important tool even after the golden jubilee year of existence, as evidenced by more than 2500 research papers dealing with its variants, generalizations, properties and applications in diverse fields. The current paper is a survey of HT and its variants, their limitations and the modifications made to overcome them, the implementation issues in software and hardware, and applications in various fields. Our survey, along with more than 200 references, will help the researchers and students to get a comprehensive view on HT and guide them in applying it properly to their problems of interest. HighlightsA survey of Hough Transform (HT) has been done.The main variants of HT and its formulations have been described.The hardware and software implementations of HT have been described.HT has many applications in diverse fields. Out of them some applications in some selected fields have been mentioned.
TL;DR: This procedure is an extension and improvement of the circle-finding concept sketched by Duda and Hart as an extension of the Hough straight-line finder.
Abstract: We describe an efficient procedure for detecting approximate circles and approximately circular arcs of varying gray levels in an edge-enhanced digitized picture. This procedure is an extension and improvement of the circle-finding concept sketched by Duda and Hart  as an extension of the Hough straight-line finder .
TL;DR: Previous work on physics-based anomaly detection based on a unified taxonomy that allows us to identify limitations and unexplored challenges and to propose new solutions is reviewed.
Abstract: Monitoring the “physics” of cyber-physical systems to detect attacks is a growing area of research. In its basic form, a security monitor creates time-series models of sensor readings for an industrial control system and identifies anomalies in these measurements to identify potentially false control commands or false sensor readings. In this article, we review previous work on physics-based anomaly detection based on a unified taxonomy that allows us to identify limitations and unexplored challenges and to propose new solutions.
Related Papers (5)
01 Oct 2019
03 Mar 2016