Presentation Attack Detection for Iris Recognition: An Assessment of the State-of-the-Art
TL;DR: In this paper, different categories of presentation attack are described and placed in an application-relevant framework, and the state-of-the-art in detecting each category of attack is summarized.
Abstract: Iris recognition is increasingly used in large-scale applications. As a result, presentation attack detection for iris recognition takes on fundamental importance. This survey covers the diverse research literature on this topic. Different categories of presentation attack are described and placed in an application-relevant framework, and the state of the art in detecting each category of attack is summarized. One conclusion from this is that presentation attack detection for iris recognition is not yet a solved problem. Datasets available for research are described, research directions for the near- and medium-term future are outlined, and a short list of recommended readings is suggested.
Citations
More filters
TL;DR: A conceptual categorisation of beautification is presented, relevant scenarios with respect to face recognition are discussed, and related publications are revisited, and technical considerations and trade-offs of the surveyed methods are summarized.
Abstract: Facial beautification induced by plastic surgery, cosmetics or retouching has the ability to substantially alter the appearance of face images. Such types of beautification can negatively affect the accuracy of face recognition systems. In this work, a conceptual categorisation of beautification is presented, relevant scenarios with respect to face recognition are discussed, and related publications are revisited. Additionally, technical considerations and trade-offs of the surveyed methods are summarized along with open issues and challenges in the field. This survey is targeted to provide a comprehensive point of reference for biometric researchers and practitioners working in the field of face recognition, who aim at tackling challenges caused by facial beautification.
55 citations
TL;DR: This paper presents a new approach in iris presentation attack detection (PAD) by exploring combinations of convolutional neural networks (CNNs) and transformed input spaces through binarized statistical image features (BSIFs).
Abstract: The adoption of large-scale iris recognition systems around the world has brought to light the importance of detecting presentation attack images (textured contact lenses and printouts). This paper presents a new approach in iris presentation attack detection (PAD) by exploring combinations of convolutional neural networks (CNNs) and transformed input spaces through binarized statistical image features (BSIFs). Our method combines lightweight CNNs to classify multiple BSIF views of the input image. Following explorations on complementary input spaces leading to more discriminative features to detect presentation attacks, we also propose an algorithm to select the best (and most discriminative) predictors for the task at hand. An ensemble of predictors makes use of their expected individual performances to aggregate their results into a final prediction. Results show that this technique improves on the current state of the art in iris PAD, outperforming the winner of LivDet-Iris 2017 competition both for intra- and cross-dataset scenarios, and illustrating the very difficult nature of the cross-dataset scenario.
50 citations
16 Jun 2019
TL;DR: A new technique for generating synthetic iris images is designed and its potential for presentation attack detection (PAD) is demonstrated and the viability of using these synthetic images to train a PAD system that can generalize well to "unseen" attacks is demonstrated.
Abstract: In this work we design a new technique for generating synthetic iris images and demonstrate its potential for presentation attack detection (PAD). The proposed technique utilizes the generative capability of a Relativistic Average Standard Generative Adversarial Network (RaSGAN) to synthesize high quality images of the iris. Unlike traditional GANs, RaSGAN enhances the generative power of the network by introducing a "relativistic" discriminator (and generator), which aims to maximize the probability that the real input data is more realistic than the synthetic data (and vice-versa, respectively). The resultant generated images are observed to be very similar to real iris images. Furthermore, we demonstrate the viability of using these synthetic images to train a PAD system that can generalize well to "unseen" attacks, i.e., the PAD system is able to detect attacks that were not used during the training phase.
39 citations
Posted Content•
TL;DR: A new PAD technique based on three image representation approaches combining local and global information of the fingerprint is proposed, which can correctly discriminate bona fide from attack presentations in the aforementioned scenarios.
Abstract: Fingerprint-based biometric systems have experienced a large development in the last years. Despite their many advantages, they are still vulnerable to presentation attacks (PAs). Therefore, the task of determining whether a sample stems from a live subject (i.e., bona fide) or from an artificial replica is a mandatory issue which has received a lot of attention recently. Nowadays, when the materials for the fabrication of the Presentation Attack Instruments (PAIs) have been used to train the PA Detection (PAD) methods, the PAIs can be successfully identified. However, current PAD methods still face difficulties detecting PAIs built from unknown materials or captured using other sensors. Based on that fact, we propose a new PAD technique based on three image representation approaches combining local and global information of the fingerprint. By transforming these representations into a common feature space, we can correctly discriminate bona fide from attack presentations in the aforementioned scenarios. The experimental evaluation of our proposal over the LivDet 2011 to 2015 databases, yielded error rates outperforming the top state-of-the-art results by up to 50\% in the most challenging scenarios. In addition, the best configuration achieved the best results in the LivDet 2019 competition (overall accuracy of 96.17\%).
31 citations
01 Sep 2018
TL;DR: A fingerprint PAD method based on textural information extracted from pre-processed LSCI images, which shows that the proposed approach classifies correctly all bona fides, however, the LSCi technology experiences difficulties with thin and transparent overlay attacks.
Abstract: With the increased deployment of biometric authentication systems, some security concerns have also arisen. In particular, presentation attacks directed to the capture device pose a severe threat. In order to prevent them, liveness features such as the blood flow can be utilised to develop presentation attack detection (PAD) mechanisms. In this context, laser speckle contrast imaging (LSCI) is a technology widely used in biomedical applications in order to visualise blood flow. We therefore propose a fingerprint PAD method based on textural information extracted from pre-processed LSCI images. Subsequently, a support vector machine is used for classification. In the experiments conducted on a database comprising 32 different artefacts, the results show that the proposed approach classifies correctly all bona fides. However, the LSCI technology experiences difficulties with thin and transparent overlay attacks.
31 citations
References
More filters
01 Jan 1998
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Abstract: Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques. Real-life document recognition systems are composed of multiple modules including field extraction, segmentation recognition, and language modeling. A new learning paradigm, called graph transformer networks (GTN), allows such multimodule systems to be trained globally using gradient-based methods so as to minimize an overall performance measure. Two systems for online handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of graph transformer networks. A graph transformer network for reading a bank cheque is also described. It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal cheques. It is deployed commercially and reads several million cheques per day.
42,067 citations
01 Jul 1992
TL;DR: A training algorithm that maximizes the margin between the training patterns and the decision boundary is presented, applicable to a wide variety of the classification functions, including Perceptrons, polynomials, and Radial Basis Functions.
Abstract: A training algorithm that maximizes the margin between the training patterns and the decision boundary is presented. The technique is applicable to a wide variety of the classification functions, including Perceptrons, polynomials, and Radial Basis Functions. The effective number of parameters is adjusted automatically to match the complexity of the problem. The solution is expressed as a linear combination of supporting patterns. These are the subset of training patterns that are closest to the decision boundary. Bounds on the generalization performance based on the leave-one-out method and the VC-dimension are given. Experimental results on optical character recognition problems demonstrate the good generalization obtained when compared with other learning algorithms.
11,211 citations
09 Oct 1994
TL;DR: This paper evaluates the performance both of some texture measures which have been successfully used in various applications and of some new promising approaches to classification based on Kullback discrimination of sample and prototype distributions.
Abstract: This paper evaluates the performance both of some texture measures which have been successfully used in various applications and of some new promising approaches. For classification a method based on Kullback discrimination of sample and prototype distributions is used. The classification results for single features with one-dimensional feature value distributions and for pairs of complementary features with two-dimensional distributions are presented.
1,240 citations
TL;DR: This work presents a high-level categorization of the various vulnerabilities of a biometric system and discusses countermeasures that have been proposed to address these vulnerabilities.
Abstract: Biometric recognition offers a reliable solution to the problem of user authentication in identity management systems. With the widespread deployment of biometric systems in various applications, there are increasing concerns about the security and privacy of biometric technology. Public acceptance of biometrics technology will depend on the ability of system designers to demonstrate that these systems are robust, have low error rates, and are tamper proof. We present a high-level categorization of the various vulnerabilities of a biometric system and discuss countermeasures that have been proposed to address these vulnerabilities. In particular, we focus on biometric template security which is an important issue because, unlike passwords and tokens, compromised biometric templates cannot be revoked and reissued. Protecting the template is a challenging task due to intrauser variability in the acquired biometric traits. We present an overview of various biometric template protection schemes and discuss their advantages and limitations in terms of security, revocability, and impact on matching accuracy. A template protection scheme with provable security and acceptable recognition performance has thus far remained elusive. Development of such a scheme is crucial as biometric systems are beginning to proliferate into the core physical and information infrastructure of our society.
1,119 citations
Patent•
10 Oct 1992
TL;DR: In this article, the sign of the projection of many different parts of the iris onto these filters determines each bit in an iris code, and the similarity metric (Hamming distance) is computed from the XOR of any two iris codes.
Abstract: Image analysis algorithms find the iris in a live video image (10) of a person's face, and encode its texture into an 'iris code' (24). Iris texture is extracted from the image at multiple scales of analysis by a self-similar set of quadrature bandpass filters defined in a dimensionless polar coordinate system. The sign of the projection of many different parts of the iris onto these filters determines each bit in an iris code. Comparisons between codes are readily implemented by the Exclusive-OR (XOR) logical operation. Pattern recognition is achieved by combining signal processing methods with statistical decision theory, leading to a statistical test of independence based on a similarity metric (Hamming distance) (26) that is computed from the XOR of any two iris codes. This measure positively establishes, confirms, or disconfirms, the identity of any individual (28). It also generates an objective confidence level (30) associated with the identification decision.
988 citations