Search

Current state-of-the-art automatic speaker verification (ASV) systems are prone to spoofing. The security and reliability of ASV systems can be threatened by different types of spoofing attacks using voice conversion, synthetic speech, or recorded passphrase. It is therefore essential to develop countermeasure techniques which can detect such spoofed speech. Inspired by the success of deep learning approaches in various classification tasks, this work presents an in-depth study of convolutional neural networks (CNNs) for spoofing detection in automatic speaker verification (ASV) systems. Specifically, we have compared the use of three different CNNs architectures: AlexNet, CNNs with max-feature-map activation, and an ensemble of standard CNNs for developing spoofing countermeasures, and discussed their potential to avoid overfitting due to small amounts of training data that is usually available in this task. We used popular deep learning toolkits for the system implementation and have released the implementation code of our methods publicly. We have evaluated the proposed countermeasure systems for detecting replay attacks on recently released spoofing corpora ASVspoof 2017, and also provided in-depth visual analyses of CNNs to aid for future research in this area.

Questioned document examination is extensively used by forensic specialists for criminal identification. This paper presents a writer recognition system based on allographic features operating in identification mode (one-to-many). It works at the level of isolated characters, considering that each writer uses a reduced number of shapes for each one. Individual characters of a writer are manually segmented and labeled by an expert as pertaining to one of 62 alphanumeric classes (10 numbers and 52 letters, including lowercase and uppercase letters), being the particular setup used by the forensic laboratory participating in this work. A codebook of shapes is then generated by clustering and the probability distribution function of allograph usage is the discriminative feature used for recognition. Results obtained on a database of 30 writers from real forensic documents show that the character class information given by the manual analysis provides a valuable source of improvement, justifying the proposed approach. We also evaluate the selection of different alphanumeric channels, showing a dependence between the size of the hit list and the number of channels needed for optimal performance. © 2010 IEEE.

The effect of different acquisition distances on the performance of face verification is studied. In particular, we evaluate two standard approaches using popular features (DCT and PCA) and matchers (GMM and SVM) under variation in the acquisition distance, as well as their score-level combination. The DCT-GMM-based system is found to be more robust to acquisition distance degradation than the PCASVM-based system. We exploit this fact by introducing an adaptive score fusion scheme based on a novel automatic scenario estimation which is shown to improve our system in uncontrolled environments. © 2010 IEEE.

In this chapter, we first provide an overview of the existing main approaches, databases, evaluation campaigns and the remaining challenges in online handwritten signature verification. We then propose a new benchmarking framework for online signature verification by introducing the concepts of “Reference Systems”, “Reference Databases” and associated “Reference Protocols.” Finally, we present the results of several approaches within the proposed evaluation framework. Among them are also present the best approaches within the first international Signature Verification Competition held in 2004 (SVC’2004), Dynamic Time Warping and Hidden Markov Models. All these systems are evaluated first within the benchmarking framework and also with other relevant protocols. Experiments are also reported on two different databases (BIOMET and MCYT) showing the impact of time variability for online signature verification. The two reference systems presented in this chapter are also used and evaluated in the BMEC’2007 evaluation campaign, presented in Chap11. ©Springer 2009

This paper evaluates the combination of static image (off-line) and dynamic information (on-line) for signature verification. Two off-line and two on-line recognition approaches exploiting information at the global and local levels are used. Experimental results are given using the BiosecurID database (130 signers, 3,640 signatures). Fusion experiments are done using a trained fusion approach based on linear logistic regression. It is shown experimentally that the local systems outperform the global ones, both in the on-line and in the off-line case. We also observe a considerable improvement when combining the two on-line systems, which is not the case with the off-line systems. The best performance is obtained when fusing all the systems together, which is specially evident for skilled forgeries when enough training data is available. ©2009 IEEE.

One of the biggest challenges in person recognition using biometric systems is the variability in the acquired data. In this paper, we evaluate the effects of an increasing time lapse between reference and test biometric data consisting of static images of handwritten signatures and texts. We use for our experiments two recognition approaches exploiting information at the global and local levels, and the BiosecurlD database, containing 3,724 signature images and 532 texts of 133 individuals acquired in four acquisition sessions distributed along a 4 months time span. We report results of the recognition systems working both in verification (one-to-one) and identification (one-to-many) mode. The results show the extent of the impact that the time separation between samples under comparison has on the recognition rates, being the local approach more robust to the time lapse than the global one. We also observe in our experiments that recognition based on handwritten texts provides higher accuracy than recognition based on signatures.

Automatically verifying the identity of a person by means of biometrics (e.g. face and fingerprint) is an important application in our to-day activities such as accessing banking services and security control in airports. To increase the system reliability, several biometric devices are often used. Such a combined system is known as a multimodal biometric system. This paper reports a benchmarking study carried out within the framework of the BioSecure DS2 (Access Control) evaluation campaign organized by the University of Surrey, involving face, fingerprint, and iris biometrics for person authentication, targeting the application of physical access control in a medium-size establishment with some 500 persons.

In this contribution, the vulnerabilities of iris-based recognition systems to direct attacks are studied. A database of fake iris images has been created from real iris of the BioSec baseline database. Iris images are printed using a commercial printer and then, presented at the iris sensor. We use for our experiments a publicly available iris recognition system, which some modifications to improve the iris segmentation step. Based on results achieved on different operational scenarios, we show that the system is vulnerable to direct attacks, pointing out the importance of having countermeasures against this type of fraudulent actions. © 2008 Springer Berlin Heidelberg.

An off-line signature verification system based on contour features is presented. It works at the local image level, and encodes directional properties of signature contours and the length of regions enclosed inside letters. Results obtained on a sub-corpus of the MCYT signature database shows that directional-based features work much better than length-based features. Results are comparable to existing approaches based on different features. It is also observed that combination of the proposed features does not provide improvements in performance, maybe to some existing correlation among them.

Multimodal biometric systems allow to overcome some of the problems presented in unimodal systems, such as non-universality, lack of distinctiveness of the unimodal trait, noise in the acquired data, etc. Integration at the matching score level is the most common approach used due to the ease in combining the scores generated by different unimodal systems. Unfortunately, scores usually lie in application-dependent domains. In this work, we use linear logistic regression fusion, in which fused scores tend to be calibrated log-likelihood-ratios and thus, independent of the application. We use for our experiments the development set of scores of the DS2 Evaluation (Access Control Scenario) of the BioSecure Multimodal Evaluation Campaign, whose objective is to compare the performance of fusion algorithms when query biometric signals are originated from heterogeneous biometric devices. We compare a fusion scheme that uses linear logistic regression with a set of simple fusion rules. It is observed that the proposed fusion scheme outperforms all the simple fusion rules, with the additional advantage of the application-independent nature of the resulting fused scores.

One of the open issues in fingerprint verification is the lack of robustness against image-quality degradation. Poor-quality images result in spurious and missing features, thus degrading the performance of the overall system. Therefore, it is important for a fingerprint recognition system to estimate the quality and validity of the captured fingerprint images. In this work, we review existing approaches for fingerprint image-quality estimation, including the rationale behind the published measures and visual examples showing their behavior under different quality conditions. We have also tested a selection of fingerprint image-quality estimation algorithms. For the experiments, we employ the BioSec multimodal baseline corpus, which includes 19 200 fingerprint images from 200 individuals acquired in two sessions with three different sensors. The behavior of the selected quality measures is compared, showing high correlation between them in most cases. The effect of low-quality samples in the verification performance is also studied for a widely available minutiae-based fingerprint matching system., ©2007 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

The performance of two popular approaches for off-line signature nature verification in terms of signature legibility and signature type is studied. We investigate experimentally if the knowledge of letters, syllables or name instances can help in the process of imitating a signature. Experimental results are given on a sub-corpus of the MCYT signature database for random and skilled forgeries. We use for our experiments two machine experts, one based on global image analysis and statistical distance measures, and the second based on local image analysis and Hidden Markov Models. Verification results are reported in terms of Equal Error Rate (EER), False Acceptance Rate (FAR) and False Rejection Rate (FRR). ©2007 IEEE.

Although several image quality measures have been proposed for fingerprints, no work has taken into account the differences among capture devices, and how these differences impact on the image quality. In this paper, several representative measures for assessing the quality fingerprint images are compared using an optical and a capacitive sensor. The capability to discriminate between images of different quality and its relationship with the verification performance is studied. We report differences depending on the sensor, and interesting relationships between sensor technology and features used for quality assessment are also pointed out. ©2007 IEEE.

Performance in terms of accuracy is one of the most important goal of a biometric system. Hence, having a measure which is able to predict the performance with respect to a particular sample of interest is specially useful, and can be exploited in a number of ways. In this paper, we present two automatic measures for predicting the performance in off-line signature verification. Results obtained on a sub-corpus of the MCYT signature database confirms a relationship between the proposed measures and system error rates measured in terms of Equal Error Rate (EER), False Acceptance Rate (FAR) and False Rejection Rate (FRR). © 2007 IEEE.

An imponant step in fingerprint recognition is the segmentation of the region of interest. In this paper, we present an enhanced approach for fingerprint segmentation based on the response of eight oriented Gabor filters. The performance of the algorithm has been evaluated in terms of decision error trade-off curves of an overall verification system. Experimental results demonstrate the robustness of the proposed method.