Ram P. Krish

Mobile signature verification: feature robustness and performance comparison

In this study, the effects of using handheld devices on the performance of automatic signature verification systems are studied. The authors compare the discriminative power of global and local signature features between mobile devices and pen tablets, which are the prevalent acquisition device in the research literature. Individual feature discriminant ratios and feature selection techniques are used for comparison. Experiments are conducted on standard signature benchmark databases (BioSecure database) and a state-of-the-art device (Samsung Galaxy Note). Results show a decrease in the feature discriminative power and a higher verification error rate on handheld devices. It is found that one of the main causes of performance degradation on handheld devices is the absence of pen-up trajectory information (i.e. data acquired when the pen tip is not in contact with the writing surface).

Pre-registration of latent fingerprints based on orientation field

In this study, the authors present a hierarchical algorithm to register a partial fingerprint against a full fingerprint using only the orientation fields. In the first level, they shortlist possible locations for registering the partial fingerprint in the full fingerprint using a normalised correlation measure, taking various rotations into account. As a second level, on those candidate locations, they calculate three other similarity measures. They then perform score fusion for all the estimated similarity scores to locate the final registration. By registering a partial fingerprint against a full fingerprint, they can reduce the search space of the minutiae set in the full fingerprint, thereby improving the result of partial fingerprint identification, particularly for poor quality latent fingerprints. They report the rank identification improvements of two minutiae-based automated fingerprint identification systems on the National Institute of Standards and Technology (NIST)-Special Database 27 database when they use the authors hierarchical registration as a pre-alignment.

Dynamic Signature Verification on Smart Phones

This work is focused on dynamic signature verification for state-of-the-art smart phones, including performance evaluation. The analysis was performed on database consisting of 25 users and 500 signatures in total acquired with Samsung Galaxy Note. The verification algorithm tested combines two approaches: feature based (using Mahalanobis distance) and function based (using DTW), and the results are shown in terms of EER values. A number of experimental findings associated with signature verification in this scenario are obtained, e.g., the dominant challenge associated with the intra-class variability across time. As a result of the algorithm adaptation to the mobile scenario, the use of a state-of-the-art smart phone, and contrarily to what has been evidenced in previous works, we finally demonstrate that signature verification on smart phones can result in a similar verification performance compared to one obtained using more ergonomic stylus-based pen tablets. In particular, the best result achieved is an EER of 0.525%.

Partial fingerprint registration for forensics using minutiae-generated orientation fields

Minutia based matching scheme is the most widely accepted method for both automated as well as manual (forensic) fingerprint matching. The scenario of comparing a partial fingerprint minutia set against a full fingerprint minutia set is a challenging problem. In this work, we propose a method to register the orientation field of the partial fingerprint minutia set to that of the orientation field of full fingerprint minutia set. As a consequence of registering the partial fingerprint orientation field, we obtain extra information that can augment a minutia based matcher by reducing the search space of minutiae in the full fingerprint. We present the accuracy of our registration algorithm on NIST-SD27 database, reporting separately for both subjective and quantitative quality classification of NIST-SD27. The registration performance accuracy is measured in terms of percentage of ground truth minutiae present in the reduced minutiae search space generated by our algorithm.

Evaluation of AFIS-Ranked Latent Fingerprint Matched Templates

The methodology currently practiced in latent print examination (known as ACE-V) yields only a decision as result, namely individualization, exclusion or inconclusive. From such a decision, it is not possible to express the strength of opinion of a forensic examiner quantitatively with a scientific basis to the criminal justice system. In this paper, we propose a framework to generate a score from the matched template generated by the forensic examiner. Such a score can be viewed as a measure of confidence of a forensic examiner quantitatively, which in turn can be used in statistics-based evidence evaluation framework, for e.g, likelihood ratio. Together with the description and evaluation of new realistic forensic case driven score computation, we also exploit the developed experimental framework to understand more about matched templates in forensic fingerprint databases.

Automatic region segmentation for high-resolution palmprint recognition: Towards forensic scenarios

Recently, a novel matching strategy based on regional fusion for high resolution palmprint recognition arises for both forensic and civil applications, under the concept of different regional discriminability of three palm regions, i.e., interdigital, hypothenar and thenar. This matching strategy requires accurate automatic region segmentation techniques since manual region segmentation is time consuming. In this work, we develop automatic region segmentation techniques based on datum point detection for high-resolution palmprint recognition which can be further applied to forensic applications. Firstly, Canny edge detector is applied to a full palmprint to obtain gradient magnitudes and strong edges. Then a first datum point, i.e., the endpoint of heart line, is detected by using convex hull on gradient magnitude image and its left/right differential image and strong edge image. A second datum point, i.e., the endpoint of life line, is estimated based on the position and direction of the first datum point and statistical average distance between the two datum points. Finally, segmented palm regions are generated based on the two datum points and their perpendicular bisector. To evaluate the accuracy of our region segmentation method, we compare the automatic segmentation with manual segmentation performed on a public high resolution palmprint database THUPALMLAB with full palmprint images. The regional error rates of interdigital, thenar and hypothenar regions are 15.72%, 17.05% and 21.38% respectively. And the total error rate is 19.54% relative to full palmprint images.

From Biometric Scores to Forensic Likelihood Ratios

In this chapter, we describe the issue of the interpretation of forensic evidence from scores computed by a biometric system. This is one of the most important topics into the so-called area of forensic biometrics. We will show the importance of the topic, introducing some of the key concepts of forensic science with respect to the interpretation of results prior to their presentation in court, which is increasingly addressed by the computation of likelihood ratios (LR). We will describe the LR methodology, and will illustrate it with an example of the evaluation of fingerprint evidence in forensic conditions, by means of a fingerprint biometric system.

Pre-registration for Improved Latent Fingerprint Identification

Comparing a latent fingerprint minutiae set against a ten print fingerprint minutiae set using an automated fingerprint identification system is a challenging problem. This is mainly because latent fingerprints obtained from crime scenes are mostly partial fingerprints, and most automated systems expect approximately the same number of minutiae between query and the reference fingerprint under comparison for good performance. In this work, we propose a methodology to reduce the minutiae set of ten print with respect to that of query latent minutiae set by registering the orientation field of latent fingerprint with the ten print orientation field. By reducing the search space of minutiae from the ten print, we can improve the performance of automated identification systems for latent fingerprints. We report the performance of our registration algorithm on the NIST-SD27 database as well as the improvement in the Rank Identification accuracy of a standard minutiae-based automated system.

On the importance of rare features in AFIS-ranked latent fingerprint matched templates

In this paper, we introduce an algorithm to generate a score from the matched templates derived by the forensic examiner at the ACE-V stage. Such a score can be viewed quantitatively as a measure of confidence of the forensic examiner for the given latent and impression prints. This quantitative measure can be used in statistics-based evidence evaluation frameworks. Together with the description and evaluation of new realistic forensic casework driven score computation, we also exploit this experimental framework to show the importance of type attributes for minutiae in terms of its discriminating ability in forensic scenarios. We derive the conclusion that together with reliably extracted typical minutiae features, the presence of rare minutiae features helps to improve the measure of confidence of the forensic examiner at the ACE-V stage.

Towards Regional Fusion for High-Resolution Palmprint Recognition

The existing high resolution palm print matching algorithms essentially follow the minutiae-based fingerprint matching strategy and focus on full-to-full/partial-to-full palm print comparison. These algorithms would face problems when they are applied to forensic palm print recognition where latent marks have much smaller area than full palm prints. Therefore, towards forensic scenarios, we propose a novel matching strategy based on regional fusion for high resolution palm print recognition using regions segmented by major creases features. The matching strategy includes two stages: 1) region-to-region palm print comparison, 2) regional fusion at score level. We first studied regional discriminability of a high resolution palm print under the concept of three regions, i.e., interdigital, hypothenar and thenar, which is the most significant difference between palmprits and fingerprints. Then we implemented regional fusion based on logistic regression at score level using region-to-region comparison scores obtained by a commercial SDK, Mega Matcher 4.0. Significant improvement of recognition accuracy is achieved by regional fusion on a public high resolution palm print database THUPALMLAB. The EER of logistic regression based regional fusion is 0.25%, while the EER of full-to-full palm print comparison is 1%.