Asker M. Bazen

Practical biometric authentication with template protection

In this paper we show the feasibility of template protecting biometric authentication systems. In particular, we apply template protection schemes to fingerprint data. Therefore we first make a fixed length representation of the fingerprint data by applying Gabor filtering. Next we introduce the reliable components scheme. In order to make a binary representation of the fingerprint images we extract and then quantize during the enrollment phase the reliable components with the highest signal to noise ratio. Finally, error correction coding is applied to the binary representation. It is shown that the scheme achieves an EER of approximately 4.2% with secret length of 40 bits in experiments.

Fingerprint Matching by Thin-plate Spline Modelling of Elastic Deformations

This paper presents a novel minutiae matching method that describes elastic distortions in fingerprints by means of a thin-plate spline model, which is estimated using a local and a global matching stage. After registration of the fingerprints according to the estimated model, the number of matching minutiae can be counted using very tight matching thresholds. For deformed fingerprints, the algorithm gives considerably higher matching scores compared to rigid matching algorithms, while only taking 100 ms on a 1 GHz P-III machine. Furthermore, it is shown that the observed deformations are different from those described by theoretical models proposed in the literature.

Likelihood-ratio-based biometric verification

The paper presents results on optimal similarity measures for biometric verification based on fixed-length feature vectors. First, we show that the verification of a single user is equivalent to the detection problem, which implies that, for single-user verification, the likelihood ratio is optimal. Second, we show that, under some general conditions, decisions based on posterior probabilities and likelihood ratios are equivalent and result in the same receiver operating curve. However, in a multi-user situation, these two methods lead to different average error rates. As a third result, we prove theoretically that, for multi-user verification, the use of the likelihood ratio is optimal in terms of average error rates. The superiority of this method is illustrated by experiments in fingerprint verification. It is shown that error rates below 10/sup -3/ can be achieved when using multiple fingerprints for template construction.

Fingerprint Verification Using Spectral Minutiae Representations

Most fingerprint recognition systems are based on the use of a minutiae set, which is an unordered collection of minutiae locations and orientations suffering from various deformations such as translation, rotation, and scaling. The spectral minutiae representation introduced in this paper is a novel method to represent a minutiae set as a fixed-length feature vector, which is invariant to translation, and in which rotation and scaling become translations, so that they can be easily compensated for. These characteristics enable the combination of fingerprint recognition systems with template protection schemes that require a fixed-length feature vector. This paper introduces the concept of algorithms for two representation methods: the location-based spectral minutiae representation and the orientation-based spectral minutiae representation. Both algorithms are evaluated using two correlation-based spectral minutiae matching algorithms. We present the performance of our algorithms on three fingerprint databases. We also show how the performance can be improved by using a fusion scheme and singular points.

A landmark paper in face recognition

Good registration (alignment to a reference) is essential for accurate face recognition. The effects of the number of landmarks on the mean localization error and the recognition performance are studied. Two landmarking methods are explored and compared for that purpose: (1) the most likely-landmark locator (MLLL), based on maximizing the likelihood ratio, and (2) Viola-Jones detection. Both use the locations of facial features (eyes, nose, mouth, etc) as landmarks. Further, a landmark-correction method (BILBO) based on projection into a subspace is introduced. The MLLL has been trained for locating 17 landmarks and the Viola-Jones method for 5. The mean localization errors and effects on the verification performance have been measured. It was found that on the eyes, the Viola-Jones detector is about 1% of the interocular distance more accurate than the MLLL-BILBO combination. On the nose and mouth, the MLLL-BILBO combination is about 0.5% of the inter-ocular distance more accurate than the Viola-Jones detector. Using more landmarks will result in lower equal-error rates, even when the landmarking is not so accurate. If the same landmarks are used, the most accurate landmarking method gives the best verification performance

Spectral minutiae: A fixed-length representation of a minutiae set

Minutiae, which are the endpoints and bifurcations of fingerprint ridges, allow a very discriminative classification of fingerprints. However, a minutiae set is an unordered set and the minutiae locations suffer from various deformations such as translation, rotation and scaling. In this paper, we introduce a novel method to represent a minutiae set as a fixed-length feature vector, which is invariant to translation, and in which rotation and scaling become translations, so that they can be easily compensated for. By applying the spectral minutiae representation, we can combine the fingerprint recognition system with a template protection scheme, which requires a fixed-length feature vector. This paper also presents two spectral minutiae matching algorithms and shows experimental results.

Hand-Geometry Recognition Based on Contour Parameters

This paper demonstrates the feasibility of a new method of hand-geometry recognition based on parameters derived from the contour of the hand. The contour is completely determined by the black-and-white image of the hand and can be derived from it by means of simple image-processing techniques. It can be modelled by parameters, or features, that can capture more details of the shape of the hand than what is possible with the standard geometrical features used in hand-geometry recognition. The set of features considered in this paper consists of the spatial coordinates of certain landmarks on the contour. The feature set and the recognition method used are discussed in detail. The usefulness of the proposed feature set is evaluated experimentally in a verification context. The verification performance obtained with contour-based features is compared with the verification performance of other methods described in the literature.

An Intrinsic Coordinate System for Fingerprint Matching

In this paper, an intrinsic coordinate system is proposed for fingerprints. First the fingerprint is partitioned in regular regions, which are regions that contain no singular points. In each regular region, the intrinsic coordinate system is defined by the directional field. When using the intrinsic coordinates instead of pixel coordinates, minutiae are defined with respect to their position in the directional field. The resulting intrinsic minutiae coordinates can be used in a plastic distortion-invariant fingerprint matching algorithm. Plastic distortions, caused by pressing the 3-dimensional elastic fingerprint surface on a flat sensor, now deform the entire coordinate system, leaving the intrinsic minutiae coordinates unchanged. Therefore, matching algorithms with tighter tolerance margins can be applied to obtain better performance.

Elastic minutiae matching by means of thin-plate spline models

This paper presents a novel minutiae matching method that deals with elastic distortions by normalizing the shape of the test fingerprint with respect to the template. The method first determines possible matching minutiae pairs by means of comparing local neighborhoods of the minutiae. Next a thin-plate spline model is used to describe the non-linear distortions between the two sets of possible pairs. One of the fingerprints is deformed and registered according to the estimated model, and then the number of matching minutiae is counted. This method is able to deal with all possible non-linear distortions while using very tight bounding boxes. For deformed fingerprints, the algorithm gives considerably higher matching scores compared to rigid matching algorithms, while only taking 100 ms on a 1 GHz P-III machine.

Sensor Interoperability and Fusion in Fingerprint Verification: A Case Study using Minutiae-and Ridge-Based Matchers

Information fusion in fingerprint recognition has been studied in several papers. However, only a few papers have been focused on sensor interoperability and sensor fusion. In this paper, these two topics are studied using a multisensor database acquired with three different fingerprint sensors. Authentication experiments using minutiae and ridge-based matchers are reported. Results show that the performance drops dramatically when matching images from different sensors. We have also observed that fusing scores from different sensors results in better performance than fusing different instances from the same sensor