Liaojun Pang

Fingerprint classification by a hierarchical classifier

Fingerprint classification is still a challenging problem due to large intra-class variability, small inter-class variability and the presence of noise. To deal with these difficulties, we propose a regularized orientation diffusion model for fingerprint orientation extraction and a hierarchical classifier for fingerprint classification in this paper. The proposed classification algorithm is composed of five cascading stages. The first stage rapidly distinguishes a majority of Arch by using complex filter responses. The second stage distinguishes a majority of Whorl by using core points and ridge line flow classifier. In the third stage, K-NN classifier finds the top two categories by using orientation field and complex filter responses. In the fourth stage, ridge line flow classifier is used to distinguish Loop from other classes except Whorl. SVM is adopted to make the final classification in the last stage. The regularized orientation diffusion model has been evaluated on a web-based automated evaluation system FVC-onGoing, and a promising result is obtained. The classification method has been evaluated on the NIST SD 4. It achieved a classification accuracy of 95.9% for five-class classification and 97.2% for four-class classification without rejection.

Fingerprint matching by incorporating minutiae discriminability

Traditional minutiae matching algorithms assume that each minutia has the same discriminability. However, this assumption is challenged by at least two facts. One of them is that fingerprint minutiae tend to form clusters, and minutiae points that are spatially close tend to have similar directions with each other. When two different fingerprints have similar clusters, there may be many well matched minutiae. The other one is that false minutiae may be extracted due to low quality fingerprint images, which result in both high false acceptance rate and high false rejection rate. In this paper, we analyze the minutiae discriminability from the viewpoint of global spatial distribution and local quality. Firstly, we propose an effective approach to detect such cluster minutiae which of low discriminability, and reduce corresponding minutiae similarity. Secondly, we use minutiae and their neighbors to estimate minutia quality and incorporate it into minutiae similarity calculation. Experimental results over FVC2004 and FVC-onGoing demonstrate that the proposed approaches are effective to improve matching performance.

Minutiae and modified Biocode fusion for fingerprint-based key generation

Key generation from biometrics has been studied intensively in recent years, linking a key with certain biometric enhances the strength of identity authentication. But the state-of-the-art key generation systems are far away from practicality due to low accuracy. The special manner of biometric matching makes a single feature based key generation system difficult to obtain a high recognition accuracy. Integrating more features into key generation system may be a potential solution to improve the system performance. In this paper, we propose a fingerprint based key generation system under the framework of fuzzy extractor by fusing two kinds of features: minutia-based features and image-based features. Three types of sketch, including minutiae based sketch, modified Biocode based sketch, and combined feature based sketch, are constructed to deal with the feature differences. Our system is tested on FVC2002 DB1 and DB2, and the experimental results show that the fusion scheme effectively improves the system performance compared with the systems based only on minutiae or modified Biocode.

A key binding system based on n-nearest minutiae structure of fingerprint

Biometric cryptosystem has gained increasing attention in recent years. One of the difficulties in this field is how to perform biometric matching under template protection. In this paper, we propose a key binding system based on n-nearest minutiae structures of fingerprint. Unlike the traditional fingerprint recognition method, the matching of nearest structures are totally performed in the encrypted domain, where the template minutiae are protected. Three levels of secure sketch are applied to deal with error correction and key binding: (1) The wrap-around construction is used to tolerate random errors that happens on paired minutiae; (2) the PinSketch construction is used to recover nearest structures which are disturbed by burst errors; and (3) Shamirs secret sharing scheme is used to bind and recover a key based on template minutia structures. The experimental results on FVC2002 DB1 and DB2 and security analysis show that our system is efficient and secure.

Random local region descriptor (RLRD): A new method for fixed-length feature representation of fingerprint image and its application to template protection

Minutia based features are the most widely used features in fingerprint recognition. However, the minutiae based fingerprint matching algorithms have some drawbacks that limit their applications in template protection. Because the minutia sets are unordered, it is difficult to determine the correspondence between two minutia sets and cannot be used in some known template protection schemes directly (e.g., fuzzy commitment, wrap around). In this paper, we propose a new fixed-length feature representation: random local region descriptor (RLRD) feature. The RLRD feature is extracted by randomly and uniformly selecting a set of points, where the order of points is determined by a random seed. For each point, a real fixed-length feature vector is extracted based on Ticos sampling structure. The real RLRD feature vector can be further transformed into a bit vector for secure sketches working in the Hamming space. The experimental results on FVC2002 DB1 and DB2 show the advantages of the RLRD feature over some other fixed-length fingerprint feature vectors in terms of equal error rate (EER), genuine accept rate (GAR) and false accept rate (FAR).

Fingerprint Singular Point Detection Based on Multiple-Scale Orientation Entropy

This letter develops a novel method for fingerprint singular point detection based on a new singularity representation of ridge-valley region called orientation entropy. The candidate singular point is obtained by the multiple-scale analysis of orientation entropy and some post processing steps are proposed to filter the spurious core and delta points. An iteration compensation scheme is proposed to search the precise location for core points against the offset further. Performance of the proposed method has been evaluated on the dataset of FVC2002 DB1. Experimental results show that the multiple-scale orientation entropy is correct and effective for singular detection and the location compensation scheme reduces the distance between the detection result and the truth singular point.

Multi fuzzy vault based on secret sharing for deadlock restoration

A new multi-biometric-based secret sharing algorithm is presented to relieve the message deadlock problem of the single biometric instance-based fuzzy vault method. A multi-vault structure is constructed for all participants to equally share the key. During the enrolment procedure, sub-keys are generated from the key by applying secret sharing scheme and each of them is bound with a minutia set by a modified fuzzy vault method. At the authentication stage, the key can be reconstructed when the necessary minutia sets come together. The experimental results on FVC2002 DB2 show that the proposed scheme decreases the deadlock rate without increasing the false acceptance rate significantly.