Quality Induced Multiclassifier Fingerprint Verification Using Extended Feature Set

Abstract

Automatic fingerprint verification systems use ridge flow patterns and general morphological information for broad classification and minutia features for verification. With the availability of high resolution fingerprint sensors, it is now feasible to capture more intricate features such as ridges, pores, permanent scars, and incipient ridges. These fine details are characterized as level-3 or extended features and play an important role in matching and improving the verification accuracy. The main objective of this research is to develop a quality induced multi-classifier fingerprint verification algorithm that incorporates both level-2 and level-3 features. A quality assessment algorithm is developed that uses Redundant Discrete Wavelet Transform to extract edge, noise and smoothness information in local regions and encodes into a quality vector. The feature extraction algorithm first registers the gallery and probe fingerprint images using a two-stage registration process. Then, a fast Mumford-Shah curve evolution algorithm is used to extract four level-3 features namely, pores, ridge contours, dots, and incipient ridges. Gallery and probe features are matched using Mahalanobis distance measure and quality based likelihood ratio approach. Further, the quality induced sum rule fusion algorithm is used to combine the match scores obtained from level-2 and level-3 features. The experiments performed on 1000 ppi (pixels per inch) fingerprint databases show the effectiveness of the proposed algorithms.KeywordsFingerprint ImageImage Quality ScoreBasic Probability AssignmentFeature Extraction AlgorithmVerification AccuracyThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.