Minutiae Verification in Fingerprint Images Using Steerable Wedge Filters
Sharat Chikkerur, Sharath Pankanti, Nalini Ratha, Ruud Bolle, and Venu Govindaraju
2004 IEEE Workshop on Applications of Computer Vision, WACV-04
(in submission)
A majority of the existing fingerprint recognition systems are based on matching minutia features. Therefore minutiae extraction forms a very critical step and largely determines the overall accuracy of the matching system. Poor ridge structure and processing artifacts result in missing and spurious minutia that can degrade the matching performance. We propose a novel approach based on Steerable wedge filters to eliminate false positives resulting from feature extraction. The proposed feature can also be used as a minutia detector that operates directly on the gray scale images.