Abstract
Extracting minutiae from a digital fingerprint is a crucial step in a fingerprint-based recognition systems. This work deals with poor-quality fingerprint images containing broken ridges. The enhancement stage connects broken ridges and is essential for extracting correct minutiae. We use a FFT variant [8] for this stage, but, to truly benefit from FFT in a block, it is essential to determine a suitable block size, depending on ridges orientation field. We propose to use a quadtree to partition the ridges orientation field into homogeneous blocks. A block is homogeneous when at least seventy percent of its ridges orientations are within ten degrees. Another issue addressed in this article is the choice of a suitable neighborhood window size W for computing orientation field image, depending on the fingerprint image quality. The performance improvements of our algorithm are evaluated and compared with standard measures MSE, PSNR and GI, on databases DB1 to DB4 of FVC2004 and NIST special database SD302d.
Highlights
Fingerprints recognition and verification tend to become the most used in biometric systems, and is one of the challenging Pattern Recognition problems
A starting or ending minutiae is a black pixel with crossing number 1, and a bifurcation minutiae a black pixel with crossing number 3
Minutiae features of a fingerprint image are extracted in some seconds
Summary
Fingerprints are unique to each person and each finger has its own unique fingerprint. The ridge frequency of fingerprint images is quickly estimated and used to choose the block size for computing the block orientation field of the current region of the fingerprint. This block size is used as an input parameter for the Gabor filter: the latter inputs a frequency bandwidth and the orientation field. For each block of the region, its (at most nine) adjacent blocks in the region are selected for the stage: the average inter-ridge distance of the image is the main parameter used to determine the block size and the filter mask size, valid for all the image.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have