Direct gray-scale minutiae extraction in fingerprint identification

Fingerprint verification is one of the most reliable and widely accepted personal identification methods used in the real world. However, the traditional methods are very tedious, time-consuming, and expensive. There are great demands on the Automatic Fingerprint Identification Systems (AFIS). Most of the fingerprint identification methods proposed require preprocessing on the original fingerprint images before the actual minutiae extraction phase, such as segmentation, histogram, binarization, thinning, etc. Although some image processing algorithms do give fairly good results on processing the fingerprint images, certain drawbacks exist for such methods. The most serious one is that during the pre-processing stages, some valuable information is inevitably lost, and is not able to recover. Therefore, direct gray-scale minutia detection that works on the original image itself is preferable. In this paper, a system based on fuzzy-neural network (FNN) to derive fuzzy rules to perform the direct gray-scale minutiae extraction in fingerprint is introduced. Experiments have been conducted to examine the performance of the system, which are also provided in this report.