Fingerprint classification based on extraction and analysis of singularities and pseudo ridges

In this paper, we introduce a new approach to fingerprint classification based on extraction and analysis of both singularities and traced pseudo ridges relating to singular points. Because of the image quality, it is difficult to get the correct number and position of the singularities that are widely used in current structural classification methods. With the help of pseudo ridge tracing and analysis of the traced curves, our method does not rely on the extraction of the exact number and positions of the true singular point(s), thus improving the classification accuracy. This method has been tested on the NIST special fingerprint database 4. For the 4000 images in this database, the classification accuracy reaches 92.7% for the 4-class problem. © 2004 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.