Fingerprint Classification Based on Extraction and Analysis of Singularities and Pseudoridges

Zhang, Q., Huang, K. and Yan, H.

    In this paper, we introduce a new approach to fingerprint classification based on both singularities and traced pseudoridge analysis. Since noise exists in most of the fingerprint images including those in the NIST databases which are used by many researchers, it is difficult to get the correct number and position of the singulairities such as core or delta points which are widely used in current structural classification methods. The problem is we may miss the true singular points and/or get false singular points due to the poor quality of fingerprint images. Classification based on exact pair of singulairities will fail in such conditions. With the help of the pseudoridge tracing and analysis of the traced cvrve, our method does not rely on the extraction of the exact number and positions of the true singular points, thus improving the classification accuracy. This method has been tested on the NIST-4 fingerprint database. For the 4000 images in this database, the classification accuracy is 95.3% with 11.8% reject rate for 4-class problem (combining Arch and Tented Arch as one class).
Cite as: Zhang, Q., Huang, K. and Yan, H. (2002). Fingerprint Classification Based on Extraction and Analysis of Singularities and Pseudoridges. In Proc. Selected papers from 2001 Pan-Sydney Area Workshop on Visual Information Processing (VIP2001), Sydney, Australia. CRPIT, 11. Feng, D. D., Jin, J., Eades, P. and Yan, H., Eds. ACS. 83-87.
pdf (from crpit.com) pdf (local if available) BibTeX EndNote GS