Title: SINGULAR POINT DETECTION FOR EFFICIENT FINGERPRINT CLASSIFICATION

Issue Number: Vol. 2, No. 1
Year of Publication: Jan - 2012
Page Numbers: 1-7
Authors: Ali Ismail Awad, Kensuke Baba
Journal Name: International Journal of New Computer Architectures and their Applications (IJNCAA)
- Hong Kong

Abstract:


A singular point or singularity on fingerprint is considered as a fingerprint landmark due its scale, shift, and rotation immutability. It is used for both fingerprint classification and alignment in automatic fingerprint identification systems. This paper presents a comparative study between two singular point detection methods available in the literature. The comparative study has been conducted on the Poincaré index and the complex filter methods, and it aims to catch the optimum singular point detection method in terms of the processing time and the detection accuracy. Moreover, discovering the processing time bottlenecks for both methods is an advanced step to improve the their performance. The optimum detection method in both processing time and detection accuracy will be updated to suite our efficient classification method. The conducted experimental evaluation for both methods proved that the maximum accuracy achieved by the complex filter is up to 95% with a considerable processing time and 90% with the Poincaré index method with a higher processing time.