Authors: Li Min Liu, Ching Yu Huang, Tian Shyr Dai, George Chang
Addresses: Department of Applied Mathematics, Chung Yuan Christian University, Chung-Li, Taiwan, ROC. ' Center for Pharmacogenomics and Complex Disease Research, New Jersey Dental School, Newark, NJ 07101, USA. ' Department of Information and Financial Management, National Chiao-Tung University, Hsin-Chu, Taiwan, ROC. ' Department of Computer Science, Kean University, Union, NJ 07083, USA
Abstract: This paper proposes the Enhanced Shrinking and Expanding Algorithm (ESEA) with a new categorisation method. The ESEA overcomes anomalies in the original Shrinking and Expanding Algorithm (SEA) which fails to locate Singular Points (SPs) in many cases. Experimental results show that the accuracy rate of the ESEA reaches 94.7%, a 32.5% increase from the SEA. In the proposed fingerprint categorisation method, each fingerprint will be assigned to a specific subclass. The search for a specific fingerprint can therefore be performed only on specific subclasses containing a small portion of a large fingerprint database, which will save enormous computational time.
Keywords: fingerprints; fingerprint classification; singular points; SPs; fault lines; directional images; shrinking and expanding algorithm; SEA; fingerprint analysis; fingerprint identification; biometrics.
International Journal of Computer Applications in Technology, 2007 Vol.30 No.4, pp.295 - 302
Published online: 19 Feb 2008 *Full-text access for editors Access for subscribers Purchase this article Comment on this article