Overlapped Finger Geometry Signal Processing and Finger Shape Comparisons for Person Identification

Article type: Research Article

Authors: Su, Ching-Liang^;

Affiliations: Department of Industrial Engineering and Technology Management, Da Yeh University, 112 Shan-Jeau Road, Da-Tsuen, Chang-Hua, 51505 Taiwan, e-mail: cls2@mail.dyu.edu.tw

Note: [] National Science Council, Taiwan, supported this work under grant NSC 95-2221-E-212-003.

Abstract: This study uses object-extracting technique to extract – thumb, index, middle, ring, and small fingers from hands. The algorithm developed in this study can find precise locations of fingertips and finger-to-finger-valleys. The extracted fingers contain many useful geometry features. One can use these features to conduct the person identification. Geometry descriptor is used to transfer geometry features of fingers to another feature-domain for image-comparison. Image subtraction is used to exam difference of two fingers. This study uses the fingers as features to recognize different persons.

Keywords: finger shape extraction, finger shape identification

Journal: Informatica, vol. 18, no. 3, pp. 447-456, 2007