Title :
A two-level classifier for fingerprint recognition
Author :
Luk, Andrew ; Leung, S.H. ; Lee, C.K. ; Lau, W.H.
Author_Institution :
Dept. of Electron. Eng., City Polytech. of Hongkong, Kowloon, Hong Kong
Abstract :
A PC-based two-level classifier for fingerprint recognition is presented. Input fingerprint images are preprocessed via Laplacian edge detector and a skeletonization algorithm. The thinned binary image is then classified into one of the four categories of fingerprint via a curve tracing algorithm and a scoring method. Local density of the designated area is then computed for the second-level classification (i.e. within category classification). The proposed method is found to be reliable for a small set of fingerprints
Keywords :
computerised pattern recognition; microcomputer applications; Laplacian edge detector; PC-based classifier; curve tracing algorithm; fingerprint recognition; scoring method; skeletonization algorithm; thinned binary image; two-level classifier; Data preprocessing; Fingerprint recognition; Fingers; Friction; Image edge detection; Image matching; Image recognition; Laplace equations; Pattern recognition; Thumb;
Conference_Titel :
Circuits and Systems, 1991., IEEE International Sympoisum on
Print_ISBN :
0-7803-0050-5
DOI :
10.1109/ISCAS.1991.176084
