Fingerprint analysis and singular point detection
Document Type
Article
Publication Date
11-1-2007
Abstract
Correctly locating singular points (core and delta points) is crucial for most fingerprint classification and recognition applications. In this paper, we propose an algorithm to compute pixel direction and in return create essential primitive features called fault lines. By analyzing direction sequence of fault lines, we are able to provide a computational definition of singular points and distinguish different types of singular points. We also present a shrinking and expanding algorithm (SEA) based on a scale-pyramid model to extract singular points within an area as small as 2 × 2 pixels from fingerprint images. Our algorithm is rotation insensitive and can be applied to all types of fingerprints. Fingerprint images from the FVC2004 database are used for an experimental test, and the accuracy rate of the algorithm on identifying singular points is 92.2% (97.6% for core and 83% for delta points). © 2007 Elsevier B.V. All rights reserved.
Identifier
34548674934 (Scopus)
Publication Title
Pattern Recognition Letters
External Full Text Location
https://doi.org/10.1016/j.patrec.2007.04.003
ISSN
01678655
First Page
1937
Last Page
1945
Issue
15
Volume
28
Recommended Citation
Huang, Ching Yu; Liu, Li min; and Hung, D. C.Douglas, "Fingerprint analysis and singular point detection" (2007). Faculty Publications. 13261.
https://digitalcommons.njit.edu/fac_pubs/13261
