DocumentCode :
2347681
Title :
Fast focal point localization algorithm for fingerprint registration
Author :
Areekul, Vutipong ; Boonchaiseree, Natthawat
Author_Institution :
Dept. of Electr. Eng., Kasetsart Univ., Bangkok
fYear :
2008
fDate :
3-5 June 2008
Firstpage :
2089
Lastpage :
2094
Abstract :
Fingerprint registration is still a challenging problem for large-scale fingerprint identification system. In this paper, a new, fast, and efficient algorithm for the focal point localization is proposed. The focal point is a reliable reference point, which can replace a singular point such as core in fingerprint registration process. The advantages of the focal point over the singular point are its uniqueness and reliability under low quality fingerprint and partial fingerprint conditions. In this paper, the proposed algorithm employed only orientation fields of fingerprint instead of a fully enhanced fingerprint, resulting in reduction of 7 times computational complexity compared to a previous algorithm. Moreover, the new algorithm achieves good localization accuracy and outstanding stability comparing with existing results in literature.
Keywords :
fingerprint identification; image registration; fingerprint registration; focal point localization algorithm; large-scale fingerprint identification system; Algorithm design and analysis; Computational complexity; Filters; Fingerprint recognition; Image processing; Iterative algorithms; Laboratories; Large-scale systems; Mathematical model; Signal processing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Industrial Electronics and Applications, 2008. ICIEA 2008. 3rd IEEE Conference on
Conference_Location :
Singapore
Print_ISBN :
978-1-4244-1717-9
Electronic_ISBN :
978-1-4244-1718-6
Type :
conf
DOI :
10.1109/ICIEA.2008.4582888
Filename :
4582888
Link To Document :
بازگشت