A method of fingerprint identification based on space invariant transforms and support vector machines

Author

He, Yang ; Ou, Zongying ; Guo, Hao

Author_Institution

Sch. of Mech. Eng., Dalian Univ. of Technol., China

Volume

3

fYear

2003

fDate

2-5 Nov. 2003

Firstpage

1322

Abstract

A new method of fingerprint identification based on space invariant transforms and support vector machines is presented. The method uses the rotation, scale and translation invariant properties of the Fourier-Mellin transform to preprocess the fingerprint images. Afterward, with the results as the input properties, the automatically fingerprint identification is performed using support vector machines (SVM). The experimental results show that the method of fingerprint identification is effective and has high accuracy.

Keywords

Fourier transforms; fingerprint identification; image enhancement; support vector machines; Fourier-Mellin transform; fingerprint identification; fingerprint images; scale invariant properties; space invariant transforms; support vector machines; translation invariant properties; Biometrics; Fingerprint recognition; Fourier transforms; Frequency domain analysis; Helium; Image matching; Machine learning; Space technology; Support vector machine classification; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics, 2003 International Conference on

Print_ISBN

0-7803-8131-9

Type

conf

DOI

10.1109/ICMLC.2003.1259696

Filename

1259696