Fingerprint recognition using wavelet features

Author

Tico, Marius ; Immonen, Eero ; Rämö, Pauli ; Kuosmanen, Pauli ; Saarinen, Jukka

Author_Institution

Digital Media Inst., Tampere Univ. of Technol., Finland

Volume

2

fYear

2001

fDate

6-9 May 2001

Firstpage

21

Abstract

A new method of fingerprint recognition based on features extracted from the wavelet transform of the discrete image is introduced. The wavelet features are extracted directly from the gray-scale fingerprint image with no pre-processing (i.e. image enhancement, directional filtering, ridge segmentation, ridge thinning and minutiae extraction). The proposed method has been tested on a small fingerprint database using the k-nearest neighbor (k-NN) classifier. The very high recognition rates achieved show that the proposed method may constitutes an efficient solution for a small-scale fingerprint recognition system

Keywords

computational complexity; feature extraction; fingerprint identification; image enhancement; security; wavelet transforms; directional filtering; discrete image; features extract; fingerprint database; fingerprint recognition; gray-scale fingerprint image; high recognition rate; image enhancement; k-nearest neighbor classifier; minutiae extraction; ridge segmentation; ridge thinning; signal preprocessing; wavelet features; Discrete wavelet transforms; Feature extraction; Filtering; Fingerprint recognition; Gray-scale; Image databases; Image enhancement; Image matching; Image segmentation; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 2001. ISCAS 2001. The 2001 IEEE International Symposium on

Conference_Location

Sydney, NSW

Print_ISBN

0-7803-6685-9

Type

conf

DOI

10.1109/ISCAS.2001.920996

Filename

920996