Title
On-Line Signature Verification Based on Discrete Wavelet Domain Adaptive Signal Processing
Abstract
This paper presents the on-line signature verification method based on the Discrete Wavelet Transform (DWT) and the adaptive signal processing. Time-varying pen-position signals of the on-line signature are decomposed into sub-band signals by using the DWT. Individual features are extracted as high frequency signals in sub-bands. Verification is achieved by utilizing the adaptive algorithm. If the adaptive weight converges on one, the sub-band signal is regarded as of the genuine signature. The total decision for verification is done by averaging verification results and then comparing with a threshold. In this paper, a nonlinear function is introduced to enhance each verification result. Experimental results show that the verification rate is 96%, while that of the time-domain method is 85%.
Year
DOI
Venue
2004
10.1007/978-3-540-25948-0_80
BIOMETRIC AUTHENTICATION, PROCEEDINGS
Keywords
Field
DocType
adaptive signal processing,time domain,high frequency,discrete wavelet transform
Signal processing,Discrete-time signal,Computer science,Image processing,Algorithm,Digital signature,Adaptive filter,Discrete wavelet transform,Adaptive algorithm,Wavelet
Conference
Volume
ISSN
Citations 
3072
0302-9743
6
PageRank 
References 
Authors
0.76
1
4
Name
Order
Citations
PageRank
Isao Nakanishi110428.15
Naoto Nishiguchi2212.73
Yoshio Itoh35918.04
Yutaka Fukui45512.83