29 June 2016 Fingerprint liveness detection using multiscale difference co-occurrence matrix
Chengsheng Yuan, Zhihua Xia, Xingming Sun, Decai Sun, Rui Lv
Author Affiliations +
Abstract
Fingerprint identification systems have been widely applied in both civilian and governmental applications due to its satisfying performance. However, the fingerprint identification systems can be easily cheated by the presentation of artificial fingerprints made from common materials. Therefore, it reduces the reliability and misleads the decision of the fingerprint identification systems. In this work, we propose a software-based fingerprint liveness detection method based on multiscale difference co-occurrence matrix (DCM). In doing so, multiscale wavelet transform operation is first conducted on the original image. After the preprocessing of the decomposition of the original image, DCMs are computed by using the Laplacian operator. Horizontal and vertical difference co-occurrence matrices are constructed in our method. In order to reduce the dimensionality of the feature vectors, truncation operation is introduced for DCMs. Then, the elements of processing DCMs are regarded as the texture features of original fingerprint images. Finally, classification accuracy of feature vectors is predicted based on a support vector machine classifier. The experimental results have shown that the performance of our method is very promising and meanwhile achieve better accurate classification compared with the best algorithms of LivDet2013 and LivDet2011, while being able to recognize spoofed fingerprints with better recognition accuracy.
© 2016 Society of Photo-Optical Instrumentation Engineers (SPIE) 0091-3286/2016/$25.00 © 2016 SPIE
Chengsheng Yuan, Zhihua Xia, Xingming Sun, Decai Sun, and Rui Lv "Fingerprint liveness detection using multiscale difference co-occurrence matrix," Optical Engineering 55(6), 063111 (29 June 2016). https://doi.org/10.1117/1.OE.55.6.063111
Published: 29 June 2016
Lens.org Logo
CITATIONS
Cited by 12 scholarly publications.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image processing

Feature extraction

Fingerprint recognition

Quantization

Databases

Image sensors

Optical engineering

RELATED CONTENT

Optimized filterbank fingerprint recognition
Proceedings of SPIE (May 28 2003)

Back to Top