Title: Biometric feature extraction with biometric specific shape descriptors

Authors: C. Lakshmi Deepika; A. Kandaswamy; C. Vimal; B. Sathish

Addresses: Department of Biomedical Engineering, PSG College of Technology, Coimbatore 641004, Tamil Nadu, India ' Department of Biomedical Engineering, PSG College of Technology, Coimbatore 641004, Tamil Nadu, India ' Department of Biomedical Engineering, Technical University of Eindhoven, Eindhoven, 5600 MB, The Netherlands ' Department of Biomedical Engineering, PSG College of Technology, Coimbatore 641004, Tamil Nadu, India

Abstract: Orthogonal moments, namely Legendre and pseudo-Zernike moments, are popular region-based shape descriptors which can be used to represent regions with invariant feature vectors. In this paper we propose that the accuracy of biometric verification can be improved by selecting a shape descriptor after exploring its suitability for the given shape or biometric. Fingerprint and palmprint biometrics are used for the experiment. It was observed that the inherent nature of the Legendre moments makes it more suitable for palmprint images and that of the Zernike moments makes it more suitable for the fingerprint images.

Keywords: palmprints; fingerprints; biometrics; ROI extraction; shape descriptors; Legendre moments; Zernike moments; Bayes net classifier; biometric verification; feature extraction.

DOI: 10.1504/IJBM.2012.047643

International Journal of Biometrics, 2012 Vol.4 No.3, pp.246 - 264

Received: 07 May 2011
Accepted: 12 Jul 2011

Published online: 06 Jul 2012 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article