A NON Reference Fingerprint Image Validity via Statistical Weight Calculation

M. S. Al-Tarawneh, L. C. Khor, W. L. Woo, and S. S. Dlay

Abstract

Clarity of fingerprint image structure is crucial for many fingerprint applications, as well as the performance of built systems which relies on the validity and quality of captured images. Validity check will eliminate invalid images before starting the life cycle of fingerprint metadata enrolling for system processing cycle; therefore the overall benchmarking system accuracy will not be affected by rejecting an invalid image before getting in the system cycle. In this paper we propose a validity check algorithm (VCA). The VCA is applied to the base image eiement statistical weight calculation because the image element (pixel) describes an image object with the contrast, brightness, clarity and noising attributes. Our algorithm depends on fingerprint object segmentation, background subtraction, total image thresholding and pixel weight calculation. A VTC200ODB1_B, TIMA databases was used to evaluate the VCA and it has been compared with NIST fingerprint image quality results. Correlation results indicate that the proposed algorithm is feasible in detecting low quality as well as non-fingerprint images.

 Digital Information Management Journal, vol. 5, pp. 220-224, August, 2007.ISBN/ISSN: 0972-7272 http://www.dirf.org/jdim/v5i4.asp