Translator Disclaimer
3 April 2008 Information distance based contrast invariant iris quality measure
Author Affiliations +
Poor quality can affect iris recognition accuracy. Feature information is an objective measure to evaluate the iris image quality. By combining Feature Information Measure (FIM), an occlusion measure and a dilation measure, a quality score is obtained that is well correlated with recognition accuracy. FIM is calculated as the distance between the distribution of iris features and a uniform distribution. Images of low contrast can appear to lack information from manual inspection, but actually perform well in iris recognition due to the presence of feature information. However, the FIM score for a low contrast image could be low. To adjust this affect, this paper developed an information based contrast invariant iris quality measure. For exhaustive comparison, CASIA 1.0, CASIA 2.0, ICE and WVU databases is used. In addition, the proposed method is compared to the convolution matrix, spectrum energy and Mexican hat wavelet approaches which represent a variety of approaches to iris quality measure. The experimental results show that the proposed quality measure is capable of predicting matching performance.
© (2008) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Craig Belcher and Yingzi Du "Information distance based contrast invariant iris quality measure", Proc. SPIE 6982, Mobile Multimedia/Image Processing, Security, and Applications 2008, 69820O (3 April 2008);

Back to Top