Use of Histogram Distances in Iris Authentication

Quantitatively establishing the discriminative power of iris biometric data is considered. Multi-level 2D wavelet transform has been widely used for iris verification system. While previous approaches compute only means and variances, we propose using a histogram distance. We also use a methodology to establish a measure of discrimination that is statistically inferable. To establish the inherent distinctness of the classes, i.e., validate individuality, we transform the many class problem into a dichotomy by using a "distance" between two samples of the same person and between those of two different peoples. We demonstrate that using histogram matching results better performances than using only means and variances. Key Words: Iris recognition, Dichotomy model, Histogram, Distance measure, Biometrics

• Type: Conference
• Year: 2004
• Where: ICAI
• Authors: Seung-Seok Choi, Sungsoo Yoon, Sung-Hyuk Cha, Charles C. Tappert
• Keywords: Histogram Distance, ICAI 2004, ICAI 2007, Iris Biometric Data, Iris Verification System