Incorporating Cohort Information for Reliable Palmprint Authentication

This paper presents a new approach to achieve the performance improvement for the traditional palmprint authentication approaches. The cohort information is used in the matching stage but only when the matching scores are inadequate to generate reliable decisions. The cohort information can also be utilized to achieve the significant performance improvement for the combination of modalities and this is demonstrated from the experimental results in this paper. The rigorous palmprint authentication results presented in this paper are the best in the literature and confirm the utility of significant information that can be extracted from the imposter scores. The statistical estimation of confidence level for the palmprint matching requires an excellent match between the theoretical distribution and the real score distribution. The performance analysis presented in this paper, from over 29.96 million imposter matching scores, suggests that Beta-Binomial function can more accurately model the distribution of real palmprint matching scores.