DSW feature based Hidden Marcov Model: An application on object identification

This paper proposes to perform palmprint identification with Hidden Markov Models (HMM). Palmprint identification, as an emerging biometric technology, has been extensively investigated in the last decade. Due to its low-price capture device, fast implementation speed and high accuracy, palmprint identification is very competitive in biometric research area. Currently, the majority of literatures focus on palm line extraction algorithms and coding schemes, with little attention on classifier design. In this paper, Down-sliding Window (DSW) technique is employed to create a highcorrelated feature sequence while palmprint is featured by simple down-sampled images. One-to-50 experiment demonstrates that HMM with single component and six states give the best overall performance 99.80%, which indicates the feasibility of HMMs for tasks in palmprint identification.