An effective hyperspectral palmprint identification system based on deep learning and band selection approach.

Over the past two decades, there has been an explosion of biometric technologies because anything that characterizes a person provides a source of information. The palmprint modality is a biometric characteristic of great interest to researchers, and its traits can be found in a variety of representations, including grayscale, color, and multi/hyperspectral representations. The most difficult challenge in developing a hyperspectral palmprint-based recognition system is determining how to use all the information available in these spectral bands. In this paper, we propose a hyperspectral palmprint identification system. In the first stage, an Optimal Clustering Framework (OCF) is proposed to extract the most representative bands. Then, in order to determine the best method to describe palmprint features, two types of feature extraction methods (handcrafted and deep learning approaches) were used. After setting the number of selected bands to 4, we performed our set of experiments using the Hong Kong Polytechnic University (Poly U), which consists of 69 spectral bands. The results indicated that the proposed system offers the best performance, which qualifies it to be intended for usage in high-security situations.