Fuzzy directional element energy feature (FDEEF) based palmprint identification

Abstract

Palmprint is a novel biometric method to identify a person. Generally, there are two types of features in palmprint: structural features and statistical features. Structural features, such as lines, can characterize a palm exactly, but are difficult to be extracted and represented; while statistical features can be extracted and represented easily, but are unable to reflect the structural information of a palmprint. Since the principal features of both Chinese characters and palmprint are lines we attempt to use methods of Chinese character recognition to identify palmprint. In this paper, we use the idea of an efficient Chinese character recognition method, the directional element feature, to define a novel palmprint feature, named the fuzzy directional element energy feature (FDEEF) which is a statistical feature containing some line structural information about palmprints. It can be extracted and represented easily and, at the same time, has a strong ability to distinguish palms. Two other low-dimensional features: global fuzzy directional element energy feature and block edge energy feature are also derived from FDEEF in this paper. The experimental results demonstrate the effectiveness of this method.