Palmprint Classification Algorithm Based on Wavelet Multi-scale Analysis

Palmprint recognition inherently implements many of the same matching characteristics that have allowed fingerprint recognition to be one of the most well-known and best publicized biometrics. Because of palm region has obvious principle line features in outline and texture features in detail, in order to describe different patterns based on palmprint, a new feature extraction and match algorithm is proposed in this paper. The feature extraction algorithm based on wavelet analysis can be used to achieve multi-scale features, and a layered match algorithm for different scale features can be used to calculate similarity score between palms. Simulation results show that the proposed algorithm has high classification correct rate.