Blurred Palmprint Recognition Based on Relative Invariant Structure Feature

Abstract

A blurred palmprint recognition method based on Relative Invariant Structure Feature (RISF) is proposed in this paper to improve the low recognition accuracy of blurred palmprint. Firstly, the OSV decomposition model is used to obtain stable feature from blurred images. Next, a non-overlapping sampling method based on Structure Ratio (SR) for RISF is used to further improve the effectiveness of feature. Finally, Structural Similarity Index Measurement (SSIM) is introduced to measure the similarity of palmprints and judge the palmprint category for classification. Numerical experiments show that the proposed method is effective and better than some other classical algorithms.