Blurred Palmprint Recognition Based on Stable-FeatureExtraction Using a Vese-Osher Decomposition Model

Abstract As palmprints are captured using non-contact devices, image blur is inevitably generated because of the defocused statusThis dearades the recoanition performance of the svstem, To solve this problem. we propose a stable-feature extractionmethod based on a Vese-0sher (0) decomposition model to recognize blurred palmprints effectively. A Gaussian defocusdegradation model is first established to simulate image blur. With different degrees of bluring, stable features are found toexist in the image which can be investigated by analyzing the blur theoretically. Then, a VO decomposition model is used toobtain structure and texture layers of the blurred palmprint images. The structure layer is stable for different degrees otblurring this is a theoretical conclusion that needs to be further proved via experiment,. Next, an algorithm based onweighted robustness histogram of oriented gradients (WRHOG) is designed to extract the stable features from the structurelayer of the blurred palmprint image. Finally, a normalized correlation coefficient is introduced to measure the similarity inthe palmprint features. We also desicned and pertormed a series of exoerments to show the benefits of the proposecmethod. The experimental results are used to demonstrate the theoretica conclusion that the structure laver is stable foidifferent bluring scales The WRHOG method also proves to be an advanced and robust method of distinauishing blurredpalmprints. The recognition results obtained using the proposed method and data from two palmprint databases (Polyland Blurred-PolyU) are stable and superior in comparison to previous high-performance methods (the equal error rate is only 0.132%). In addition, the authentication time is less than 1.3 s, which is fast enough to meet real-time demands. Therefore, the proposed method is a feasible way of implementing blurred palmprint recognition.