基于局部Gabor相位特征的手背静脉识别方法

An Approach to Palm-dorsal Vein Recognition Based on Local Gabor Phase Feature

文章介绍了一种新的手背静脉识别方法,和以往的手背静脉识别方法相比,本文的方法能够通过低质量的手背静脉图片来获得高质量的识别效果。本文提出的方法分文两个部分:一个是手背静脉的预处理和感兴趣区域(ROI)提取;另一个是静脉的特征提取和匹配,该部分利用静脉图像的局部的2DGabor相位编码变化特征来表示其局部特征,并且结合直方图全局特征来表达静脉图像的全局特征,采用卡方距离来实现特征匹配。在自制的手背静脉库的实验结果表明,本文的方法得到了100%的识别率和0%拒识率,这意味着该识别方法可以有效的运用于生物识别。

This paper presents a new approach to palm-dorsal vein recognition. In contrast to the existing methods, our method employs low-resolution palm-dorsal vein images to achieve effective identification. This method consists of two parts: one part is the palm-dorsal image preprocessing and region of interest (ROI) extraction, the other part is vein feature extraction and verification, using local 2D Gabor phase encoding variance feature to represent the texture feature of the vein image and using histogram to represent the global feature. Chi-square distance is used to evaluate the matching degree. On our own palm-dorsal vein image database, experimental results show that this method achieves 100% acceptance rate and 0% false refuse rate, which indicates the vein pattern biometric is potentially a useful biometric.