一种非矩形指体区域静脉图像Gabor滤波增强方法  

A Finger Vein Image Enhancement Method in Non-Rectangular ROI Based on Gabor Filter

作　　者：杜瑶 陈刘奎[1] 李作进[1] DU Yao;CHEN Liukui;LI Zuojin(Chongqing University of Science and Technology,Chongqing 401331,China)

机构地区：[1]重庆科技学院,重庆401331

出　　处：《重庆科技学院学报（自然科学版）》2020年第6期57-61,共5页Journal of Chongqing University of Science and Technology：Natural Sciences Edition

基　　金：重庆市教委科学技术研究项目“基于多通道卷积神经网络的手指静脉活体检测研究”(KJQN201901530);重庆市科委基础与前沿计划项目“驾驶人疲劳特征深度学习与疲劳状态鲁棒性辨识方法研究”(CSTC2018JCYJAX0048);重庆科技学院培育基金项目“基于动态视频的近红外手指静脉活体检测研究”(CK2017ZKYB024);重庆科技学院硕士研究生创新计划项目“基于相位欧拉视频放大的手指静脉活体识别”(YKJCX1920808)。

摘　　要：在手指静脉图像Gabor滤波增强过程中,手指轮廓处会有过强响应而抑制静脉纹路的增强。针对此问题,提出一种新的解决方法:将该非矩形指体区域拉伸为矩形,进行Gabor滤波增强,再逆拉伸,使其恢复到原指体形状,保持原有静脉纹路的分布形状,便于后期的特征提取和匹配识别。传统方法是直接截取一块矩形区域进行滤波操作,易造成局部有效静脉信息缺失,而此新方法则保留了指体内的所有静脉纹路信息。实验结果表明,通过拉伸整体指体区域再进行Gabor滤波,最后进行逆拉伸,实现了像素级配准,提升了静脉的视觉效果,保留了完整的纹路信息,突出了Gabor增强效果。When finger vein image is enhanced by Gabor filter,the edge of the finger body will be strongly highlighted,thereby inhibiting the enhancement effect of the vein pattern,which will make the feature extraction very difficult.In order to solve this problem,this paper proposes to stretch the outline of the finger contour to a rectangular area and cut it out to Gabor enhancement,then stretch it to the origin contour shape inversely,which is convenient for feature extraction and matching recognition.The traditional method directly intercepts a rectangular area for filtering operation,which lacks local effective venous information,while the method proposed in this paper retains all the vein lines in the finger.In the experiment,the whole finger region is stretched and Gabor filtering is carried out;and pixel level registration is realized by inverse stretching.This method improves the visual effect of vein,retains the complete texture information,and highlights the Gabor enhancement effect.

关 键 词：静脉增强 非矩形区域 GABOR滤波 区域拉伸 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]