结合方差和方向的指纹图像分割算法  

Fingerprint Image Segmentation Algorithm Based on Variance and Orientation

作　　者：蔡秀梅[1] 张永健[2] 梁辉[3] 

机构地区：[1]西安邮电学院自动化学院,陕西西安710121 [2]西安电力电子技术研究所,陕西西安710061 [3]西安卫星测控中心,陕西西安710043

出　　处：《现代电子技术》2011年第12期111-113,共3页Modern Electronics Technique

基　　金：国家自然科学基金资助项目(60572133);陕西省自然科学基金资助项目(2007F18);陕西省教育厅专项科研计划资助项目(09JK721);西安邮电学院中青年科研基金重点项目(ZL2009-2)

摘　　要：指纹图像分割指从图像背景中分离出有用的指纹区域的过程。良好的指纹分割能够有效提高特征提取精度和减少后续处理时间,在指纹图像预处理中具有重要作用。结合指纹图像灰度方差和方向信息,提出一种指纹图像分割算法。将指纹图像分块,计算每块灰度方差和点方向图,根据图像块方差和点方向一致性设定两种分割阈值实现基于方差和方向的指纹图像分割。实验结果表明该算法兼具方差法和方向法的优点,简单快速,是一种有效的指纹图像分割方法。The task of fingerprint segmentation is to isolate the fingerprint area from the image background.The good fingerprint segmentation can not only improve the accuracy of the feature extraction but also reduce the time of subsequent processing effectively.A fingerprint image segmentation algorithm based on variance and orientation is proposed.The fingerprint image is partitioned into several blocks,and then the block variance and its point orientation map are computed.The fingerprint image is segmented with two kinds of threshold of block variance and its consistency of point orientation.The experimental results show that the proposed algorithm has the advantages of the fingerprint segmentation method based on the orientation map and gray variance,it is simple,fast and effective.

关 键 词：指纹图像 指纹分割 方差 方向图 

分 类 号：TN911-34[电子电信—通信与信息系统] TP391.41[电子电信—信息与通信工程]