首页 | 官方网站   微博 | 高级检索  
     

基于Harris角点能量的指纹图像分割算法
引用本文:刘花香,王玲.基于Harris角点能量的指纹图像分割算法[J].计算机工程与应用,2011,47(15):206-208.
作者姓名:刘花香  王玲
作者单位:1. 湖南师范大学,物理与信息科学学院,长沙,410081
2. 湖南大学,电气与信息工程学院,长沙,410082
基金项目:湖南省教育厅资助科研项目
摘    要:指纹图像分割是自动指纹识别系统预处理过程中的一个重要环节。提出了一种基于Harris角点检测器的指纹图像自适应分割算法。首先利用Harris算子计算待分割图像的角点能量,然后使用一种自适应的方法设定阈值完成初分割;采用形态学方法进行后处理以减少分割错误,最后通过面积参数去除分离的残留噪声区域。在FVC2004数据库上的实验结果表明,该分割算法能够准确提取指纹有效区域,并且对低质量指纹图像具有很好的鲁棒性。

关 键 词:Harris角点检测器  指纹图像分割  形态学
修稿时间: 

Fingerprint segmentation based on Harris corner strength
LIU Huaxiang,WANG Ling.Fingerprint segmentation based on Harris corner strength[J].Computer Engineering and Applications,2011,47(15):206-208.
Authors:LIU Huaxiang  WANG Ling
Affiliation:1.College of Physics and Information,Hunan Normal University,Changsha 410081,China 2.College of Electric and Information Engineering,Hunan University,Changsha 410082,China
Abstract:Fingerprint segmentation is one of critical pre-processing steps in automatic fingerprint identification system.This paper proposes an adaptive fingerprint segmentation based on Harris corner detector.At first, Harris operator is used to compute the strength of Harris corners in the fingerprint image, and then a threshold-setting method is adopted to compute adap- tively the threshold for the early segmentation.Morphology is applied as post-processing to reduce the number of classification errors,the area parameter is used to remove remaining noised region to get the final segmented image.The experimental results on databases of FVC2004 prove that the proposed algorithm provides very accurate segmentation of valid ridge region.Moreover,this classification method also has a great robustness to those fingerprint images with low quality.
Keywords:Harris corner detector  fingerprint segmentation  morphology
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《计算机工程与应用》浏览原始摘要信息
点击此处可从《计算机工程与应用》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号