一种新的指纹图像轮廓分割算法  

An novel outline segmentation method for fingerprint images

作　　者：温春友[1] 张学东[1] 

机构地区：[1]鞍山科技大学计算机科学与工程学院,辽宁鞍山114044

出　　处：《鞍山科技大学学报》2004年第5期352-354,共3页Journal of Anshan University of Science and Technology

基　　金：辽宁省自然科学基金资助项目(20022163).

摘　　要：指纹图像分割是指纹图像预处理的一个重要部分,有效的分割既可以减少后续处理的时间,又可以大大增强特征提取的可靠性.本文简单介绍三种指纹分割算法,并提出了一种针对活体指纹采集器所采集的指纹图像的轮廓分割方法,根据手指与传感器中接触区的位置差异,用角部灰度均值作为分割阈值,并用形态学进行的处理.试验结果表明,该方法可以快速高效地对该种指纹图像进行轮廊分割.Segmentation for fingerprint is an important part of fingerprint image preprocessing.Effective segmentation can not only reduce the time of subsequent processing,but also improve the reliability of feature extraction considerably.In this paper,on the basis of discussing some common algorithms for fingeprint segmentation,a speedy and effective approach to fingerprint by live-scan segmentation method is proposed which based on the difference between finger and touch area in sensor selecte the arveragl vale grey in fowr corners as threshold and thit by morphology and proved by experimental results.

关 键 词：指纹图像 轮廓分割 阀值 开运算 闭运算 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]