滤除指纹伪特征算法的优化研究  

A Novel Improved Approach to Eliminate the False Minutiae in Fingerprint Images

作　　者：刘灵丽[1] 谢燕江[1] 刘晓玲[1] 

机构地区：[1]湘南学院计算机系,郴州423000

出　　处：《科学技术与工程》2010年第21期5184-5186,5212,共4页Science Technology and Engineering

基　　金：湖南省自然科学基金(07JJ6107);湘南学院2009年院级教改课题青年项目(09Q002)资助

摘　　要：通过分析指纹图像中存在的各类噪声的拓扑结构,并结合细化指纹图像中细节特征点固有的分布规律,提出了一种有效的滤除指纹细节伪特征点的方法。该方法简单、处理速度快,滤除精度基本可以满足应用的需要。In the aspect of feature extraction and post-processing,an effective approach to eliminate false features is presented.The elimination algorithm of false features is based on structural information of all kinds of noises in thinned fingerprint images and the distributing disciplinarian of fingerprint features.It is found that the approach is simple and the speed is high.Moreover,the accuracy of minutiae elimination can fill the demand of application.

关 键 词：指纹图像 细节特征 后处理 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]