摘要
本文提出了细化图像的纹线跟踪技术及基于其细化指纹伪特征判别方法 ,进而对细化指纹图上存在的噪声 ,例如毛刺、小桥和小孔等进行了滤除处理。结果发现 ,本方法可以快速、准确、彻底地滤除这些噪声 ,而且并不引入新的噪声 。
An approach was proposed in which was proposed pixels on fingerprint ridges can be traced. Based on the proposed approach, an algorithm to remove pseudo-structures from a thinned fingerprint image was developed. The algorithm is carried using a library of thinned fingerprint images with such pseudo-structures as spurs, bridges and holes. It is found that these pseudo-structures can be accurately and totally removed, and on the other hand, the processing speed is higher, if compared with the conventional algorithms.
出处
《光电子.激光》
EI
CAS
CSCD
北大核心
2002年第2期184-187,共4页
Journal of Optoelectronics·Laser
关键词
纹线跟踪
指纹
细化
图像处理
Edge detection
Feature extraction
Image analysis
Pattern matching