摘要
对目前基于Sobel算子的指纹区域的方向估计进行了优化和改进,并提出了一种全新的投票加权的指纹方向校正方法,利用Poincare方法求奇异点时的部分结果校正错误的方向,在提高了算法速度的同时也获得了准确的指纹方向图,指纹图像增强的结果显示了本算法的优越性,具有很强的实用价值.
Optimization and improvements are made on the existing orientation estimation of fingerprint area based on the Sobel operator. A new voting weighted method for the correction of error direction is then put forward. When Poincare is adopted for singular point value, accuracy and speed of the algorithm are acquired at the same time. It is proved through the enhancement of fingerprint images that this algorithm is advantageous with practical value.
出处
《昆明理工大学学报（理工版）》
2005年第4期48-50,54,共4页
Journal of Kunming University of Science and Technology(Natural Science Edition)
基金
重庆市科技攻关重点项目(CSTC.2004AA2001-8277-02).
关键词
指纹图像
方向估计
指纹增强
奇异点
指纹识别系统
fingerprint image
orientation estimation
orientation correction
singular point
fingerprint identification system
