基于RANSAC策略优化的稀疏矩阵指纹匹配算法  

Sparse Matrix Fingerprint Matching Algorithm Based on the Strategy Optimization of RANSAC Algorithm

作　　者：曹中琰 施琳琳[1] 卢恩雪 陈思达[1] 李全彬[1] 

机构地区：[1]江苏省先进激光材料与器件重点实验室江苏师范大学物理与电子工程学院,徐州221116

出　　处：《现代计算机（中旬刊）》2015年第8期42-45,共4页Modern Computer

基　　金：江苏高校优势学科建设工程资助项目(No.PAPD);2013年江苏省高等教育教改研究课题(No.2013JSJG155);江苏省现代教育技术研究2013重点课题(No.2013-R-24729)

摘　　要：基于改进点模式指纹匹配算法在匹配速度与匹配准确率上的不足,提出一种新的指纹匹配算法。稀疏矩阵具有计算速度快、储存容量小的优点,本文将稀疏矩阵应用到指纹匹配算法中,通过稀疏矩阵进行指纹图像初匹配,并进一步通过RANSAC算法进行总体二次匹配,在提高算法速度的基础上,维持匹配的准确率。实验证明,该算法匹配速度快、误识率低、准确性高,是一种有效实用的匹配算法。Aiming at the deficiency of the matching speed and accuracy of the fingerprint matching algorithm based on point pattern, proposes a new fingerprint matching algorithm by discussing the existing algorithms. According to the sparse matrix computing speed and storage capacity of small features, the sparse matrix is applied to the fingerprint matching algorithm to handle initial fingerprint image matching in this paper. And through the RANSAC algorithm for the second time overall matching, to maintain a higher algorithm speed, at the same time, to ensure the accuracy of the matching. The experimental results show that the algorithm has good matching speed, low error rate, high accuracy, and has good performance in all aspects, and it is expected to be a practical and effective matching algorithm.

关 键 词：指纹匹配 稀疏矩阵 RANSAC策略 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]