煤矿考勤系统中人脸识别算法的研究  

Research of face recognition algorithm of coal mine workers attendance system

作　　者：陈立潮[1] 张秀琴[2] 潘理虎[1,3] 李博[1] 

机构地区：[1]太原科技大学计算机科学与技术学院,山西太原030024 [2]太原科技大学电子信息工程学院,山西太原030024 [3]中国科学院地理科学与资源研究所,北京100101

出　　处：《工矿自动化》2015年第4期69-73,共5页Journal Of Mine Automation

基　　金："十二五"山西省科技重大专项项目(20121101001)

摘　　要：针对传统的人脸识别算法存在识别率低甚至无法识别的缺点,提出了一种基于SURF和双向FLANN的人脸识别算法。该算法首先用SURF算法中的快速Hessian矩阵检测特征点,并生成SURF特征的描述符;然后通过Hessian矩阵迹的正负性和双向FLANN匹配的搜索算法对图像SURF描述符进行匹配,以实现人脸的识别,从而达到考勤的目的。实验结果表明,该算法在剔除匹配识别中误匹配点对的同时提高了SURF算法识别速率与正确率,保证了算法在考勤系统中的实时性。In view of shortcomings of low recognition rate and even unable to identify coal mine personnel existed in traditional face recognition algorithm, the paper proposed a face recognition algorithm based on SURF and FLANN. Firstly, the algorithm uses fast-Hessian detection matrix of SURF algorithm to find features, and generates feature vector of SURF descriptor. Then it adoptes search algorithm of positive and negative characteristics of Hessian detection matrix and bothway FLANN matching algorithm to match SURF descriptor, so as to realize face recognition and check on worker attendance. The experimental result shows that the algorithm can not only exclude mistake matching points, but also improve recognition speed and correct rate of SURF algorithm , and ensure the real-time performance of the algorithm in the attendance system.

关 键 词：煤矿井下 人员考勤 人脸识别 特征描述符 SURF算法 HESSIAN矩阵 FLANN 

分 类 号：TD655[矿业工程—矿山机电]