复杂环境下基于聚类分析的人脸目标识别  

Face Recognition Based on Cluster Analysis in Complex Environment

作　　者：高玉潼 雷为民[1] 原玥 GAO Yu-tong;LEI Wei-min;YUAN Yue(School of Computer Science&Engineering,Northeastern University,Shenyang 110169,China;School of Information Engineering,Shenyang University,Shenyang 110044,China)

机构地区：[1]东北大学计算机科学与工程学院,沈阳110169 [2]沈阳大学信息工程学院,沈阳110044

出　　处：《计算机科学》2020年第7期111-117,共7页Computer Science

基　　金：国家自然科学基金(61401081)。

摘　　要：在现代社会,人脸目标识别技术在各大领域应用得越来越广泛;同时,社会治安环境和国际安全问题也愈发严峻,人脸目标识别面临着越来越严峻的挑战。在复杂环境下,检测目标和背景场景都是复杂且动态变化的,传统的人脸目标识别技术已无法满足日益增长的需求。对此,文中通过聚类分析方法对传统SIFT(Scale Invariant Feature Transform)算法进行优化改进,利用聚类分析的原理将对象特征点进行归类,使得聚类结果更加符合设定阈值,从而提高匹配效率。为了验证优化改进后算法的匹配效果,将改进后的算法和传统SIFT算法进行对比检测分析。结果表明,改进后的SIFT算法能够消除无关书籍的干扰,实现图像匹配点的完整连接。为了验证改进算法的有效性,基于几个常用库将其与常用算法进行对比分析,结果显示聚类SIFT算法在CASPEAL-R1,CFP,Multi-PIE方面都要优于其他算法,具有更好的应用效果和适用性。In modern society,the use of face recognition technology in a variety of fields is increasing.Meanwhile,the problems of social security environment and international security are becoming more serious,thus face recognition is confronted with more severe challenges.Detection target and background are complex and dynamic in a complicated environment,so the traditional face recognition technology can not meet the growing demand.Therefore,in this paper,the traditional SIFT(Scale,Invariant,Feature,Transform)algorithm is optimized by clustering analysis method,and the object features are classified according to the principle of clustering analysis,so as to make the clustering results more in line with the set threshold and improve the matching efficiency.The results show that the improved SIFT algorithm can eliminate the interference of irrelevant books and realize the complete connection of image matching points.In order to verify the effectiveness of the improved SIFT algorithm,it is compared with the common algorithms based on several commonly-used databases,and the results show that the clustering algorithm SIFT is better than other algorithms in CASPEALG R1,CFP,MultiGPIE,and has better application effect and applicability.

关 键 词：聚类分析 SIFT算法 特征匹配 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]