复杂环境下基于聚类分析的人脸目标识别

doi:10.11896/jsjkx.190500004

计算机科学 ›› 2020, Vol. 47 ›› Issue (7): 111-117.doi: 10.11896/jsjkx.190500004

• 计算机图形学&多媒体 • 上一篇下一篇

复杂环境下基于聚类分析的人脸目标识别

高玉潼^1,2, 雷为民¹, 原玥²

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

收稿日期:2019-05-05 出版日期:2020-07-15 发布日期:2020-07-16
通讯作者: 高玉潼(sydxgyt@126.com)
基金资助:
国家自然科学基金(61401081)

Face Recognition Based on Cluster Analysis in Complex Environment

GAO Yu-tong^1,2, LEI Wei-min¹, YUAN Yue²

1 School of Computer Science & Engineering,Northeastern University,Shenyang 110169,China
2 School of Information Engineering,Shenyang University,Shenyang 110044,China

Received:2019-05-05 Online:2020-07-15 Published:2020-07-16
About author:GAO Yu-tong, born in 1982,Ph.D candidate.Her research interests include image processing and multimedia communication.
Supported by:
This work was supported by the National Natural Science Foundation of China (61401081)

摘要/Abstract

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。

关键词: SIFT算法, 聚类分析, 特征匹配

Abstract: 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.

Key words: Cluster analysis, Feature matching, SIFT algorithm

中图分类号:

TP391

高玉潼, 雷为民, 原玥. 复杂环境下基于聚类分析的人脸目标识别[J]. 计算机科学, 2020, 47(7): 111-117. https://doi.org/10.11896/jsjkx.190500004

GAO Yu-tong, LEI Wei-min, YUAN Yue. Face Recognition Based on Cluster Analysis in Complex Environment[J]. Computer Science, 2020, 47(7): 111-117. https://doi.org/10.11896/jsjkx.190500004

参考文献

[1]SHARMA S,KUMAR V.Performance evaluation of 2D face recognition techniques under image processing attacks[J].Mo-dern Physics Letters B,2018,32(19):1850212.
[2]YAN H,WANG P,YANG X L,et al.One Type of New AdaBoost Human Telling Method[J].Journal of Chongqing University of Technology(Natural Science),2019,33(2):106-110,161.
[3]SUN J G,LIU J,ZHAO L Y.Clustering algorithms research[J].Journal of Software,2008,19(1):48-61.
[4]ROSSION B.Humans are visual experts at unfamiliar face reco-gnition[J].Trends in Cognitive Sciences,2018,22(6):471-472.
[5]WANG F F,ZHANG B H,CHAI S C,et al.Community detection in complex networks using proximate support vector clustering[J].Modern Physics Letters B,2018,32(7):1850101.
[6]BAY H,TUYTELAARS T,GOOL L.SURF:speeded up robust features[M]//Computer Vision - ECCV 2006.2006.
[7]REN Y,GU C C.Hand gesture recognition based on HOG characters and SVM[J].Bulletin of Science and Technology,2011,27(2):211-214.
[8]WU Y Z,SUN H H.SIFT feature matching algorithm based on global information[J].Editorial Office of Optics and Precision,2009,17(2):439-444.
[9]YANG Q J,XIAO X M.Improved SIFT algorithm based on Canny feature points[J].Computer Engineering and Design,2011,32(7):2428-2431,2458.
[10]PAN J J,YANG X,XIE X,et al.SIFT:a method for background subtraction in maximum likelihood fit[J].Physics,2009,20(2/3):121-131.
[11]GAO J,HUANG X H,PENG G,et al.Color-based SIFT feature point detection and matching[J].Computer Engineering and Applications,2007,43(34):10-12,15.
[12]MOKHAYERI F,GRANGER E,BILODEAU G A.Domain-specific face synthesis for video face recognition from a single sample per person[J].IEEE Transactions on Information Forensics and Security,2019,14(3):757-772.
[13]HU M,LIU C P,CUI Z M,et al.Clustering difference image kernel density estimation for foreground object detection[J].Journal of Image and Graphics,2009,14(10):2126-2131.
[14]LIU S,LIN K Z,SUN X D,et al.Scale-invariant feature transform based on clustering in face recognition[J].Journal of Harbin University of Science and Technology,2014,19(1):31-35.
[15]YANG X F,LIU P.Face recognition based on clustering optimization algorithm for active model[J].Computer Simulation,2012,29(1):238-241.
[16]HE G H,PAN Y J,WU F.Colorful human face detection based on skin color features and dynamic clustering[J].Opto-Electro-nic Engineering,2004,31(11):47-50.
[17]MA H J,ZHANG D T,FENG J,et al.Three-dimensional facial feature points matching based on K-means clustering of relative angle context distribution and support vector machine[J].Journal of Image and Graphics,2011,16(5):850-856.
[18]ZHOU T,ZHANG Y N,YUAN H J,et al.Sequence targetsclassification algorithm based on ensemble improvement SVM and clustering analysis[J].Computer Science,2009,36(1):148-152.
[19]HO H T,CHELLAPPA R.Pose-invariant face recognition using Markov random fields[J].IEEE Transactions on Image Proces-sing,2013,22(4):1573-1584.
[20]DING C X,TAO D C.Pose-invariant face recognition with homography-based normalization[J].Pattern Recognition,2017,66:144-152.
[21]SU Y,GAO X B,YIN X C.Fast alignment for sparse representation based face recognition[J].Pattern Recognition,2017,68:211-221.
[22]MA H,SUN W C,SHI J H,et al.A Low-Resolution of Face Recognition Method Based on Curvelet Transform[J].Journal of Chongqing University of Technology(Natural Science),2018,32(11):162-168.

相关文章 15

[1]	胡安祥, 尹小康, 朱肖雅, 刘胜利. 基于数据流特征的比较类函数识别方法 Strcmp-like Function Identification Method Based on Data Flow Feature Matching 计算机科学, 2022, 49(9): 326-332. https://doi.org/10.11896/jsjkx.220200163
[2]	刘帅, 芮挺, 胡育成, 杨成松, 王东. 基于深度学习SuperGlue算法的单目视觉里程计 Monocular Visual Odometer Based on Deep Learning SuperGlue Algorithm 计算机科学, 2021, 48(8): 157-161. https://doi.org/10.11896/jsjkx.200700134
[3]	程松盛, 潘金山. 基于深度学习特征匹配的视频超分辨率方法 Video Super-resolution Method Based on Deep Learning Feature Warping 计算机科学, 2021, 48(7): 184-189. https://doi.org/10.11896/jsjkx.200800224
[4]	肖蕾, 陈荣赏, 缪淮扣, 洪煜. 融合聚类算法和缺陷预测的测试用例优先排序方法 Test Case Prioritization Combining Clustering Approach and Fault Prediction 计算机科学, 2021, 48(5): 99-108. https://doi.org/10.11896/jsjkx.200400100
[5]	曹素娥, 杨泽民. 基于聚类分析算法和优化支持向量机的无线网络流量预测 Prediction of Wireless Network Traffic Based on Clustering Analysis and Optimized Support Vector Machine 计算机科学, 2020, 47(8): 319-322. https://doi.org/10.11896/jsjkx.190800075
[6]	李月峰. 一种基于多特征结合的三维模型检索方法 3D Retrieval Algorithm Based on Multi-feature 计算机科学, 2019, 46(6A): 266-269.
[7]	黄海燕, 刘晓明, 孙华勇, 杨志才. 聚类分析算法在不确定性决策中的应用 Application of Clustering Analysis Algorithm in Uncertainty Decision Making 计算机科学, 2019, 46(6A): 593-597.
[8]	邵进达, 杨帅, 程琳. 改进SIFT算法结合两级特征匹配的无人机图像匹配算法 UAV Image Matching Algorithm Based on Improved SIFT Algorithm and Two-stage Feature Matching 计算机科学, 2019, 46(6): 316-321. https://doi.org/10.11896/j.issn.1002-137X.2019.06.048
[9]	霍敏霞,薛博桓. 基于智能算法的破碎文件拼接复原技术的研究 Research on Splicing Recovery of Broken Files Based on Intelligent Algorithms H 计算机科学, 2018, 45(6A): 174-178.
[10]	郝俊生,李冰锋,陈曦,高文娟. 基于Android平台的高校网络订餐系统的设计与实现 Design and Implementation of Network Subscription System Based on Android Platform 计算机科学, 2018, 45(6A): 591-594.
[11]	刘朝霞,邵峰,景雨,祁瑞华. 基于视觉约束能量最小化的特征点匹配算法 Feature Matching Algorithm Based on Visual Feature Constrained Energy Minimization 计算机科学, 2018, 45(5): 228-231. https://doi.org/10.11896/j.issn.1002-137X.2018.05.039
[12]	王振朝,侯欢欢,连蕊. 抑制CMT中乱序程度的路径优化方案 Path Optimization Scheme for Restraining Degree of Disorder in CMT 计算机科学, 2018, 45(4): 122-125. https://doi.org/10.11896/j.issn.1002-137X.2018.04.019
[13]	陈淑鑫,孙伟民,王丽丽. 网格聚类分析天文光谱数据 Analysis of Astronomical Spectral Data Based on Grid Clustering 计算机科学, 2017, 44(Z11): 453-456. https://doi.org/10.11896/j.issn.1002-137X.2017.11A.096
[14]	夏庆亚. 基于密度峰值和网格的自动选定聚类中心算法 Automatically Selecting Clustering Centers Algorithm Based on Density Peak and Grid 计算机科学, 2017, 44(Z11): 403-406. https://doi.org/10.11896/j.issn.1002-137X.2017.11A.085
[15]	唐佳林,郑杰锋,李熙莹,苏秉华. 航拍视频中运动目标检测算法研究 Research on Detecting Algorithm of Moving Target in Aerial Video 计算机科学, 2017, 44(Z11): 175-177. https://doi.org/10.11896/j.issn.1002-137X.2017.11A.036

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

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

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0