计算机科学 ›› 2020, Vol. 47 ›› Issue (11A): 615-619.doi: 10.11896/jsjkx.200400142
林增敏, 洪朝群, 庄蔚蔚
LIN Zeng-min, HONG Chao-qun, ZHUANG Wei-wei
摘要: 人脸图像去重处理对智能监控系统中的人脸识别有着重要意义。针对视频中人脸检测环节会产生大量重复的人脸图像的问题,提出了一种融合人脸跟踪和聚类的人脸图像去重方法。在视频中,利用Multi-task Convolutional Neural Network中的人脸检测算法提取人脸框及其对应的坐标。根据人脸跟踪算法构建人脸轨迹和约束矩阵,同时引入人脸质量评估算法,从人脸轨迹中挑选人脸姿态和图像清晰度较好的人脸图像作为人脸轨迹的代表图片;再由约束矩阵和无监督聚类算法对人脸代表图像进行聚类以获取同一个人的人脸图像;最后对每一个人的人脸图像再次进行评估,得到去重结果。实验结果表明,通过人脸跟踪与无监督聚类融合的方法获取同一个人的人脸图像,再结合人脸质量评估算法,能够快速有效地从一段视频中获取每个人不重复的高质量人脸图片。
中图分类号:
[1] LI X F.Development status and changes of the face recognition market [J].China Security,2020(Z1):39-42. [2] ZHOU J,LU C Y,ZHANG C S,et al.A review of automaticface recognition methods [J].Acta Electronica Sinica,2000(4):102-106. [3] LIANG L H,AI H Z,XU G Y,et al.Review of research on face detection [J].Journal of Computer Science,2002(5):449-458. [4] FANG G N,HU Q H,FANG S Y,et al.Face image quality evaluation in video stream and its application in classroom attendance system [J].Computer Applications and Software,2018,35(10):140-146,251. [5] CHEN Q.Face detection and face deduplication in video surveillance [D].China Jiliang University,2018. [6] CHEN Z H,WU Y D,CAI G R,et al.Facequality assessment algorithm based on texture feature fusion [J].Journal of Jimei University (Natural Science),2018,23(4):312-320. [7] WANG C,CUI R Y,JIN J X,et al.Research on the optimization method of face images in videos based on face clustering [J].Progress in Laser and Optoelectronics,2019,56(20):243-251. [8] CAO X,ZHANG C,ZHOU C,et al.Constrained multi-view video face clustering [J].IEEE Transactions on Image Processing,2015,24(11):4381-4393. [9] WU B,ZHANG Y,HU B,et al.Constrained clustering and its application to face clustering in videos [C]//Proceedings of the IEEE Conference on Computer Vision and PatternRecognition.Portland Oregon:IEEE,2013:3507-3514. [10] ZHANG K,ZHANG Z,LI Z,et al.Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks[J].IEEE Signal Processing Letters,2016,23(10):1499-1503. [11] ORTIZ E G,WRIGHT A,SHAH M.Facerecognition in movie trailers via mean sequence sparse representation-based classification[J].IEEE Conference on Computer Vision and Pattern Recognition,2013:3531-3538. [12] PECH-PACHECO J L,CRISTOBAL G,CHAMORRO-MAR-TINEZ J,et al.Diatom autofocusing in brightfield microscopy:a comparative study [C]//15th International Conference on Pattern Recognition.Barcelona,Spain.New York:IEEE,2002:6894564. [13] ZHANG C H,SHI Y Z.Dynamic face clustering based on Chin-ese Whispers [J].Computer Technology and Development,2019,29(11):92-96. [14] AMIG,ENRIQUE,GONZALO,et al.A comparison of extrinsic clustering evaluation metrics based on formalconstraints[J].Information Retrieval,2009,12(5):461-486. |
[1] | 景慧昀, 周川, 贺欣. 针对人脸检测对抗攻击风险的安全测评方法 Security Evaluation Method for Risk of Adversarial Attack on Face Detection 计算机科学, 2021, 48(7): 17-24. https://doi.org/10.11896/jsjkx.210300305 |
[2] | 张开强, 蒋从锋, 程小兰, 贾刚勇, 张纪林, 万健. 多分辨率下资源感知的图像目标自适应缩放检测 Resource-aware Based Adaptive-scaling Image Target Detection Under Multi-resolution Scenario 计算机科学, 2021, 48(4): 180-186. https://doi.org/10.11896/jsjkx.201200116 |
[3] | 王文博, 罗恒利. 基于图卷积神经网络的完全图人脸聚类 Complete Graph Face Clustering Based on Graph Convolution Network 计算机科学, 2021, 48(11A): 275-277. https://doi.org/10.11896/jsjkx.201200102 |
[4] | 邓良, 许庚林, 李梦杰, 陈章进. 基于深度学习与多哈希相似度加权实现快速人脸识别 Fast Face Recognition Based on Deep Learning and Multiple Hash Similarity Weighting 计算机科学, 2020, 47(9): 163-168. https://doi.org/10.11896/jsjkx.190900118 |
[5] | 赵博, 杨明, 汤志伟, 蔡玉鑫. 基于FPGA的智能视频加速检索系统 Intelligent Video Surveillance Systems Based on FPGA 计算机科学, 2020, 47(6A): 609-611. https://doi.org/10.11896/JsJkx.190700118 |
[6] | 钟马驰, 张俊朗, 蓝扬波, 何月铧. 基于人脸检测和模糊综合评判的在线教育专注度研究 Study on Online Education Focus Degree Based on Face Detection and Fuzzy Comprehensive Evaluation 计算机科学, 2020, 47(11A): 196-203. https://doi.org/10.11896/jsjkx.191100203 |
[7] | 罗恒利, 王文博, 葛宏孔. 基于上下文约束的人脸聚类算法 Face Clustering Algorithm Based on Context Constraints 计算机科学, 2019, 46(11A): 260-263. |
[8] | 霍芋霖,符意德. 基于Zynq的人脸检测设计 Face Detection Design Based on Zynq 计算机科学, 2016, 43(10): 322-325. https://doi.org/10.11896/j.issn.1002-137X.2016.10.060 |
[9] | 贾宁,高楠,力贵才,王兆云. 基于OpenCV的图像分类软件的设计与实现 Design and Implementation of Image Classification Software Based on OpenCV 计算机科学, 2014, 41(Z11): 150-153. |
[10] | 叶俊,张正军. 基于DS-Adaboost算法的人脸检测 Face Detection Based on DS-Adaboost Algorithm 计算机科学, 2013, 40(Z11): 318-319. |
[11] | 谢倩茹,耿国华. 复杂光照环境下视频人脸序列的自动检测方法 Automatic Face Detection in Video Sequences in Complex Lighting Environments 计算机科学, 2011, 38(10): 267-269. |
[12] | 张永,薛芝茂. 基于两级分类器的人脸检测系统设计 Face Detection System Design Based on Two Classifiers 计算机科学, 2010, 37(4): 293-. |
[13] | 李样,王建国. 彩色图像中纯脸检测与定位的优化算法研究 Optimization Algorithm for Detection and Localization of Pure Face in Color Images 计算机科学, 2009, 36(7): 284-287. https://doi.org/10.11896/j.issn.1002-137X.2009.07.070 |
[14] | . 基于广义掩膜积分图像的快速模板匹配 计算机科学, 2008, 35(6): 223-226. |
[15] | 蒋鹏 秦小麟. 一种基于多特征的视频人物聚类方法 计算机科学, 2008, 35(5): 240-242. |
|