基于聚类的人脸图像检索及相关反馈.pdfVIP

34 9 2008 9 ACTA AUTOMATICA SINICA Vol. 34, No. 9 September, 2008 11 , , , , . , TP391 , . . , (Normalized cuts, NCuts) AdaBoost ., . Cluster-based Face Image Retrieval and Its Relevance Feedback YANG Zhi-Guang1 AI Hai-Zhou1 Abstract This paper proposes a novel cluster-based face image retrieval algorithm. By using normalized cuts (NCuts) to cluster faces in each time span into optimal partitions, various face images of the same character can be grouped together. A face recognition classi?er learned by real AdaBoost is used for measuring similarity between two faces, and a similarity measure for the query face and the face cluster is further proposed for retrieval. To further improve the performance, we design an online step, in which users can interactively label false positives and missing retrieval, so that some constraints are involved to revise the clustering results. The algorithm is integrated into an automatic retrieval system, and the experiment on a family album containing over a thousand face images con?rms its e?ectiveness in comparison to other alternative algorithms. Key words Family album, face retrieval, face clustering , , , ., (Content based image retrieval, CBIR) . [1] , . , [7?9], , [3?4] [2] , . [5?6] . , . , . . . [10] , [11] , , , : 1) Zhang . , . 2) Zhao . 2007-06-12 2007-11-15 Received June 12, 2007; in revised form November 15, 2007 , (973 ) (2006CB303102) Supported by National Natural Science Foundation of China and National Basic Research Program of China (973 Program) (2006CB303102) 1. 100084 1. Department of Computer Science and Technology, Tsinghua University, Beijing 100084 DOI: 10.3724/SP.J.1004.2008.01033 , . , : Kamei[12] descriptor) (Mahalanobis) ; Kim [13] . MPEG-7 , (Face , 1034 (Component-based) LDA (Linear discriminant analysis) . , . , ., ,. , , ( 80%), . :1 , 2, 3 ,4 . 1 [4] ., , .6 1, [6] 88 () , . : ; , , . : 2 . . : , , . , , (Probe set), ( , ., , , . ,; , 34 , . , , . . , ) . . , . , , 1 Fig. 1 Index