摘要: 分析了K-means聚类算法在图像检索中的缺点,提出了一种改进的K-means聚类算法的图像检索方法。它首先计算图像特征库里面的所有颜色直方图特征之间的欧氏距离;然后根据“两个对象距离越近,相似度越大”[1]这一原理,找到符合条件的特征向量作为K-means聚类的初始类心进行聚类;最后进行图像检索。实验结果表明,本算法具有较高的检索准确率。
[1] 百度百科.http://baike.baidu.com/view/3066906.htm [2] VelpKamp R C.Content-Based Image Retrieval System:A Survey[D].Mirela Tanase Department of Comnuting Seience,Utrecht University,2001 [3] Pena J M,Lozano J A,Larranaga P.An empiricalcomparison of four initialization methods for the K-means algorithm[J].Pattern Recognition letters,1999,20(10):1027-1040 [4] 张培珍,付萍,晓君.基于聚类的图像检索[J].计算机工程与应用,2004,31:46-48 [5] Kebapci H,Unal B Y G.Plant Image Retrieval Using Color,Shape and Texture Features[J].The Computer Journal Advance Access,2011,54(9):1475-1490 [6] Barrios J M,Diaz-Espinoza D,Bustos B.Text-Basedand Content-Based Image Retrieval on Flickr:DEMO[C]∥Similarity Search and Application,2009.SISAP’09.Second International Workshop,2009:156-157 [7] Elango P K,Jayaraman K.Clustering Images Using the Latent Dirichlet Allocation Model[Z].Dec.2005 [8] Thilagamani S,Shanthi N.A Survey on Image SegmentationThrough Clustering[J].International Journal of Research and Reviews in Information Sciences,2011,1(1) [9] Zhou X S,Huang T S.Relevance feedback in image retrieval:A comprehensive review[J].Multimedia Syst.,2003,8(6):536-544 [10] Chundi P,Dayal U,Sayal M,et al.US20077181678,7 [11] Chen Yi-xin,Wang J Z,Krovetz R.Content Based Image Retrieval by Clustering[C]∥Proc of the 5th ACM SIGMM I’ntl workshop on multimedia information retrieval.New York,ACM press,2003:193-200 [12] Zhou Hui-yu,Sadka A H,Swash M R,et al.Content Based Ima-ge Retrieval and Clustering:A Brief Survey[D].School of Engineering and Design,Brunel University,Uxbridge,UB83PH,UK,2009 [13] Zhang Q,Goldman S A,Yu W,et al.Content based image retrieval using multiple instance learning[C]∥Proc.ICML.2002 [14] Kolen J F,Hntcheson T.Redneing the Time Complexity of the Fuzzy c-Means Alorithm[J].TFS,2002,10(2):263-267 [15] Pentand A,Picard R,Sclaroff S.Photobook:tools for contentbased Manipulation of database[J].SPIE,1994,2185:34-47 [16] Looney C G.A Fuzzy Clustering and Fuzzy Merging Algorithm[Z].Cs791q Class notes,1999 [17] Wu X,Kumar V,et al.Top 10 algorithms in data mining[J].Knowl.Inf.Syst.,2007(14):1-37 [18] Huang Zhe-xue.Extensions to the k-means algorithm for clustering large data sets with categorical values[C]∥Data mining Konwledge Discovery.Netherlands:Kluwer Academic Publi-shers,1998:283-304 [19] Rui Y,Huang T S,ChangHANG S F.Image retrieval:current techniques,promising directions,and open issues[J].Visual Communication and Image Representation,1999,0(1):39-62 [20] Richard O D,Peter E H,David G S.模式分类(第2版)[M].北京:机械工业出版社,2004 [21] 陈湘涛,王爱云,谢伟平,等.基于内容图像检索的聚类算法研究[J].计算机应用研究,2008,12:3546-3549 [22] Jainak,Vailay A A.Image retrievalusing color and shape[J].Pattern Recognition,1997,9(8):1233-1244 [23] 杨阳,刘峰.分类器的数据预处理[J].计算机工程,1998,24(4):33-34 [24] 施伟,战守义,盛思源.基于粗糙集理论的数据预处理[J].计算机工程与应用,2003(22):193-194 |
No related articles found! |
|