A particular Gaussian mixture model for clustering and its application to image retrieval

被引:0
作者
Hichem Sahbi
机构
[1] Cambridge University,Machine Intelligence Laboratory, Department of Engineering
[2] Ecole Nationale des Ponts et Chaussees,Certis Laboratory
来源
Soft Computing | 2008年 / 12卷
关键词
Gaussian mixture models; Clustering; Kernel methods and image retrieval;
D O I
暂无
中图分类号
学科分类号
摘要
We introduce a new method for data clustering based on a particular Gaussian mixture model (GMM). Each cluster of data, modeled as a GMM into an input space, is interpreted as a hyperplane in a high dimensional mapping space where the underlying coefficients are found by solving a quadratic programming (QP) problem. The main contributions of this work are (1) an original probabilistic framework for GMM estimation based on QP which only requires finding the mixture parameters, (2) this QP is interpreted as the minimization of the pairwise correlations between cluster hyperplanes in a high dimensional space and (3) it is solved easily using a new decomposition algorithm involving trivial linear programming sub-problems. The validity of the method is demonstrated for clustering 2D toy examples as well as image databases.
引用
收藏
页码:667 / 676
页数:9
相关论文
共 20 条
  • [1] Carson C(2002)Blobworld: image segmentation using expectation-maximization and its application to image querying IEEE Trans Pattern Anal Mach Intell 24 1026-1038
  • [2] Belongie S(1991)Characterization and detection of noise in clustering In Pattern Recognit 12 657-664
  • [3] Greenspan H(1977)Maximum likelihood from incomplete data via the em algorithm J R Stat Soc B 39 1-38
  • [4] Malik J(1998)Algorithms for model-based gaussian hierarchical clustering SIAM J Sci Comput 20 270-281
  • [5] Dave RN(1999)A robust competitive clustering algorithm with applications in computer vision IEEE Trans Pattern Anal Mach Intell 21 450-465
  • [6] Dempster A(2001)Hierarchical model-based clustering for large datasets J Comput Graph Stat 10 464-486
  • [7] Laird N(2000)A global geometric framework for non-linear dimensionality reduction Science 290 2319-2323
  • [8] Rubin D(1994)Fuzzy kohonen clustering networks PR 27 757-764
  • [9] Fraley C(1999)LOQO: an interior point code for quadratic programming Optim Methods Softw 11 451-484
  • [10] Frigui H(1993)A survey of fuzzy clustering MathCompMod 18 1-16