Unsupervised Learning of Gaussian Mixture Model with Application to Image Segmentation  

作　　者：LI Bo LIU Wenju DOU Lihua 

机构地区：[1]School of Automation, Beijing Institute of Technology, Beijing 100081, China [2]Key Laboratory of Complex System Intelligent Control and Decision （Beijing Institute of Technology）, Ministry of Education, Beijing 100081, China [3]National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100080, China

出　　处：《Chinese Journal of Electronics》2010年第3期451-456,共6页电子学报（英文版）

基　　金：This work is supported by the National Natural Science Foundation of China （No.60675026, No.60121302, No.90820011）, 863 China National High Technology Development Project （No.20060101Z4073, No.2006AA01Z194）, the National Grand Fundamental Research 973 Program of China （No.2004CB318105）.

摘　　要：Density estimation via Gaussian mixture modeling has been successfully applied to image segmentation, speech processing and other fields relevant to clustering analysis and Probability density function （PDF） modeling. Finite Gaussian mixture model is usually used in practice and the selection of number of mixture components is a significant problem in its application. For example, in image segmentation, it is the donation of the number of segmentation regions. The determination of the optimal model order therefore is a problem that achieves widely attention. This paper proposes a degenerating model algorithm that could simultaneously select the optimal number of mixture components and estimate the parameters for Gaussian mixture model. Unlike traditional model order selection method, it does not need to select the optimal number of components from a set of candidate models. Based on the investigation on the property of the elliptically contoured distributions of generalized multivariate analysis, it select the correct model order in a different way that needs less operation times and less sensitive to the initial value of EM. The experimental results show the effectiveness of the algorithm.

关 键 词：Gaussian mixture model Model order Degenerating model Elliptically contoured distributions Image segmentation. 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TN912.34[自动化与计算机技术—计算机科学与技术]