Unsupervised color image segmentation using mean shift and deterministic annealing EM

Authors:
Wanhyun Cho;Jonghyun Park;Myungeun Lee;Soonyoung Park
Affiliations:
Department of Statistics, Chonnam National University, Chonnam, South Korea;Institute for Robotics and Intelligent Systems, University of Southern California, Los Angeles, CA;Department of Electronics Engineering, Mokpo National University, Chonnam, South Korea;Department of Electronics Engineering, Mokpo National University, Chonnam, South Korea
Venue:
ICCSA'05 Proceedings of the 2005 international conference on Computational Science and Its Applications - Volume Part IV
Year:
2005

Citing 5
Cited 2

Deterministic annealing EM algorithm

Neural Networks
Mean Shift: A Robust Approach Toward Feature Space Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
Mean Shift, Mode Seeking, and Clustering

IEEE Transactions on Pattern Analysis and Machine Intelligence
Pairwise Data Clustering by Deterministic Annealing

IEEE Transactions on Pattern Analysis and Machine Intelligence
Estimation of generalized mixtures and its application in image segmentation

IEEE Transactions on Image Processing

Region-based fit of color homogeneity measures for fuzzy image segmentation

Fuzzy Sets and Systems
An unsupervised model for exploring hierarchical semantics from social annotations

ISWC'07/ASWC'07 Proceedings of the 6th international The semantic web and 2nd Asian conference on Asian semantic web conference

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present an unsupervised segmentation algorithm combining the mean shift procedure and deterministic annealing expectation maximization (DAEM) called MS-DAEM algorithm. We use the mean shift procedure to determine the number of components in a mixture model and to detect their modes of each mixture component. Next, we have adopted the Gaussian mixture model (GMM) to represent the probability distribution of color feature vectors. A DAEM formula is used to estimate the parameters of the GMM which represents the multi-colored objects statistically. The experimental results show that the mean shift part of the proposed MS-DAEM algorithm is efficient to determine the number of components and initial modes of each component in mixture models. And also it shows that the DAEM part provides a global optimal solution for the parameter estimation in a mixture model and the natural color images are segmented efficiently by using the GMM with components estimated by MS-DAEM algorithm.