A Modified Deterministic Annealing Algorithm for Robust Image Segmentation

Authors:
Xu-Lei Yang;Qing Song;Yue Wang;Ai-Ze Cao;Yi-Lei Wu
Affiliations:
Nanyang Technological University, Singapore, Singapore;Nanyang Technological University, Singapore, Singapore;Institute for Infocomm Research, Singapore, Singapore;Vanderbilt University, Nashville, USA;Nanyang Technological University, Singapore, Singapore
Venue:
Journal of Mathematical Imaging and Vision
Year:
2008

Citing 12
Cited 0

An introduction to support Vector Machines: and other kernel-based learning methods

An introduction to support Vector Machines: and other kernel-based learning methods
Spatial models for fuzzy clustering

Computer Vision and Image Understanding
Pattern Recognition with Fuzzy Objective Function Algorithms

Pattern Recognition with Fuzzy Objective Function Algorithms
Constrained Clustering as an Optimization Method

IEEE Transactions on Pattern Analysis and Machine Intelligence
A New Cluster Validity for Data Clustering

Neural Processing Letters
A robust deterministic annealing algorithm for data clustering

Data & Knowledge Engineering
Robust image segmentation using FCM with spatial constraints based on new kernel-induced distance measure

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Image segmentation by a fuzzy clustering algorithm using adaptive spatially constrained membership functions

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
A novel kernelized fuzzy C-means algorithm with application in medical image segmentation

Artificial Intelligence in Medicine
Robust clustering methods: a unified view

IEEE Transactions on Fuzzy Systems
Segmentation of color lip images by spatial fuzzy clustering

IEEE Transactions on Fuzzy Systems
An introduction to kernel-based learning algorithms

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we present a modified deterministic annealing algorithm, which is called DA-RS, for robust image segmentation. The presented algorithm is implemented by incorporating the local spatial information and a robust non-Euclidean distance measure into the formulation of the standard deterministic annealing (DA) algorithm. This implementation offers several improved features compared to existing image segmentation methods. First, it has less sensitivity to noise and other image artifacts due to the incorporation of spatial information. Second, it is independent of data initialization and has the ability to avoid many poor local optima due to the deterministic annealing process. Lastly, it possesses enhancing robustness and segmentation ability due to the injection of a robust non-Euclidean distance measure, which is obtained through a nonlinear mapping by using Gaussian radial basis function (GRBF). Experimental results on synthetic and real images are given to demonstrate the effectiveness and efficiency of the presented algorithm.