Edge multi-scale markov random field model based medical image segmentation in wavelet domain

Authors:
Wenjing Tang;Caiming Zhang;Hailin Zou
Affiliations:
School of Computer Science and Technology, Shandong University, Jinan, China,School of Information and Electrical Engineering, Ludong University, Yantai, China;School of Computer Science and Technology, Shandong University, Jinan, China;School of Information and Electrical Engineering, Ludong University, Yantai, China
Venue:
ICIC'13 Proceedings of the 9th international conference on Intelligent Computing Theories and Technology
Year:
2013

Citing 8
Cited 0

Markov random field modeling in image analysis

Markov random field modeling in image analysis
Review: A comparative study of deformable contour methods on medical image segmentation

Image and Vision Computing
Integrating spatial fuzzy clustering with level set methods for automated medical image segmentation

Computers in Biology and Medicine
A framework with modified fast FCM for brain MR images segmentation

Pattern Recognition
Homogeneity- and density distance-driven active contours for medical image segmentation

Computers in Biology and Medicine
Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images

IEEE Transactions on Pattern Analysis and Machine Intelligence
Multiscale image segmentation using wavelet-domain hidden Markov models

IEEE Transactions on Image Processing
A multiscale random field model for Bayesian image segmentation

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The segmentation algorithms based on MRF often exist edge block effect, and have low operation efficiency by modeling the whole image. To solve the problems the image segmentation algorithm using edge multiscale domain hierarchical Markov model is presented. It views an edge as an observable data series, the image characteristic field is built on a series of edge extracted by wavelet transform, and the label field MRF model based on the edge is established to integrate the scale interaction in the model, then the image segmentation is obtained. The test images and medical images are experimented, and the results show that compared with the WMSRF algorithm, the proposed algorithm can not only distinguish effectively different regions, but also retain the edge information very well, and improve the efficiency. Both the visual effects and evaluation parameters illustrate the effectiveness of the proposed algorithm.