TANG Wen-jing, XU Zhao-xin. Image segmentation algorithm of wavelet domain Markov model with boundary[J]. 2014, 33(9): 145-147+154. DOI: 10.13873/J.1000-9787(2014)09-0145-03.
结合边界的小波域马尔科夫模型的图像分割算法
摘要
针对基于马尔科夫随机场(MRF)的分割算法常存在边界块效应
且对整幅图像进行建模运行效率低等问题
提出了结合边界的小波域马尔科夫模型的图像分割算法
把影像的特征场建立在一系列小波域提取的边界上
并建立相应的边界标号场MRF模型
借助贝叶斯框架和SMAP准则实现分割。利用Matlab GUI实现了分割系统
通过医学图像检验
结果表明:相比于小波域分层随机场模型(WMSRF)
该算法在有效区分不同区域的同时很好地保留了边界信息
提高了运行效率。
Abstract
Aiming at problems that segmentation algorithms based on MRF often occur boundary block effect and low operation efficiency by modeling the whole image
image segmentation algorithm using wavelet domain Markov model with boundary is proposed. In which the image characteristic field is built on a series of boundary extracted by wavelet domain
and corresponding label field MRF model with boundary is established
then image segmentation is obtained by Bayesian framework and SMAP. The segmentation system based on Matlab GUI is implemented
and the medical images are utilized to test the proposed algorithm. The results show that it can not only distinguish effectively different regions
but also retain the boundary information very well
and improve operation efficiency compared with WMSRF.
Homogeneity- and density distance-driven active contours for medical image segmentation [J] . Phan Tran Ho Truc,Tae-Seong Kim,Sungyoung Lee,Young-Koo Lee. Computers in Biology and Medicine . 2011 (5)
Integrating spatial fuzzy clustering with level set methods for automated medical image segmentation [J] . Bing Nan Li,Chee Kong Chui,Stephen Chang,S.H. Ong. Computers in Biology and Medicine . 2010 (1)