摘要
The noniterative algorithm of multiscale MRF has much lower computing complexity and better result thanits iterative counterpart of noncausal MRF model, since it has causality property between scales, and such causality isconsistent with the character of images. Maximizer of the posterior marginals(MPM)algorithm of multiscale MRFmodel is presented for only one image can be obtained in image segmentation. EM algorithm for parameter estimate isalso given. Experiments demonstrate that comparing with iterative ones, the proposed algorithms have the character-istics of greatly reduced computing time and better segmentation results. This is more notable for large images.
The noniterative algorithm of multiscale MRF has much lower computing complexity and better result than its iterative counterpart of noncausal MRF model, since it has causality property between scales, and such causality is consistent with the character of images. Maximizer of the posterior marginals (MPM)algorithm of multiscale MRF model is presented for only one image can be obtained in image segmentation. EM algorithm for parameter estimate is also given. Experiments demonstrate that comparing with iterative ones, the proposed algorithms have the characteristics of greatly reduced computing time and better segmentation results. This is more notable for large images.
出处
《计算机科学》
CSCD
北大核心
2003年第7期174-176,共3页
Computer Science
基金
国家自然科学基金(60133010)
教育部博士点基金
关键词
图像分割
图像像素
多尺度马尔可夫随机场
图像边缘
图像处理
Multiscale markov random field(MRF),Noniterative algorithm,Iterative algorithm, Maximizer of the posterior marginals (MPM), Expectation maximization (EM)
