A new image segmentation algorithm based the fusion of Markov random field and fuzzy c-means clustering

Author

Liu, Siyuan ; Li, Xiaofeng ; Li, Zaiming

Author_Institution

Sch. of Commun. & Inf. Eng., Univ. of Electron. Sci. & Technol. of China, Chengdu, China

Volume

1

fYear

2005

fDate

12-14 Oct. 2005

Firstpage

144

Lastpage

147

Abstract

A new image segmentation algorithm based on the fusion of Markov random field and fuzzy c-means clustering (FCM) is proposed in this paper. Due to disregard of spatial constraint information, the FCM algorithm fails to segment images corrupted by noises. For improving the robustness of FCM to noises, we use Markov random field model to represent the spatial constraint information of an image and based on the fusion of Markov spatial constraint field and the fuzzy segmentation information resulting from FCM, the new algorithm overcomes the problem of FCM and keeps the computation simplicity. The results of experiments prove the robustness and validity our algorithm.

Keywords

Markov processes; fuzzy set theory; image segmentation; pattern clustering; sensor fusion; Markov random field; fuzzy c-means clustering; image segmentation algorithm; spatial constraint information; Clustering algorithms; Image segmentation; Markov random fields; Noise robustness; Noise shaping; Pixel; Random variables; Shape;

fLanguage

English

Publisher

ieee

Conference_Titel

Communications and Information Technology, 2005. ISCIT 2005. IEEE International Symposium on

Print_ISBN

0-7803-9538-7

Type

conf

DOI

10.1109/ISCIT.2005.1566818

Filename

1566818