The region based segmentation method has been attracting much attention in automatic or semi-automatic image segmentation research. This paper proposes a new region based segmentation method based on cloud model in order to take uncertainty into account in image segmentation. Firstly

cloud transform algorithm is given to determine the growing criteria

and then the region is transformed from quantitative pixel set to qualitative concept by backward cloud algorithm

finally cloud synthesis algorithm is realized to merge the two adjacent regions. Experiments show that the new method can extract target from background accurately

and more effectively than traditional image segmentation method.