Abstract: In this paper, an improved image segmentation method based on parametric active contour model of inter-region variance was proposed and successfully applied to image segmentation. This proposed model replaces constant force in the balloon parametric active contour model with variable force incorporating foreground and background two regions information. It guides curve to evolve with the criterion of the maximization inter-region variance of the foreground and background. Experimental results show that the proposed model is robustness to initial contours position whether it is inside the target region, or outside background region, or intersects with target and background region, and can segment image automatically.