A multi-step decision model based on adaptive edge preserving generalized gradient vector flow using component-based normalization for snake model is proposed.

The proposed algorithm presents a novel external force, which provides better results than other approaches in terms of noise robustness, weak edge preserving and convergence.

An improved multi-step decision model based on this novel external force is adopted, which adds new effective weighting function to attenuate the magnitudes of unwanted edges and adopts narrow band method to reduce time complexity.

Experimental results and comparisons against other methods show that the proposed method has better segmentation accuracy than other comparative approaches.