Image segmentation is the key component in the automatic target recognition system (ATRS). It's an important step of image analysis. Its results have critical implications for the information processing stages that follow: The evaluation of a segmentation algorithm makes an important part of the estimation of performance for are as an off-line ATRS; Based on the knowledge of data fusion and systems engineering

a new model of gray multi-hierarchical appraise by combining gray appraise method with the Analytic Hierarchy Process (AHP) and data fusion is proposed in this paper. It is used to evaluate the performance of image segmentation. The performance evaluation can be performed from both global and local aspects. The paper also discussed evaluation models and their experimental comparative results to prove its feasibility and to confirm the advantages of the new model. The application shows that the new model is more efficient and reasonable than other methods.