评估图像匹配算法的优劣很难用“好”或“不好”来界定，评估结果往往存在一定的模糊性，因此，可以利用模糊理论中的综合评判方法对图像匹配算法的性能进行评估，指明评估结果隶属于某个评语的程度，得出更加科学的评估结论。本文结合多种图像匹配算法性能评估指标重点说明了模糊综合评判模型的建立过程及权重的确定方法，经过评估实验，对灰度相关匹配算法和相位相关匹配算法两类算法进行性能评估，得出了比单一指标评估体系更好的评估结果，验证了评估模型的实用性和有效性。

Since the result of evaluation usually had ambiguity, it is difficult to define the performance of image matching algorithm with “good” or “bad”. So the performance of image matching algorithm can be evaluated by comprehensive evaluation method in fuzzy theories, which indicated the degree of evaluation results belonging to a certain review. Finally, it can get more scientific evaluation results. Combined with image matching algorithm performance evaluation of multiple criteria, the modeling course and the method for determining the weight were explained. With the evaluation experiments, the performance of gray correlation matching algorithm and phase correlation matching algorithm was evaluated by using the model. Compared with the single criteria evaluation architecture, the evaluation result is better. The practicality and effectiveness of the evaluation model are proved.