基于模糊算法的多聚焦图像融合效果评价研究  

Multi-Focus Image Fusion Effect Evaluation Based on Fuzzy Algorithm

作　　者：胡春海[1] 丁志秀[1] 

机构地区：[1]燕山大学电气工程学院,河北秦皇岛066004

出　　处：《传感技术学报》2007年第4期885-888,共4页Chinese Journal of Sensors and Actuators

摘　　要：针对多聚焦图像的融合效果评价问题,提出了一种基于模糊理论的图像融合效果评价方法.该方法采用融合图像熵值、交互信息量值、平均梯度值、偏差值构成单因素评价指标集,引入基于专家评判法的人的知识确定隶属度函数,用对比排序法综合各个单因素指标得到综合评价指标,其计算简单,评价结果更为全面客观.将该方法应用于多聚焦图像的融合试验,评价结果与理论分析和人的目视效果一致,从而证明了该评价方法的有效性.In view of the multi-focus image fusion effect evaluation problem, the effect evaluation method based on fuzzy algorithm is proposed. This method uses the fusion image entropy value, the interactive information magnitude, the average gradient value, and the deviation amount to form a set of single-factor evaluation measure. Then,we introduce human knowledge based on experts＇ judgment method into defining membership functions. We obtained a synthetic evaluation factor by synthesizing single factors with con- trast-queue-method. This method is easily be counted. Its appraisal result is more comprehensive and objective. This method was applied in the multi-focus image fusion experiment, so the appraisal result is consistent with the theoretical analysis and human＇s visual effect, and proves the validity of the assessment method.

关 键 词：图像融合 多聚焦 模糊算法 评价指标 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]