摘要
针对基于小波变换的多聚焦图像融合算法,改进融合规则和融合算子,低频分量采用以相关系数作为阈值的加权平均算法,高频分量采用基于区域特征的融合算法,并对最佳分解层数与最佳小波基的选取进行优化验证。通过对实验结果的分析,选用bior4.4小波,进行最佳分解层数小波分解,并应用改进的融合规则,在融合多聚焦图像的效果上,与其他多种融合算法相比,各项评价指标都比较理想。
In view of multi-focus image fusion algorithm, fusion rules and fusion operators are improved. The low-frequency component uses the weighted average algorithm with correlation coefficient as threshold, the high-frequency component uses fusion algorithm based on regional characteristics. In addition, the optimal decomposition level and the selection of the best wavelet basis are verified. The evaluation indexes of multi-focus image fusion based on improved fusion rules and bior4.4 wavelet with optimal decomposition level, through the analysis of experimental results, are better than many other fusion algorithm.
出处
《计算机工程与应用》
CSCD
北大核心
2015年第23期184-188,共5页
Computer Engineering and Applications
基金
河北科技师范学院博士基金(No.2011YB-006)
关键词
多聚焦图像融合
小波变换
小波基
融合规则
multi-focus image fusion
wavelet transform
wavelet basis
fusion rules
