基于多小波变换的多聚焦图像融合  

Multi-focus image fusion method based on multi-wavelet transform

作　　者：朱四荣[1] 王迎春[1] 

机构地区：[1]武汉理工大学理学院,武汉430070

出　　处：《计算机工程与应用》2010年第6期169-170,226,共3页Computer Engineering and Applications

基　　金：国家自然科学基金(No.10672128;No.50878169);the National Natural Science Foundation of China under Grant No.10672128;No.50878169

摘　　要：多聚焦图像融合的关键问题是如何保持原始图像的边缘和细节信息。多小波分析具有多个分析基函数和产生更多分解子图像的特点。在多小波变换域对低频和高频小波系数采用不同的融合方法——对低频系数采用取平均的方法,而对高频系数采用边缘梯度对比的方法。通过实验证明,该方法能够很好地保存图像的边缘和细节信息,融合结果得到了改善。The key problem in multi-focus image fusion is how to keep the detail and edge in the original image.Based on the features of more decomposing sub-images generated by the multi-wavelet analysis function,a new image fusion method is proposed in this paper.In wavelet domain,different fusion rules are adopted for low frequency coefficient and high frequency coefficient.The rule of average method is used to fuse low frequency coefficient and the contrast of edge gradient for high frequency coefficient.The experiments demonstrate that this method can save the edge of original image and improve the result.

关 键 词：多小波变换 边缘梯度 图像融合 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]