基于低频边缘特征和能量的多聚焦图像融合方法  

Multi-focus Image Fusion Method Based-on Characteristics of Low-frequency Edge and Energe

作　　者：罗南超[1] 向昌成[1,2] 

机构地区：[1]阿坝师范高等专科学校计算机科学系,四川郫县611741 [2]电子科技大学应用数学学院,成都610054

出　　处：《重庆工学院学报（自然科学版）》2009年第8期168-171,共4页Journal of Chongqing Institute of Technology

基　　金：阿坝师范高等专科学校基金资助项目(网络系统管理专业职业教育培养构建与实践研究)

摘　　要：针对多聚焦图像融合问题,提出一种基于低频边缘特征和能量的多聚焦小波图像融合方法.首先对待融合图像进行小波多尺度分解,然后对高频细节分量图像按区域能量最大化原则进行融合,对低频近似分量图像采用能量结合边缘特征的融合方法.试验结果表明,与已有的低频域平均法相比,该方法所得的融合图像能反映更丰富的细节信息,具有更好的视觉效果.For the problem of multi-focus image fusion, a low-frequency edge-based features and wavelet energy of the multi-focus image fusion method is proposed. Firstly, it decomposes the original images by multi-resolution based on wavelet transform, and then it fuses the high-frequency images based on the local maximum energy principle, and low-frequency fusion is done based on edge features combined with the use of the local energy. Test results show that the algorithm, compared with average algorithm for low-frequency fusion, can preserve richer detail information from primitive images and have better vision effect.

关 键 词：图像融合 小波变换 边缘特征 能量 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]