基于边缘检测的多聚焦彩色图像融合算法  

Color multi-focus image fusion algorithm based on edge detection

作　　者：王建[1] 杨根善 张少应[1] 王国珲[2] 

机构地区：[1]西安航空学院计算机工程系,西安710077 [2]西安工业大学光电工程学院,西安710032

出　　处：《信息技术》2013年第8期15-17,共3页Information Technology

基　　金：陕西省教育厅科研计划资助项目(11JK0996);西安航空学院校级科研基金资助项目(13XP17)

摘　　要：针对左聚焦和右聚焦彩色图像的融合问题,设计了一种基于边缘检测的彩色图像融合算法。首先将彩色图像转换为NTSC图像,再利用Canny方法检测出亮度信息图像的最优边缘,然后对亮度信息图像的边缘部分采用平均法进行融合,其余部分采用相关系数的权值法进行融合,最后将融合之后的饱和度图像、亮度图像和色调图像转换为彩色图像。从融合效果来看,文中算法能够将两幅左右聚焦的彩色图像融合成一幅信息量饱满且清晰的单一聚焦彩色图像。实验结果和信息熵客观评价结论表明,该彩色融合算法能够将信息熵提高2.13%～2.51%。Focusing on the color image fusion problem of the left focus image and right focus image, the color multi-focus image fusion algorithm based on edge detection was designed. First the color image was converted to NTSC image, second the luminance information image was detected best edges using the Canny method, third the edge portions was used the average method and the rest portions were used the correlation coefficient weights method for the luminance information image fusion, finally the color image was converted by the saturation fusion image, the luminance fusion image and the tone fusion image. From the fusion effect, the algorithm can fuse into a full information content and clear single focus color image from two-focus color image. The experimental results and objective evaluation of the information entropy demonstrate that the desinged algorithm is superior with 2. 13% to 2.51% improvement of information entropy.

关 键 词：彩色图像 多聚焦图像 边缘检测 图像融合 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]