基于聚焦测度和决策图的岩石薄片图像融合  

Rock Thin Section Image Fusion Based on Focus Measure and a Decision Map

作　　者：康瑕[1] 滕奇志[1] 唐棠[1] 何小海[1] 

机构地区：[1]四川大学电子信息学院,成都610064

出　　处：《计算机与数字工程》2009年第2期125-128,共4页Computer & Digital Engineering

摘　　要：为了解决显微镜成像时高倍数和大景深不能共存的矛盾,得到高质量的显微图像,提出了一种简单的空间域像素级显微图像融合算法。首先将彩色图像转换成灰度图像,然后使用基于Sobel算子的Tenengrad聚焦测度生成初始决策图。最后采用一致性检验去除决策图中的孤立点,由精炼后的决策图生成融合图像。用该方法对多组显微薄片图像进行融合,将其结果与基于SML,EOL和SF的融合结果进行了比较。实验结果表明,该方法优于文中提到的其它方法。To resolve a contradiction between high magnification and long DOF in microscopy technology, acquiring microscopy image of desired quality, a simple algorithm for pixel- level microscopy image fusion in spatial domain is presented. Firstly the color image is converted to grayscale intensity, and then an initial decision map is generated using Tenengrad focus measure method, which is based on Sobel operator. Finally an iterative consistency checking method is used to remove isolated points in decision map, and the fused image is generated from the refined decision map. Experiments are conducted on several sets of macroscopic thin section images, and the performance of the method is compared with image fusion methods based on SML, EOL and SF. The results show that the method is superior to the other methods mentioned in this paper.

关 键 词：聚焦测度 决策图 图像融合 

分 类 号：TN911.73[电子电信—通信与信息系统]