基于边缘信息的图像融合算法研究  

A New Algorithm for Image Fusion Based on Edge Information

作　　者：王勇[1] 韩九强[1] 张新曼[1] 

机构地区：[1]西安交通大学电子与信息工程学院,陕西西安710049

出　　处：《微电子学与计算机》2004年第4期66-68,共3页Microelectronics & Computer

基　　金：教育部教育行动计划资助项目

摘　　要：为了得到全局色调一致的无缝镶嵌融合图像,文章提出了一种基于边缘信息的图像融合方法。该方法根据融合区域的边缘强度信息,对融合区域进行图像增强处理,进而选取一组区域特征进行自适应动态加权,实现了不同图像在选定区域范围内的融合运算,使得被合成的图像完整、自然。通过两幅图像的融合实验,证明了该算法在边缘上保持良好的视觉效果。The combining of image mosaics is an important part of image processing. A new algorithm for image fusion based on edge information is developed to produce seamless image mosaics with global grayscale coherency. The intensity component of the fusion image is modified by enhancing image information which is determined by image edge intensity. Fusion process is performed in specified fusion fields to generate an integrated and smoothing image by dynamic weighting. By fusion experiments of the two images, it appears that the proposed algorithm has excellent visual results in reservation of boundary information as well as neighboring coherence.

关 键 词：图像镶嵌 图像融合 图像增强 动态加权 

分 类 号：TP394.41[自动化与计算机技术—计算机应用技术]