基于图像结构和纹理的快速修复方法  

Fast Inpainting Approach Based on Image Structure and Texture

作　　者：林胜华[1] 汪继文[1] 沈玉峰[1] 张义超[1] 

机构地区：[1]安徽大学计算机科学与技术学院,安徽合肥230039

出　　处：《计算机技术与发展》2008年第12期88-91,共4页Computer Technology and Development

基　　金：安徽省自然科学基金项目（2006KJ028B）

摘　　要：传统的图像修复算法对纯结构或纯纹理图像有较好的修复效果。对于一幅既有结构又有大量纹理的图像，可先将图像分解为结构子图和纹理子图，再分别用不同的方法处理两子图，最后把处理后的子图合并，完成修复。对结构子图的处理常采用基于PDE的修复方法，该方法需要复杂的运算，其时间代价太大。为了提高效率，使用一种新方法，结合结构图像的特征，仅利用邻域的已知信息单次填充进行修复。试验对比表明，该方法有较好的修复效果，且大大缩短了修复时间。The traditional image restoration algorithms are effective for the pure structure or the pure texture image. For the image that contain structure and massive textures,the basic idea is to first decompose the image into the sum of two functions with different basic characteristics, and then reconstruct each one of these functions separatdy with structure and texture filling - in algorithms. The inpainting result is obtained by adding back these two sub- images. The structure image is repaired by the exemplar- based or PDEs method. In order to enhance efficiency of repair,in this paper, a novel algorithm is proposed for inpainting structure image. Experiments show the proposed algorithm simplify, quickly and effectively.

关 键 词：图像修复 图像分解 结构图像 纹理合成 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]