一种基于三角形网格的图像分块盲复原算法  

Image Blocking Blind Restoration Method Based on the Triangle Meshes

作　　者：邓莉[1] 鲁瑞华[1] 

机构地区：[1]西南大学电子信息工程学院信号与信息处理研究所,重庆400715

出　　处：《计算机科学》2008年第9期237-238,254,共3页Computer Science

基　　金：校发展基金项目(SWNUF2004006)

摘　　要：针对图像分块方法恢复空间移变降质图像时存在严重的边界噪声,以及采用传统遗传算法进行图像盲复原时运算量大的问题,提出一种基于三角形网格的图像分块盲复原算法。根据图像的退化情况采用三角形网格划分图像子块,并利用微种群遗传算法和传统遗传算法交替进化的方式分别估计各图像子块以及各子块区域中点扩散函数的参数,同时对各图像子块的重叠部分进行边界修正。实验结果表明,与传统的图像分块遗传算法相比,该算法的运行时间和复原图像的边界寄生波纹都大为减少,图像的恢复质量有明显提高。Aiming at the high boundary noise caused by blocking method for image restoration of space-variant blurs,as well as the large computation cost of conventional genetic algorithm for blind image restoration, an image blocking blind restoration method based on the triangle meshes is proposed. The image blocks are divided by the triangle meshes according to the image degradation. The micro population genetic algorithm and the conventional genetic algorithm are alternately used to estimate the image blocks and the parameters of their point spread functions. The boundaries of image blocks are also mended in the overlaps. Experiment results show that the presented method is much faster than the conventional blocking genetic algorithm, the parasitic ripples are obviously reduced, and the quality of the recovered image is enhanced visibly.

关 键 词：三角形网格 图像分块 盲复原 空间移变降质 微种群遗传算法 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TN941.1[自动化与计算机技术—计算机科学与技术]