摘要
Criminisi算法对于含有复杂的纹理结构信息的图像,修复时会出现优先权不合理与匹配块匹配错误的情况。为此提出多样本块匹配的方法。对于优先权,为了使结构信息更先修复,把结构项改进为块结构稀疏度和邻域像素差异度的数值和。对于匹配块匹配不合理的情况,先使用块内距离与块间距离设定阈值,如果破损块与样本块之间的块间距离或者块内距离大于阈值,则用多块匹配的方法恢复当前破损块;否则,用传统的Criminisi图像修复算法修复。结果表明,使用此方法修复结果较好,符合人类视觉原理。
The Criminisi image restoration algorithm for the image which has the complex texture structure information around damaged area,there is a case where the priority is unreasonably and the mismatch of the matching blocks.There for a multi-block matching method is proposed.To the priority,in order to make the structural information more repaired,the structural term is improved to the sum of the block structure sparseness and the neighborhood pixel difference degree.To the match block matching unreasonable situation,first,using the distance between the block and the distance inner the block sets the threshold,if the distance between the block and the distance inner the block＇s distance is greater than the threshold,then using the multi-block matching method to restore the current damage block,otherwise,using the traditional Criminisi image restoration algorithm repairs.The results show that the use of this method to repair the results is better,more in line with human visual principles.
作者
何凤杰
郭中华
杜娟
裴希伍
He Fengjie;Guo Zhonghua;Du Juan;Pei Xiwu(School of Physics and Electronic-Electrical Engineering, Ningxia University, Yinchuan 750021, China;Ningxia Key Laboratory of Intelligent Sensing for Desert In{ormation, Yinchuan 750021, China;Chengdu Kaitian Electronic Co. , Ltd. , Chengdu 610091, China)
出处
《国外电子测量技术》
2018年第3期34-37,共4页
Foreign Electronic Measurement Technology
关键词
图像修复
结构稀疏度
邻域像素差异度
块内距离
块间距离
多块匹配
image restoration
structural sparseness
neighborhood pixel difference
distance between the block
distance inner the blockl multi-sample block matching
