| 摘要: |
| 针对传统算法在图像修复时选取最佳块匹配准则的单一性和随机性的问题，提出了一种空间差异度量约束的图像修复方法。该算法利用等照度线确定待修复块的优先级，根据空间差异度量约束的最佳块匹配准则搜索与该待修复块最匹配的样本块，采用最佳匹配块的信息更新优先级最高的待修复块的信息以修复其缺失像素信息。实验结果表明，与传统算法相比，所提算法能有效提高图像修复的主客观质量，对三种类型的信息缺失均取得了较好的修复效果。 |
| 关键词: 图像修复 空间差异度量 块匹配 平方差之和 |
| DOI： |
|
| 基金项目:陕省教育厅专项科研计划项目（17JK0707）；中国科学院光谱成像技术重点实验室开放基金课题(LSIT201709D)；模式识别国家重点实验室开放课题(201700013)；浙江大学CAD&CG国家重点实验室开放课题（A1820）；北京航空航天大学虚拟现实技术与系统国家重点实验室开放基金（VRLAB2018B13） |
|
| Image inpainting based on spatial difference metric constraint |
| LAI Yi,REN Li,LIU Ying |
| (School of Telecommunication and Information Engineering,Xi'an University of Posts and Telecommunications,
Xi′an 710121,China;Key Laboratory of Electronic Information Application Technology for Scene Investigation,
Ministry of Public Security,Xi′an 710121,China;
Key Laboratory of Spectral Imaging Technology of Chinese Academy of Sciences,Xi′an 710119,China) |
| Abstract: |
| To to solve the problems of singleness and randomness of the best patch matching criterion in image inpainting,an improved image inpainting method based on spatial difference metric constraint is proposed.The developed algorithm uses the isophote to determine the priority of the patches to be repaired,and searches the sample patch that best matches the one to be repaired according to the optimal patch matching strategy based on the spatial difference metric constraint.And then the information of the best priority patch is updated with the information of the best matching patch to recover the missing pixel information.Experimental results show that the presented algorithm can effectively improve the subjective and objective quality of image inpainting,and achieve better visual results for three types of information loss compared with the traditional algorithms. |
| Key words: image inpainting spatial difference metric patch matching sum of squared difference |
