作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程

• 图形图像处理 • 上一篇    下一篇

区别结构和纹理的稀疏表示图像修复算法

高飞1,王佳君 2,喻强 2,张晶晶 2   

  1. (1.西藏大学藏文信息技术研究中心,拉萨 850000; 2.西南交通大学信息科学与技术学院,成都 610031)
  • 收稿日期:2015-01-21 出版日期:2016-03-15 发布日期:2016-03-15
  • 作者简介:高飞(1980-),男,副教授、硕士,主研方向为数字图像处理;王佳君(通讯作者)、喻强、张晶晶,硕士研究生。
  • 基金资助:

    国家自然科学基金资助项目(61461048);国家社会科学基金资助项目(12EF19);国家级大学生创新创业训练计划基金资助项目(201210694019);西藏自治区重点科技计划基金资助项目(Z2013B28G28/02)。

Image Inpainting Algorithm Based on Sparse Representation Distinguishing Structure and Texture

GAO Fei  1,WANG Jiajun  2,YU Qiang  2,ZHANG Jingjing  2   

  1. (1.Research Center of Tibetan Information Technology, Tibet University,Lahsa 850000,China; 2.School of Information Science and Technology,Southwest Jiaotong University,Chengdu 610031,China)
  • Received:2015-01-21 Online:2016-03-15 Published:2016-03-15

摘要:

现有基于稀疏表示的图像修复算法在修复破损区域时对纹理块和结构块不加区分,导致修复平滑部分时处理时间较长,同时在修复结构部分时精度较低。针对上述问题,提出一种改进算法。将待修复块分成纹理块和结构块2类,相应构造不同的学习字典。结构块所应用的字典用于确保修复精度,而纹理块所应用的字典则用于在保证纹理清晰的基础上加快修复速度。实验结果表明,该算法在不增加时间复杂度的前提下可有效恢复结构细节,改善破损图像整体修复效果,同时降低处理时间。

关键词: 图像修复, 稀疏表示, 结构块, 纹理块, 字典构造, 结构细节

Abstract:

Existing image inpainting algorithms based on sparse representation do not distinguish structure patch and texture patch when constructing the learning dictionary.This may increase the processing time when inpainting the smooth part of the damaged region,and decrease the inpainting accuracy when inpainting the structure part.To solve this problem,this paper proposes an improved algorithm.It classifies the patches around the damaged region into two categories where one category includes structure patches while the other includes texture patches,and correspondingly constructs two kind of learning dictionaries.For structure patches,their corresponding dictionaries are used to ensure high accuracy.For texture patches,their corresponding dictionaries are used to accelerate inpainting under the condition of clear inpainted texture.Experimental result shows that the proposed algorithm can effectively inpaint the structure detail without increasing the complexity,while the inpainting effect is better with low time consumption.

Key words: image inpainting, sparse representation, structure patch, texture patch, dictionary construction, structure detail

中图分类号: