Large Scale Image Inpainting Based on Exemplar and Structure Information

doi:10.3969/j.issn.0372-2112.2012.08.003

您当前的位置：

首页 >

文章列表页 >

Large Scale Image Inpainting Based on Exemplar and Structure Information

更新时间：2025-07-08

- Large Scale Image Inpainting Based on Exemplar and Structure Information
- Acta Electronica Sinica Vol. 40, Issue 8, Pages: 1509-1514(2012)
- 作者机构：
  
  1. 哈尔滨工业大学深圳研究生院机电工程与自动化学院,广东,深圳,518055
  2. 深圳先进运动控制技术与现代自动化装备重点实验室,广东,深圳,518055
  3. 哈尔滨工业大学深圳研究生院机电工程与自动化学院,广东,深圳,518055
  4. 深圳先进运动控制技术与现代自动化装备重点实验室,广东,深圳,518055
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.50805031);Science and Technology Program of Shenzhen (No.JC201005260161A);Special fund for Three Industries of Shenzhen (No.JC201104210015A);Shenzhen Nanshan Science and Technology Project (No.201002)
- DOI：10.3969/j.issn.0372-2112.2012.08.003
  CLC： TP302.7
- Published：2012
- 稿件说明：
移动端阅览
Large Scale Image Inpainting Based on Exemplar and Structure Information[J]. Acta Electronica Sinica, 2012, 40(8): 1509-1514.
DOI：

Large Scale Image Inpainting Based on Exemplar and Structure Information[J]. Acta Electronica Sinica, 2012, 40(8): 1509-1514. DOI： 10.3969/j.issn.0372-2112.2012.08.003.

摘要

基于纹理的图像修复算法对于修复破损区域比较大的图像效果较好

但该算法对于含有结构信息的图像修复效果很差.通过新的优先项的计算、平均值补偿及增加惩罚项提高传统的基于样本的图像修复算法的修复效果

结合图像中常出现的直线和曲线结构特征

提出了基于样本和结构信息的大范围图像修复算法.实验表明

该算法易于实现

修复结果能达到令人满意的效果

具有较高的实用价值.

Abstract

Image inpainting algorithms prefer to use the texture-based method to inpaint large scale missing regions

but the result is undesirable when the image contains structural information.Through introducing new priority value

mean value complement and penalty term in the traditional exemplar based inpainting method to improve the performance of it.After combining the linear and curve structural features

we propose an exemplar and structure based inpainting algorithm for large scale missing regions in this paper.The new algorithm is easy to implement and the inpainted experimental results compared with some inpainting algorithms are plausible.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Dual-Stream Attention Image Inpainting Method Based on Interacting and Fusing Internal-External Features

Multi-Graph Learning Based on Structure-Aware

Anti-Noise Nonparallel Support Vector Machine with Margin Distribution

Recurrent Similarity Mapping Network Oriented to Laser Stripe Image Inpainting

Related Author

JIANG Xue-qin

ZHOU Shu-bo

HUANG Rong

HUANG Guang-yuan

FU Dong-lai

GAO Ze-an

CAI Hong-bin

CHU Mao-xiang

Related Institution

Engineering Research Center of Digitized Textile & Apparel Technology, Ministry of Education, Donghua University

College of Information Science and Technology, Donghua University

School of Software， North University of China

School of Electronic and Information Engineering， University of Science and Technology Liaoning

Department of Software, Beijing Jiaotong University

⁰