基于MRF的各向异性图像修复模型

¹河海大学测绘科学与工程系,南京市西康路1号210098;²南京信息工程大学遥感学院,南京市浦口区盘城新街114号210044;³中国科学院光电研究院,北京市海淀区中关村东路95号100190

基金项目: 国家自然科学基金资助项目(40701103,40801177)；河海大学中央高校基本科研业务经费资助项目(2009B12114)

详细信息

Anisotropic Image Inpainting Model Based on MRF

¹College of Earth Science and Engineering,Hohai University,1 Xikang Road,Nanjing 210098,China;²School of Remote Sensing,Nanjing University of Information Science & Technology,114 New Pancheng Street,Pukou District,Nanjing 210044,China;³Academy of Opto-Electronics,Chinese Academy of Sciences,95 East Zhongguancun Road,Beijing 100190,China

Funds: 国家自然科学基金资助项目(40701103,40801177)；河海大学中央高校基本科研业务经费资助项目(2009B12114)

摘要: 针对图像上划痕等小区域的恢复问题,提出了一种顾及边缘的各向异性马尔可夫随机场修复模型,并采用模拟退火算法实现解算。对不同类型的图像进行了修复实验,获得了较好的修复效果。
- 马尔可夫随机场 /
- 图像修复 /
- 模拟退火 /
- 各向异性
Abstract: The goal of image inpainting is to restore the damaged or missing pixels on images and now it is a hot-point research topic in image engineering.In order to restore narrow gaps on damaged images,we propose a type of anisotropic inpainting model based on Markov Random Fields.The inpainting model can preserve the edged and orientational texture and we implement our method using Simulated Annealing algorithm.Experiments show that the proposed method can obtain good results and is practical in applications.
- Markov random fields /
- image inpainting /
- simulated annealing /
- anisotropic