计算机应用研究2018，Vol.35Issue(4)：1274-1276,1280,4.DOI:10.3969/j.issn.1001-3695.2018.04.068
基于样本块与曲率特征的图像修复改进算法
Improved algorithm for image inpainting based on sample block and curvature features
摘要
Abstract
At present,the image inpainting algorithm based on sample block is easy to produce false matching texture blocks in the process of repair.Besides,it is difficult to maintain the texture coherence.In order to address this kind of problem,this paper proposed an improved image inpainting algorithm,which combined curvature characteristic of the isophotes and Gaussian function.First of all,it introduced curvature factor reflecting the texture feature to calculate the priority in the data term.Besides,it used Gaussian function into the confidence term updating to avoid error matching in the process of image inpainting due to the rapid decline of confidence term.Compared with other algorithms,simulation results show that the proposed algorithm has a better effect on the image which contains rich texture information according to the value of PSNR.关键词
图像修复/曲率特征/优先权公式/非线性模型/置信项Key words
image inpainting/curvature feature/priority function/nonlinear mode/confidence term分类
信息技术与安全科学引用本文复制引用
黄颖,李凯,杨明..基于样本块与曲率特征的图像修复改进算法[J].计算机应用研究,2018,35(4):1274-1276,1280,4.基金项目
重庆市教委科学技术研究资助项目(kJ1400408) （kJ1400408）
2015年重庆市研究生科研创资助新项目(cs15174) （cs15174）
重庆市基础与前沿研究计划资助项目(cstc2014jcyjA40043) （cstc2014jcyjA40043）
