订阅指南   |  广告服务
图学学报
  图形学与可视化 本期目录 | 过刊浏览 | 高级检索 |
基于显著结构重构与纹理合成的图像修复算法
摘 要:文章结合结构修复算法及纹理修复算法各自的优点,并考虑显著结构对#br# 图像修复的巨大影响,提出结合显著结构重构与纹理合成的图像修复算法。算法先利用形态#br# 学算子剥离待修复图像中细小结构与大块区域;然后利用快速结构修复算法对图像进行处#br# 理;再利用插值对待修复图像进行显著结构重构;最后利用基于改进优先级的加权匹配图像#br# 修复算法进行后续修复。实验结果表明,对既有显著结构同时又包含丰富纹理的待修复图像,#br# 与传统算法相比,本文的算法不但有更好的修复效果,而且耗时更少。#br# 关 键 词:图像修复;结构修复;纹理合成;形态学算子;显著结构;优先级
An Image Restoration Algorithm Based on Structure and Texture Synthesis with Reconstruction of Significant Structure of Images
Abstract: This paper presents an image restoration algorithm by integrating structure and#br# texture features with reconstruction of significant structure of images. Firstly, the algorithm splits#br# the fine structures and large areas in the damaged image using morphological operators. Secondly,#br# the rapid structural restoration algorithm is used for image inpainting. Thirdly, significant#br# structures in the image are reconstructed by interpolation. Finally, the large damaged areas are#br# restored by the weighted matching image restoration algorithm based on the modified priority. For#br# the damaged image with significant structure and texture, the experimental results show the better#br# restoration result and less time consuming of the proposed algorithm than that of the traditional#br# algorithms.#br# Key words: image restoration; structural restoration; texture synthesis; morphological#br# operators; significant structure; priority
版权所有 © 《图学学报》编辑部
地址:北京海淀学院路37号《图学学报》编辑部 邮编:100191
电话:010-82326420, E-mail:txb@cgn.net.cn txxb2011@163.com
本系统由北京玛格泰克科技发展有限公司设计开发  技术支持:support@magtech.com.cn