Image inpainting using multiresolution wavelet transform analysis

2012 International Conference on Communication, Information & Computing Technology (ICCICT) Pub Date : 2012-12-31 DOI:10.1109/ICCICT.2012.6398156

A. Deshmukh, P. Mukherji

{"title":"Image inpainting using multiresolution wavelet transform analysis","authors":"A. Deshmukh, P. Mukherji","doi":"10.1109/ICCICT.2012.6398156","DOIUrl":null,"url":null,"abstract":"Digital image processing technique can be applied to virtual restoration of artistic paintings. This paper introduced a method for the restoration of digitized paintings which is based on wavelet transformation analysis. Initially the given image gets separated into two principal components which encompass image texture and image color, respectively. Then, using multiresolution characteristics of wavelet transform, from the lowest spatial-frequency layer to the higher one, the image is analyzed from global-area to local-area progressively. Then, variance of the energy of wavelet coefficients within each image block is used to decide the priority of inpainting blocks. Final step is to extract the multi-resolution features of each block. The correlation among horizontal, vertical and diagonal directions are considered, to determine the inpainting strategy for filling image pixels and approximate high-quality image inpainting to human vision. This method can be used for a variety of input images that exhibit different kinds of defects.","PeriodicalId":319467,"journal":{"name":"2012 International Conference on Communication, Information & Computing Technology (ICCICT)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2012-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2012 International Conference on Communication, Information & Computing Technology (ICCICT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCICT.2012.6398156","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 6

Abstract

Digital image processing technique can be applied to virtual restoration of artistic paintings. This paper introduced a method for the restoration of digitized paintings which is based on wavelet transformation analysis. Initially the given image gets separated into two principal components which encompass image texture and image color, respectively. Then, using multiresolution characteristics of wavelet transform, from the lowest spatial-frequency layer to the higher one, the image is analyzed from global-area to local-area progressively. Then, variance of the energy of wavelet coefficients within each image block is used to decide the priority of inpainting blocks. Final step is to extract the multi-resolution features of each block. The correlation among horizontal, vertical and diagonal directions are considered, to determine the inpainting strategy for filling image pixels and approximate high-quality image inpainting to human vision. This method can be used for a variety of input images that exhibit different kinds of defects.

查看原文本刊更多论文

基于多分辨率小波变换分析的图像绘制

数字图像处理技术可以应用于艺术绘画的虚拟修复。介绍了一种基于小波变换分析的数字化绘画复原方法。首先，给定的图像被分成两个主要成分，分别包含图像纹理和图像颜色。然后，利用小波变换的多分辨率特性，从最低的空频层到较高的空频层，对图像进行从全局到局部的逐级分析。然后，利用每个图像块内小波系数能量的方差来确定图像块的优先级。最后一步是提取每个块的多分辨率特征。考虑了水平方向、垂直方向和对角线方向之间的相关性，确定了填充图像像素的补图策略，使高质量的图像补图接近人类视觉。该方法可用于显示不同类型缺陷的各种输入图像。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

2012 International Conference on Communication, Information & Computing Technology (ICCICT)

自引率

0.00%

发文量