{"title":"Image Completion and Its Application in Cultural Relic Preservation","authors":"Liping Liu, Haisheng Li","doi":"10.1109/CISP.2009.5304135","DOIUrl":null,"url":null,"abstract":"The restoration of damaged images or the removal of shielding materials in a given image is well known as image completion. An important method is the exemplar-based image completion, which propagates pixel information in the source region into the missing region. Firstly, we compute the filling priority of unknown pixels based on the color and structure information, and determine the patch whose center pixel has the highest priority. Then, find an optimal patch throughout the candidate region surrounding the missing region with SSD. Based on this method, this paper proposes an approach to address the balance problem between image completion quality and efficiency. In cultural relic preservation, our method can assist restorer to recover the damaged old pictures efficiently. The experimental results demonstrate this method can complete both texture and structure images in a visually pleasing manner. Keywords-Image completion; Missing region; Priority; Cultural relic preservation","PeriodicalId":263281,"journal":{"name":"2009 2nd International Congress on Image and Signal Processing","volume":"31 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2009-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2009 2nd International Congress on Image and Signal Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CISP.2009.5304135","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
The restoration of damaged images or the removal of shielding materials in a given image is well known as image completion. An important method is the exemplar-based image completion, which propagates pixel information in the source region into the missing region. Firstly, we compute the filling priority of unknown pixels based on the color and structure information, and determine the patch whose center pixel has the highest priority. Then, find an optimal patch throughout the candidate region surrounding the missing region with SSD. Based on this method, this paper proposes an approach to address the balance problem between image completion quality and efficiency. In cultural relic preservation, our method can assist restorer to recover the damaged old pictures efficiently. The experimental results demonstrate this method can complete both texture and structure images in a visually pleasing manner. Keywords-Image completion; Missing region; Priority; Cultural relic preservation