{"title":"一种基于并行投影法的图像绘制技术","authors":"Irina Maria Artinescu, C. Boldea","doi":"10.1109/SYNASC.2018.00027","DOIUrl":null,"url":null,"abstract":"We propose in this paper a new method of image reconstruction by inpainting small pattern over a damaged scratch, using a variant of the parallel projection method (PPM) for solving the convex feasibility problem. The method is based on a fragmentation of the damaged region in small quadrilaterals and reconstruct the image by filling the scratch with PPM generated pattern. The algorithm is fast and directly parallelizable.","PeriodicalId":273805,"journal":{"name":"2018 20th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"An Image Inpainting Technique Based on Parallel Projection Methods\",\"authors\":\"Irina Maria Artinescu, C. Boldea\",\"doi\":\"10.1109/SYNASC.2018.00027\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We propose in this paper a new method of image reconstruction by inpainting small pattern over a damaged scratch, using a variant of the parallel projection method (PPM) for solving the convex feasibility problem. The method is based on a fragmentation of the damaged region in small quadrilaterals and reconstruct the image by filling the scratch with PPM generated pattern. The algorithm is fast and directly parallelizable.\",\"PeriodicalId\":273805,\"journal\":{\"name\":\"2018 20th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)\",\"volume\":\"57 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 20th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SYNASC.2018.00027\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 20th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SYNASC.2018.00027","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
An Image Inpainting Technique Based on Parallel Projection Methods
We propose in this paper a new method of image reconstruction by inpainting small pattern over a damaged scratch, using a variant of the parallel projection method (PPM) for solving the convex feasibility problem. The method is based on a fragmentation of the damaged region in small quadrilaterals and reconstruct the image by filling the scratch with PPM generated pattern. The algorithm is fast and directly parallelizable.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
