{"title":"A Novel Exemplar-Based Image Inpainting Algorithm","authors":"Y. Liu, Chanjuan Liu, Hailin Zou, Shusen Zhou, Qian Shen, Tongtong Chen","doi":"10.1109/INCoS.2015.15","DOIUrl":null,"url":null,"abstract":"A novel exemplar-based image inpainting algorithm is proposed for solving the deficiencies of the classical Criminisi method, such as the error repair accumulation, high time complexity caused by the unreasonable design of the patch priority, inaccuracy criterion and its global search strategy. Thus, we construct a local structure measurement function by introducing the structure tensor theory, and optimize the means of patch priority. On that basis, we design a matching criterion. Experiments show that the improved algorithm has greater advantages on the fidelity of image structure compared with the Criminisi method. Besides, the improved algorithm makes progresses in both subjective visual effect and objective indexes, such as peak signal-to-noise ratio (PSNR), repair error and the running time compared with some of the typical image restoration algorithms proposed recent years.","PeriodicalId":345650,"journal":{"name":"2015 International Conference on Intelligent Networking and Collaborative Systems","volume":"44 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 International Conference on Intelligent Networking and Collaborative Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/INCoS.2015.15","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 8
Abstract
A novel exemplar-based image inpainting algorithm is proposed for solving the deficiencies of the classical Criminisi method, such as the error repair accumulation, high time complexity caused by the unreasonable design of the patch priority, inaccuracy criterion and its global search strategy. Thus, we construct a local structure measurement function by introducing the structure tensor theory, and optimize the means of patch priority. On that basis, we design a matching criterion. Experiments show that the improved algorithm has greater advantages on the fidelity of image structure compared with the Criminisi method. Besides, the improved algorithm makes progresses in both subjective visual effect and objective indexes, such as peak signal-to-noise ratio (PSNR), repair error and the running time compared with some of the typical image restoration algorithms proposed recent years.