Image Inpainting with Improved Exemplar-Based Approach

Autor:	Yuncai Liu, Qiang Chen, Yingxiang Zhang
Rok vydání:	2007
Předmět:	business.industry Computer science Inpainting Computer vision Pattern recognition Artificial intelligence business Image (mathematics) Texture synthesis
Zdroj:	Multimedia Content Analysis and Mining ISBN: 9783540734161 MCAM
Popis:	Image Inpainting is widely used to restore a damaged paintings and photographs or remove unwanted objects. Criminisi's exemplar-based inpainting combined "texture synthesis" and PDE-based inpainting that showed great efficiency on removal of large objects. However, this approach has certain weakness such as high time cost, visual inconsistency in some cases. In this paper, we improve the Criminsi's exemplar-based inpainting based on Search Strategy and Color Transfer. This new method is also suitable to all exemplar-based methods and the results show its effectiveness.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::41c9dd21b602cf23e7dac3ffa59c8d3e https://doi.org/10.1007/978-3-540-73417-8_31 Zobrazit plný text záznamu