Title
High-speed texture-preserving digital image inpainting
Abstract
Automatic image in-painting is a process that attempts to automatically restore flaws in digitized images. The objective is to automatically fill in missing data simulating results achieved manually by professional painting restorators. Inpainting can be employed to remove objects as well as text, but more importantly to repair imperfections in images and scanned photographs. In this paper we present a novel inpainting algorithm which improves upon previous work by significantly reducing the time required to inpaint an image, yet providing improved visual results as well. Furthermore, our algorithm works well on larger restoration areas by estimating a functional view of texture and therefore maintains the texture in the in-painted regions.
Year
Venue
Keywords
2005
Seventh IASTED International Conference on Signal and Image Processing
image processing,image inpainting,image restoration,image quality
Field
DocType
Citations 
Computer vision,Image gradient,Computer science,Image texture,Binary image,Image processing,Digital image,Artificial intelligence,Image restoration,Digital image processing,Color image
Conference
0
PageRank 
References 
Authors
0.34
1
3
Name
Order
Citations
PageRank
Anthony Whitehead114320.84
Prosenjit K. Bose22336293.75
Veronique Audet300.34