Title :
Improved image inpainting using maximum value edge detector
Author :
De, Chandralekha ; Shih, Frank Y.
Author_Institution :
Dept. of Comput. Sci., New Jersey Inst. of Technol., Newark, NJ, USA
Abstract :
Image inpainting is a novel method to repair damaged images. In this paper, an improved edge operator is proposed to calculate the structure priority value for determining the order of filling in an image. We use a maximum value edge operator which refines the number of edge pixels detected accurately as opposed to the existing method which relies on a single edge operator and in many cases may not provide the best output. An improvement in accuracy for edge detection thereby improves the quality of the inpainting method.
Keywords :
edge detection; image reconstruction; edge detection; image inpainting; maximum value edge detector; single edge operator; structure priority value calculation; Decision support systems; inpainting; texture;
Conference_Titel :
Image Analysis and Interpretation (SSIAI), 2012 IEEE Southwest Symposium on
Conference_Location :
Santa Fe, NM
Print_ISBN :
978-1-4673-1831-0
Electronic_ISBN :
978-1-4673-1829-7
DOI :
10.1109/SSIAI.2012.6202457
