Title :
An image inpainting approach based on the Poisson equation
Author :
Shao, Xiaowei ; Liu, Zhengkai ; Li, Houqiang
Author_Institution :
Dept. of Electron. Eng. & Inf. Sci., Univ. of Sci. & Technol. of China
Abstract :
A novel algorithm is proposed for inpainting digital images based on the Poisson equation. In this method, the image to be repaired is decomposed into the structure image and the texture image, which are processed respectively according to their image characteristics. The texture image is repaired by the exemplar-based method; for the structure image, the Laplacian operator is employed to enhance the structure information, and the Laplacian image is inpainted by the exemplar-based algorithm, followed by a reconstruction based on the Poisson equation. The inpainting result is obtained by adding back these two sub-images. Experiments show the proposed algorithm provides a better visual effect, especially for large area inpainting
Keywords :
Poisson equation; image reconstruction; image texture; Laplacian operator; Poisson equation; digital images; exemplar-based method; image inpainting; image reconstruction; structure image; texture image; Digital images; Dynamic programming; Image edge detection; Image reconstruction; Image restoration; Information science; Laplace equations; Poisson equations; Statistical learning; Visual effects;
Conference_Titel :
Document Image Analysis for Libraries, 2006. DIAL '06. Second International Conference on
Conference_Location :
Lyon
Print_ISBN :
0-7695-2531-8
DOI :
10.1109/DIAL.2006.3