Title :
A New Fourth-order Equation Model for Image Inpainting
Author :
Chen, Peiying ; Wang, Yuandi
Author_Institution :
Dept. of Math., Shanghai Univ., Shanghai, China
Abstract :
PDE-based (partial differential equations) image inpainting is an important research topic in the area of image restoration. Its objective is restore the lost information according to around image information in a way that looks natural for the eye. In this paper, guided by the an isotropic diffusion principle and the connectivity principle of human visual perception, we put forward a novel nonlinear PDE inpainting model. The procedure allows for the transporting and diffusing of image information simultaneously. That is, the approach here displayed permits the transportation of available information from the outside towards inside of the inpainting domain and the diffusion of the inside information in the inpainting domain at the same time. Both theoretical analysis and experiments have verified the validity of the method proposed in the paper.
Keywords :
image restoration; nonlinear differential equations; partial differential equations; visual perception; connectivity principle; fourth-order equation model; human visual perception; image inpainting; image restoration; isotropic diffusion principle; nonlinear partial differential equations inpainting model; Anisotropic magnetoresistance; Differential equations; Digital images; Fuzzy systems; Image reconstruction; Image restoration; Mathematical model; Mathematics; Navier-Stokes equations; Pixel; image inpainting; interpolation; partial difference equation;
Conference_Titel :
Fuzzy Systems and Knowledge Discovery, 2009. FSKD '09. Sixth International Conference on
Conference_Location :
Tianjin
Print_ISBN :
978-0-7695-3735-1
DOI :
10.1109/FSKD.2009.201