Image Inpainting Algorithm Based on Partial Differential Equation

Author

Xu, Zhongyu ; Lian, Xiaoli ; Feng, Lili

Author_Institution

Sch. of Comput. Sci. &Eng., Changchun Univ. of Technol., Changchun

Volume

1

fYear

2008

fDate

3-4 Aug. 2008

Firstpage

120

Lastpage

124

Abstract

Image inpainting technique has been widely used for reconstructing damaged old photographs and removing unwanted objects from images. Now many inpainting algorithm performs well, but they consume much time. In this paper we present a new algorithm based on partial differential equation (PDE) method. This model we called quick curvature-driven diffusions(QCDD) which can get good effect with much less computation time.QCDD model is developed by the curvature-driven diffusions(CDD) model, both of the two models is supported by "connectivity and holistic principle," our experiment shows that the model is feasible.

Keywords

edge detection; image reconstruction; partial differential equations; connectivity principle; curvature-driven diffusions; holistic principle; image inpainting algorithm; partial differential equation; quick curvature-driven diffusions; Communication system control; Computer vision; Digital images; Image processing; Image restoration; Information geometry; Mathematical model; Partial differential equations; TV; Technology management;

fLanguage

English

Publisher

ieee

Conference_Titel

Computing, Communication, Control, and Management, 2008. CCCM '08. ISECS International Colloquium on

Conference_Location

Guangzhou

Print_ISBN

978-0-7695-3290-5

Type

conf

DOI

10.1109/CCCM.2008.89

Filename

4609482