A non-iterative automated mechanism for image inpainting

Author

Zubair, Abdul R.

Author_Institution

Electr./Electron. Eng. Dept., Univ. of Ibadan, Ibadan, Nigeria

fYear

2011

fDate

24-26 Nov. 2011

Firstpage

193

Lastpage

199

Abstract

Portions of an image may be damaged or missing. Inpainting is required to recover the missing portions. Inpainting is cleaning off dirt, filling discolored sports, and repairing torn, warped, or cracked in a damaged image. The existing Navier-Stokes Partial Differential Equations (PDE) method for inpainting is iterative by nature, with a time variable serving as iteration parameter. For reasons of stability a large number of iterations can be needed which results in a computational complexity that is often too large for interactive image manipulation. A non-iterative automated mechanism for image inpainting is proposed. Colors are treated as fluid that flow or diffuse from the surrounding areas into the empty region. Gains ranging from 9.44 dB to 19.49 dB were obtained with the non-iterative automated inpainting scheme. The automated inpainting scheme overcomes the computational complexity associated with the existing Navier-Stokes PDE inpainting method, and is more suitable for interactive image manipulations.

Keywords

Navier-Stokes equations; computational complexity; image colour analysis; image restoration; iterative methods; Navier-Stokes partial differential equations; computational complexity; gain; image color; image inpainting; interactive image manipulation; iteration parameter; noniterative automated mechanism; Conferences; Filling; Gain; Image color analysis; Image restoration; PSNR; Propagation losses; Fluid Dynamics; Image Recovery; Inpainting; Interpolation; Restoration;

fLanguage

English

Publisher

ieee

Conference_Titel

Adaptive Science and Technology (ICAST), 2011 3rd IEEE International Conference

Conference_Location

Abuja

Print_ISBN

978-1-4673-0758-1

Type

conf

DOI

10.1109/ICASTech.2011.6145172

Filename

6145172