A comparison of image inpainting techniques

Yaojie Liu; Chang Shu

doi:10.1117/12.2178820

4 March 2015 A comparison of image inpainting techniques

Yaojie Liu, Chang Shu

Proceedings Volume 9443, Sixth International Conference on Graphic and Image Processing (ICGIP 2014); 94431M (2015) https://doi.org/10.1117/12.2178820
Event: Sixth International Conference on Graphic and Image Processing (ICGIP 2014), 2014, Beijing, China

Abstract

Image inpainting is an important research topic in the field of image processing. The objective of inpainting is to “guess” the lost information according to surrounding image information, which can be applied in old photo restoration, object removal and demosaicing. Based on the foundation of previous literature of image inpainting and image modeling, this paper provides an overview of the state-of-art image inpainting methods. This survey first covers mathematics models of inpainting and different kinds of image impairment. Then it goes to the main components of an image, the structure and the texture, and states how these inpainting models and algorithms deal with the two separately, using PDE’s method, exemplar-based method and etc. Afterwards sparse-representation-based inpainting and related techniques are introduced. Experimental analysis will be presented to evaluate the relative merits of different algorithms, with the measure of Peak Signal to Noise Ratio (PSNR) as well as direct visual perception.

Citation Download Citation

Yaojie Liu and Chang Shu "A comparison of image inpainting techniques", Proc. SPIE 9443, Sixth International Conference on Graphic and Image Processing (ICGIP 2014), 94431M (4 March 2015); https://doi.org/10.1117/12.2178820

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available