Image inpainting based on priority values

Jiang Cao; Jingdong Du; Dafang Wang

doi:10.1117/12.2605955

15 September 2021 Image inpainting based on priority values

Jiang Cao, Jingdong Du, Dafang Wang

Proceedings Volume 11915, International Conference on Optics and Image Processing (ICOIP 2021); 119150L (2021) https://doi.org/10.1117/12.2605955
Event: International Conference on Optics and Image Processing (ICOIP 2021), 2021, Guilin, China

Abstract

Image inpainting is a means of inferring the content of the missing information based on the remaining information of the image, and inpainting the missing information, requiring the inpainted image to meet the human eye perception to the greatest extent. The image inpainting method based on the weight function takes arbitrary points for inpainting during inpainting, which results in poor inpainting effect at the junction of objects. Therefore, this paper adds the priority values calculation of inpainting points to improve the inpainting effect. Finally, comparing the inpainted image based on the priority calculation with the previous one, the inpainting effect at the boundary of the object is significantly better than the image inpainting method based solely on the weight functions.

Citation Download Citation

Jiang Cao, Jingdong Du, and Dafang Wang "Image inpainting based on priority values", Proc. SPIE 11915, International Conference on Optics and Image Processing (ICOIP 2021), 119150L (15 September 2021); https://doi.org/10.1117/12.2605955

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