Image inpainting method based sparse analysis model of synchronous dictionary learning

Bin Li; Baohua Sun; Dekun Li; Tong Jiang; Gang Li; Hao Li

doi:10.1117/12.2617933

11 November 2021 Image inpainting method based sparse analysis model of synchronous dictionary learning

Bin Li, Baohua Sun, Dekun Li, Tong Jiang, Gang Li, Hao Li

Proceedings Volume 12076, 2021 International Conference on Image, Video Processing, and Artificial Intelligence; 120760K (2021) https://doi.org/10.1117/12.2617933
Event: Fourth International Conference on Image, Video Processing, and Artificial Intelligence (IVPAI 2021), 2021, Shanghai, China

Abstract

A novel image inpainting algorithm based on sparse analysis model is proposed. The model is formulated on an analysis dictionary. The dictionary is updated using a least-squares method. The experiments on images demonstrate improved performance in peak signal to noise ratio (PSNR) compared to other image inpainting methods including AMLE Inpainting, Harmonic Inpainting, Mumford-Shah Inpainting, and Transport Inpainting algorithm. The evaluation results showed that our proposed algorithm has better performance.

Citation Download Citation

Bin Li, Baohua Sun, Dekun Li, Tong Jiang, Gang Li, and Hao Li "Image inpainting method based sparse analysis model of synchronous dictionary learning", Proc. SPIE 12076, 2021 International Conference on Image, Video Processing, and Artificial Intelligence, 120760K (11 November 2021); https://doi.org/10.1117/12.2617933

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