Blind image quality assessment based on transformer

Linxin Li; Chuzi Chen; Naixuan Zhao

doi:10.1117/12.2643493

12 October 2022 Blind image quality assessment based on transformer

Linxin Li, Chuzi Chen, Naixuan Zhao

Proceedings Volume 12342, Fourteenth International Conference on Digital Image Processing (ICDIP 2022); 123422U (2022) https://doi.org/10.1117/12.2643493
Event: Fourteenth International Conference on Digital Image Processing (ICDIP 2022), 2022, Wuhan, China

Abstract

Transformer has achieved milestones in natural language processing (NLP). Due to its excellent global and remote semantic information interaction performance, it has gradually been applied in vision tasks. In this paper, we propose PTIQ, which is a pure Transformer structure for Image Quality Assessment. Specifically, we use Swin Transformer Blocks as backbone to extract image features. The extracted feature vectors after extra state embedding and position embedding are fed into the original transformer encoder. Then, the output is passed to the MLP head to predict quality score. Experimental results demonstrate that the proposed architecture achieves outstanding performance.

Citation Download Citation

Linxin Li, Chuzi Chen, and Naixuan Zhao "Blind image quality assessment based on transformer", Proc. SPIE 12342, Fourteenth International Conference on Digital Image Processing (ICDIP 2022), 123422U (12 October 2022); https://doi.org/10.1117/12.2643493

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