Research on nonuniformity correction based on deep learning

Sifan Zhang; Xiubao Sui; Zheyi Yao; Guohua Gu; Qian Chen

doi:10.1117/12.2603263

24 November 2021 Research on nonuniformity correction based on deep learning

Sifan Zhang, Xiubao Sui, Zheyi Yao, Guohua Gu, Qian Chen

Proceedings Volume 12061, AOPC 2021: Infrared Device and Infrared Technology; 120610G (2021) https://doi.org/10.1117/12.2603263
Event: Applied Optics and Photonics China 2021, 2021, Beijing, China

Abstract

Given that the existing nonuniformity correction algorithms still struggle to achieve low noise images, good real-time performance, and more texture details, a shearlet deep neural network from the perspective of transforming domain is put forward in the paper. The proposed method uses the non-subsampled shearlet transform to track the stripe noise. And then defines the regularization method according to the features extracted by the shearlet to help restore the image details. The experiments based on simulation datasets and real datasets show that the proposed method is superior to several classical denoising algorithms in quantitative and qualitative evaluation.

Citation Download Citation

Sifan Zhang, Xiubao Sui, Zheyi Yao, Guohua Gu, and Qian Chen "Research on nonuniformity correction based on deep learning", Proc. SPIE 12061, AOPC 2021: Infrared Device and Infrared Technology, 120610G (24 November 2021); https://doi.org/10.1117/12.2603263

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