Gaussian denoising in spatial heterodyne interferograms by convolutional neural network

Wei Luo; Song Ye; Ziyang Zhang; Shuang Liu

doi:10.1117/12.3014262

29 December 2023 Gaussian denoising in spatial heterodyne interferograms by convolutional neural network

Wei Luo, Song Ye, Ziyang Zhang, Shuang Liu

Proceedings Volume 12975, 6th Optics Young Scientist Summit (OYSS 2023); 1297505 (2023) https://doi.org/10.1117/12.3014262
Event: 6th Optics Young Scientist Summit, 2023, Changsha, China

Abstract

Spatial heterodyne spectral technology is a hyperspectral remote sensing technique. With the improvement in detection accuracy, new demands have emerged for denoising methods in spatial heterodyne interferograms. Convolutional neural networks (CNNs) is a currently hot research topic. they have unique advantages in extracting abstract features from data. In recent years, CNNs have demonstrated outstanding performance in the field of image denoising. In this paper, we construct a Spatial heterodyne interferograms denoise CNN(SHI-DnCNN) using batch normalization and residual learning. We utilize the trained SHI-DnCNN to denoise spatial heterodyne interferograms contaminated with Gaussian noise. The results show that SHI-DnCNN exhibits excellent Gaussian noise denoising capability for spatial heterodyne interferograms. Furthermore, we evaluate the denoising results using PSNR, SSIM, and residual spectra, further confirming the superior denoising performance of SHI-DnCNN. This work provides a new and effective solution for denoising spatial heterodyne interferograms.

Citation Download Citation

Wei Luo, Song Ye, Ziyang Zhang, and Shuang Liu "Gaussian denoising in spatial heterodyne interferograms by convolutional neural network", Proc. SPIE 12975, 6th Optics Young Scientist Summit (OYSS 2023), 1297505 (29 December 2023); https://doi.org/10.1117/12.3014262

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