Abstract

In this Letter, we propose a fast speckle noise reduction method with only a single reconstructed image based on convolutional neural networks. The proposed network has multi-sized kernels that can capture the speckle noise component effectively from digital holographic images. For robust noise reduction performance, the network is trained with a large noisy image dataset that has object-dependent noise and a wide range of noise levels. The experimental results show the fast, robust, and outstanding speckle noise reduction performance of the proposed approach.

© 2018 Optical Society of America

Reduction of speckle noise in holographic images using spatial jittering in numerical reconstructions

Mohamed Haouat, Jorge Garcia-Sucerquia, Abdelhamid Kellou, and Pascal Picart
Opt. Lett. 42(6) 1047-1050 (2017)

Speckle noise suppression of a reconstructed image in digital holography based on the BM3D improved convolutional neural network

Yuan Chen, Yuhui Fan, Guangming Zhang, Quan Wang, Sitian Li, Zhongyang Wang, and Ming Dong
Appl. Opt. 63(22) 6000-6011 (2024)

Generalized optical signal-to-noise ratio monitoring using a convolutional neural network for digital coherent receivers

Hyung Joon Cho
Opt. Lett. 48(7) 1798-1801 (2023)

Adaptive frequency filtering based on convolutional neural networks in off-axis digital holographic microscopy

Wen Xiao, Qixiang Wang, Feng Pan, Runyu Cao, Xintong Wu, and Lianwen Sun
Biomed. Opt. Express 10(4) 1613-1626 (2019)

Speckle denoising based on Swin-UNet in digital holographic interferometry

Jie Chen, Houzhang Liao, Yong Kong, Dawei Zhang, and Songlin Zhuang
Opt. Express 32(19) 33465-33482 (2024)