光学精密工程2025，Vol.33Issue(15)：2342-2353,12.DOI:10.37188/OPE.20253315.2342
全息环纹噪声的空频协同智能抑制
Intelligent spatial-frequency cooperative suppression of holographic ring noise
摘要
Abstract
In digital holographic imaging,ring noise produced by the diffraction of microscopic scatterers is nonlinearly amplified into structured phase errors during numerical reconstruction,thereby limiting the ac-curacy of quantitative phase imaging and three-dimensional reconstruction.While speckle-noise suppres-sion has been extensively studied,systematic theoretical modeling and targeted suppression strategies for ring noise remain underdeveloped.A novel convolutional neural network,FUResNet,is proposed to op-erate jointly in the spatial and frequency domains.A multi-scatterer diffraction-field superposition model is formulated to accurately simulate ring-noise formation.FUResNet integrates Fourier neural operators,a residual-learning architecture,and attention mechanisms to suppress ring noise efficiently while preserving essential holographic features with high fidelity.Experimental evaluation on simulated and experimental holograms demonstrates that FUResNet significantly outperforms existing approaches:background-noise standard deviation is reduced by 73.9%,peak signal-to-noise ratio(PSNR)is increased by 13.46 dB,and structural similarity index measure(SSIM)is improved by 13.9%.These improvements across noise suppression,image fidelity,and structural preservation indicate that FUResNet provides an effective solu-tion for high-accuracy quantitative phase imaging.关键词
数字全息/环纹噪声/相位成像/傅里叶神经算子/卷积神经网络Key words
digital holography/ring noise/phase imaging/fourier neural operator/convolutional neural network分类
机械制造引用本文复制引用
陈本永,熊壮,黄柳,张艳超,傅霞萍..全息环纹噪声的空频协同智能抑制[J].光学精密工程,2025,33(15):2342-2353,12.基金项目
国家自然科学基金资助项目(No.52035015) （No.52035015）
浙江省自然科学基金资助项目(No.LQ23E050020) （No.LQ23E050020）
