摘要
包裹相位是激光干涉测量获取相位信息的前提,为了减小测量过程中噪声对包裹相位条纹的干扰,提高重构图像的质量,提出了一种非对称融合非局部边缘提取神经网络(Asymmetric Fusion Non-Local and Verge Extraction Neural Network,AFNVENet)。该网络在FFDNet基础上,设计了非对称融合非局部块和边缘提取模块,通过融合不同级别噪声特征及反向引导去噪过程,在有效抑制多等级噪声的同时,保留了更多的图像细节信息。选择带有乘性散斑与加性随机噪声的包裹相位数据集用于训练,通过消融实验和对比实验结果表明,AFNVENet算法对不同等级的噪声都具有更好的噪声滤除效果,当噪声标准差在[0,2.0]范围内变化时,去噪后的PSNR、SSIM和SSI均值分别达到24.88 dB,0.97和0.95。此外,通过进一步解包裹结果表明,AFNVENet去噪后的解包裹相位均方根误差均值比SCAF,NLM,KSVD和DnCNN分别减小了87%,73%,79%和36%,验证了该方法的可行性。AFNVENet方法在抑制噪声时具有较好的鲁棒性,可适用于不同干涉测量环境下多等级噪声的包裹相位信息恢复。
The wrapped phase is a precondition for obtaining phase information in laser interferometry.In order to reduce the interference of noise in the wrapped phase fringe during measurement and improve the quality of reconstructed image,an asymmetric fusion non-local and verge extraction neural network(AFN⁃VENet)was proposed.The network was designed to add an asymmetric fusion non-local block and a verge extraction module based on FFDNet.By incorporating the noise features with different levels and re⁃verse-guiding the denoising process,it could effectively suppress the noise with different levels while re⁃taining more image details.The wrapped phase dataset with multiplicative speckle and additive random noise was selected to train.The results of ablation and comparative experiments show that AFNVENet al⁃gorithm has better noise filtering effect for different level noises.When the noise standard deviation chang⁃es in the range of[0,2.0],the means of PSNR,SSIM and SSI are 24.88 dB,0.97 and 0.95 after noise suppression,respectively.In addition,the unwrapped phase results further show that the RMSE mean of unwrapped phase denoised by AFNVENet is reduced by 87%,73%,79%and 36%,respectively,com⁃pared to SCAF,NLM,KSVD and DnCNN.The feasibility of method is verified.The AFNVENet method has better robustness in suppressing noises.It is suitable for recovering the wrapped phase informa⁃tion with multilevel noises in different interferometric environments.
作者
刘芸
吴晓强
康琦
薛锦锋
陈梦露
张碧轩
焦明星
邢俊红
LIU Yun;WU Xiaoqiang;KANG Qi;XUE Jinfeng;CHEN Menglu;ZHANG Bixuan;JIAO Mingxing;XING Junhong(School of Mechanical and Precision Instrument Engineering,Xi’an University of Technology,Xi'an 710048,China)
出处
《光学精密工程》
EI
CAS
CSCD
北大核心
2024年第14期2299-2310,共12页
Optics and Precision Engineering
基金
国家自然科学基金项目(No.61805195,No.51875455)
陕西省重点研发计划项目(No.2023-YBGY-400)
西安市科技计划项目(No.22GXFW0089)
西安理工大学硕士研究生创意创新种子基金项目(No.252082206)。
