基于未训练神经网络的分数傅里叶变换成像  

Fractional Fourier transform imaging based on untrained neural networks

作　　者：黄宇航 陈理想[1] HUANG Yuhang;CHEN Lixiang(Department of Physics,Xiamen University,Xiamen 361005,China;Institute of Artificial Intelligence,Xiamen University,Xiamen 361005,China)

机构地区：[1]厦门大学物理学系,福建厦门361005 [2]厦门大学人工智能研究院,福建厦门361005

出　　处：《物理实验》2025年第1期14-20,共7页Physics Experimentation

基　　金：国家自然科学基金重点项目(No.12034016);福建省自然科学基金项目(No.2021J02002)。

摘　　要：将未训练神经网络深度学习应用到分数傅里叶变换成像,通过将神经网络和光学模型相结合的方式完成分数傅里叶变换的相位恢复.数值仿真和光学实验证明,仅需2000次迭代,该网络框架就能完成不同阶数的分数傅里叶变换重建,包括强度物体和相位物体.因此,该网络框架为分数傅里叶变换的重建提供了新的方法.An untrained neural network for deep learning was applied to study fractional Fourier transform imaging,combining neural networks with optical models to achieve phase retrieval in the fractional Fourier transform.The numerical simulations and experiments had shown that the network framework could implement the fractional Fourier transform reconstructions of the intensity objects and phase objects for different fraction orders,in which only 2000 iterations were needed.Therefore,our work offered an efficient scheme for fractional Fourier transform reconstruction with physic-enhanced deep neutral network.

关 键 词：分数傅里叶变换 深度学习 神经网络 相位恢复 

分 类 号：O438.2[机械工程—光学工程]