微透镜阵列光学实现卷积运算  

Optically realize convolution operation of microlens array

作　　者：费宇航 隋修宝[1] 王庆宝[1] 陈钱[1] 顾国华[1] Fei Yuhang;Sui Xiubao;Wang Qingbao;Chen Qian;Gu Guohua(School of Electronic and Optical Engineering,Nanjing University of Science and Technology,Nanjing 210094,China)

机构地区：[1]南京理工大学电子工程与光电技术学院,江苏南京210094

出　　处：《红外与激光工程》2022年第2期417-422,共6页Infrared and Laser Engineering

基　　金：国家自然科学基金(11773018);江苏省研究生科研与实践创新计划项目(SJCX21_0112)。

摘　　要：卷积作为一种简单的线性平移不变运算,被广泛应用于图像处理的各个领域,其衍生出的卷积神经网络更是在人工智能领域中大放异彩。为了应对后摩尔时代AI推理芯片算力受限的问题,光学神经网络应运而生。光学卷积神经网络作为其中一个重要的研究热点对光学神经网络的发展起到了重要的推动作用。设计了一种光学卷积系统,基于微透镜阵列与透镜组成的匀光光路对光场所携带的图像做二维卷积,该系统可以光学实现图像平滑和锐化。当使用空间光调制器来投影卷积核和输入图像时,系统可以实现各种步长的三种卷积形式,也可以通过多次投影/平铺实现多通道的三维卷积,进而为实现光学卷积神经网络用于复杂的图像处理任务奠定基础。As a simple linear translation invariant operation,convolution has been widely used in various fields of image processing,and the convolutional neural network derived from it is brilliant in the field of artificial intelligence.In order to deal with the problem of limited computing power of AI reasoning chip in the post-Moore era,optical neural network came into being.As one of the important research hotspots,optical convolutional neural network plays an important role in promoting the development of optical neural network.An optical convolution system was designed,based on the uniform light path formed by micro lens array and lens,the image carried in the light place was convoluted in two-dimensions.The system can complete simple image smoothing and sharpening in the optical path.When the spatial light modulator is used to realize the convolution kernel and input surface,the system can realize three convolution forms of various step sizes,and can also realize multichannel three-dimensional convolution through multiple projection or flattening,thus laying a foundation for the realization of optical convolution neural network for complex image processing tasks.

关 键 词：光学卷积 微透镜阵列 匀光系统 图像处理 

分 类 号：O439[机械工程—光学工程]