Optical machine learning with incoherent light and a single-pixel detector

An optical diffractive neural network (DNN) can be implemented with a cascaded phase mask architecture. Like an optical computer, the system can perform machine learning tasks such as number digit recognition in an all-optical manner. However, the system can work only under coherent light illumination, and the precision requirement in practical experiments is quite high. This Letter proposes an optical machine learning framework based on single-pixel imaging (MLSPI). The MLSPI system can perform the same linear pattern recognition task as DNN. Furthermore, it can work under incoherent lighting conditions, has lower experimental complexity, and can be easily programmable.

[1]  孙鸣捷 Sun Mingjie,et al.  Single-pixel imaging and its application in three-dimensional reconstruction , 2019, Infrared and Laser Engineering.

[2]  Laura Waller,et al.  Data-Driven Design for Fourier Ptychographic Microscopy , 2019, 2019 IEEE International Conference on Computational Photography (ICCP).

[3]  Rafał Kotyński,et al.  Single-pixel imaging with sampling distributed over simplex vertices. , 2019, Optics letters.

[4]  N. Treps,et al.  Efficient and mode selective spatial mode multiplexer based on multi-plane light conversion , 2014, 2014 IEEE Photonics Conference.

[5]  Rafal Kotynski,et al.  Compressive phase-only filtering at extreme compression rates , 2016, 1604.07751.

[6]  Qionghai Dai,et al.  Experimental comparison of single-pixel imaging algorithms , 2017, Journal of the Optical Society of America. A, Optics, image science, and vision.

[7]  Zibang Zhang,et al.  Secured single-pixel broadcast imaging. , 2018, Optics express.

[8]  Yi Luo,et al.  All-optical machine learning using diffractive deep neural networks , 2018, Science.

[9]  D. Neilson,et al.  Laguerre-Gaussian mode sorter , 2018, Nature Communications.

[10]  Yong Wang,et al.  Orbital angular momentum detection based on diffractive deep neural network , 2019, Optics Communications.

[11]  Yibo Xu,et al.  Compressed Domain Image Classification Using a Dynamic-Rate Neural Network , 2020, IEEE Access.

[12]  Yoav Freund,et al.  Large Margin Classification Using the Perceptron Algorithm , 1998, COLT' 98.

[13]  Mingjie Sun,et al.  Motion estimation and quality enhancement for a single image in dynamic single-pixel imaging. , 2019, Optics express.

[14]  Guihua Zeng,et al.  Single-pixel non-imaging object recognition by means of Fourier spectrum acquisition , 2018 .

[15]  Xia Li,et al.  Review on Optical Image Hiding and Watermarking Techniques , 2018, Optics & Laser Technology.

[16]  Miles J. Padgett,et al.  Principles and prospects for single-pixel imaging , 2018, Nature Photonics.

[17]  Gordon Wetzstein,et al.  Hybrid optical-electronic convolutional neural networks with optimized diffractive optics for image classification , 2018, Scientific Reports.

[18]  Roland Vollgraf,et al.  Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms , 2017, ArXiv.

[19]  Hongbin Wang,et al.  Comment on All-optical machine learning using diffractive deep neural networks , 2018, ArXiv.

[20]  Yi Luo,et al.  Response to Comment on "All-optical machine learning using diffractive deep neural networks" , 2018, ArXiv.

[21]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[22]  Luc Van Gool,et al.  Multi-view traffic sign detection, recognition, and 3D localisation , 2014, Machine Vision and Applications.

[23]  Chenggong Zhang,et al.  Compressive optical steganography via single-pixel imaging. , 2019, Optics express.

[24]  FreundYoav,et al.  Large Margin Classification Using the Perceptron Algorithm , 1999 .

[25]  Enrique Tajahuerce,et al.  Online reconstruction-free single-pixel image classification , 2019, Image Vis. Comput..

[26]  Dong Liu,et al.  Fast tracking of moving objects using single-pixel imaging , 2019, Optics Communications.

[27]  Liu Dong,et al.  Radon single-pixel imaging with projective sampling. , 2019, Optics express.

[28]  Ming-Jie Sun,et al.  Single-Pixel Imaging and Its Application in Three-Dimensional Reconstruction: A Brief Review , 2019, Sensors.