Abstract

In this Letter, we propose and experimentally demonstrate a nonlinear-optics approach to pattern recognition with single-pixel imaging and a deep neural network. It employs mode-selective image up-conversion to project a raw image onto a set of coherent spatial modes, whereby its signature features are extracted optically in a nonlinear manner. With 40 projection modes, the classification accuracy reaches a high value of 99.49% for the Modified National Institute of Standards and Technology handwritten digit images, and up to 95.32%, even when they are mixed with strong noise. Our experiment harnesses rich coherent processes in nonlinear optics for efficient machine learning, with potential applications in online classification of large-size images, fast lidar data analyses, complex pattern recognition, and so on.

© 2020 Optical Society of America

Robust and efficient single-pixel image classification with nonlinear optics

Santosh Kumar, Ting Bu, He Zhang, Irwin Huang, and Yuping Huang
Opt. Lett. 46(8) 1848-1851 (2021)

Single-pixel image reconstruction using coherent nonlinear optics

Matthew Thomas, Santosh Kumar, and Yu-Ping Huang
Opt. Lett. 48(16) 4320-4323 (2023)

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

Shuming Jiao, Jun Feng, Yang Gao, Ting Lei, Zhenwei Xie, and Xiaocong Yuan
Opt. Lett. 44(21) 5186-5189 (2019)

Single-pixel sensing with optimal binarized modulation

Hao Fu, Liheng Bian, and Jun Zhang
Opt. Lett. 45(11) 3111-3114 (2020)

Reconfigurable all-optical nonlinear activation functions for neuromorphic photonics

Aashu Jha, Chaoran Huang, and Paul R. Prucnal
Opt. Lett. 45(17) 4819-4822 (2020)