arXiv · 2010.02273
Single-Pixel Pattern Recognition with Coherent Nonlinear Optics
Abstract
We propose and experimentally demonstrate a nonlinear-optics approach to pattern recognition with single-pixel imaging and 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 nonlinear-optically. With 40 projection modes, the classification accuracy reaches a high value of 99.49% for the MNIST 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.
Explore related subjects
Keep this discovery
Ting Bu, Santosh Kumar, He Zhang, Irwin Huang, Yuping Huang. 2020-10-05. Single-Pixel Pattern Recognition with Coherent Nonlinear Optics. https://doi.org/10.1364/ol.411564
Cite the original work for its findings. Save a collection to share your selection of sources.