Single-Pixel Pattern Recognition with Coherent Nonlinear Optics
arXiv:2010.02273 · doi:10.1364/OL.411564
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.
5 pages, 5 figures
References in corpus (15)
- All-Optical Machine Learning Using Diffractive Deep Neural Networks
- Deep Learning Microscopy
- Deep-STORM: super-resolution single-molecule microscopy by deep learning
- All Optical Neural Network with Nonlinear Activation Functions
- Large-Scale Optical Neural Networks based on Photoelectric Multiplication
- Low Photon Count Phase Retrieval Using Deep Learning
- Machine learning-based classification of vector vortex beams
- Optical machine learning with incoherent light and a single-pixel detector
- Polaritonic neuromorphic computing outperforms linear classifiers
- Image-free real-time classification of fast moving objects using 'learned' spatial light modulation and a single-pixel detector
- Deep learning reconstruction of ultrashort pulses from 2D spatial intensity patterns recorded by an all-in-line system in a single-shot
- Mode-selective Image Upconversion
- A Super-resolution Optical Classifier with High Photon Efficiency
- Toward a Thinking Microscope: Deep Learning in Optical Microscopy and Image Reconstruction
- Mode Selective Image Upconversion over Turbulence