Robust and efficient single-pixel image classification with nonlinear optics

We present a hybrid image classifier by feature-sensitive image upconversion, single pixel photodetection, and deep learning, aiming at fast processing of high-resolution images. It uses partial Fourier transform to extract the images' signature features in both the original and Fourier domains, thereby significantly increasing the classification accuracy and robustness. Tested on the Modified National Institute of Standards and Technology handwritten digit images and verified by simulation, it boosts accuracy from 81.25% (by Fourier-domain processing) to 99.23%, and achieves 83% accuracy for highly contaminated images whose signal-to-noise ratio is only -17 dB. Our approach could prove useful for fast lidar data processing, high-resolution image recognition, occluded target identification, and atmosphere monitoring. (C) 2021 Optical Society of America

Automated summary

A hybrid image classifier utilizing feature-sensitive image upconversion, single pixel photodetection, and deep learning is proposed in this study for fast processing of high-resolution images. The classifier improves classification accuracy and robustness by using partial Fourier transform to extract signature features in both the original and Fourier domains. Test results show significant accuracy enhancement, especially for highly contaminated images with low signal-to-noise ratio. This approach holds potential for applications in fast lidar data processing, high-resolution image recognition, occluded target identification, and atmosphere monitoring.