Classification of optics-free images with deep neural networks

2020/11/10 by Nelson, Soren, Menon, Rajesh
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #FOS: Physical sciences #Image and Video Processing (eess.IV) #Optics (physics.optics) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2011.05132

Abstract

The thinnest possible camera is achieved by removing all optics, leaving only the image sensor. We train deep neural networks to perform multi-class detection and binary classification (with accuracy of 92%) on optics-free images without the need for anthropocentric image reconstructions. Inferencing from optics-free images has the potential for enhanced privacy and power efficiency.

Related

• Learning rich optical embeddings for privacy-preserving lensless image classification
• Optical Neural Networks
• Lensless computational imaging through deep learning
• Optics-free imaging of complex, non-sparse QR-codes with Deep Neural Networks
• Lensless-camera based machine learning for image classification