Classification of optics-free images with deep neural networks

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.

References in corpus (7)

• How transferable are features in deep neural networks?
• A systematic study of the class imbalance problem in convolutional neural networks
• Metalenses at visible wavelengths: past, present, perspectives
• Lensless Photography with only an image sensor
• Inverse-designed flat lens for imaging in the visible & near-infrared with diameter > 3mm and NA=0.3
• Anomaly Detection in Images
• Lensless-camera based machine learning for image classification