Classification of optics-free images with deep neural networks

11/10/2020

∙

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 images without the need for anthropocentric image reconstructions. Inferencing from optics-free images has the potential for enhanced privacy and power efficiency.

READ FULL TEXT

Classification of optics-free images with deep neural networks

A needle-based deep-neural-network camera

Single neuron-based neural networks are as efficient as dense deep neural networks in binary and multi-class recognition problems

BrazilDAM: A Benchmark dataset for Tailings Dam Detection

Uncertainty-aware deep learning methods for robust diabetic retinopathy classification

Sex-Prediction from Periocular Images across Multiple Sensors and Spectra

Virtual impactor-based label-free bio-aerosol detection using holography and deep learning

Biologically-primed deep neural network improves colorectal Cancer Molecular subtypes prediction from H E stained images

Classification of optics-free images with deep neural networks

Related Research

A needle-based deep-neural-network camera

Single neuron-based neural networks are as efficient as dense deep neural networks in binary and multi-class recognition problems

BrazilDAM: A Benchmark dataset for Tailings Dam Detection

Uncertainty-aware deep learning methods for robust diabetic retinopathy classification

Sex-Prediction from Periocular Images across Multiple Sensors and Spectra

Virtual impactor-based label-free bio-aerosol detection using holography and deep learning

Biologically-primed deep neural network improves colorectal Cancer Molecular subtypes prediction from H E stained images