Computational ghost imaging using deep learning

Abstract

Computational ghost imaging (CGI) is a single-pixel imaging technique that exploits the correlation between known random patterns and the measured intensity of light transmitted (or reflected) by an object. Although CGI can obtain two- or three- dimensional images with a single or a few bucket detectors, the quality of the reconstructed images is reduced by noise due to the reconstruction of images from random patterns. In this study, we improve the quality of CGI images using deep learning. A deep neural network is used to automatically learn the features of noise-contaminated CGI images. After training, the network is able to predict low-noise images from new noise-contaminated CGI images.

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• Normalized Ghost Imaging
• Ghost imaging lidar via sparsity constraints
• Single-pixel digital "ghost" holography
• Computational wave optics library for C++: CWO++ library

Cited by in corpus (17)

• Image-free real-time classification of fast moving objects using 'learned' spatial light modulation and a single-pixel detector
• Computational Imaging and Artificial Intelligence: The Next Revolution of Mobile Vision
• Does deep learning always outperform simple linear regression in optical imaging?
• On Random-Matrix Bases, Ghost Imaging and X-ray Phase Contrast Computational Ghost Imaging
• A Two-step-training Deep Learning Framework for Real-time Computational Imaging without Physics Priors
• Ghost imaging based on Y-net: a dynamic coding and conjugate-decoding approach
• Deep Hybrid Scattering Image Learning
• Ghost Imaging Based on Recurrent Neural Network
• Optimal Physical Preprocessing for Example-Based Super-Resolution
• 0.8% Nyquist computational ghost imaging via non-experimental deep learning
• Res-U2Net: Untrained Deep Learning for Phase Retrieval and Image Reconstruction
• Multi-wavelength ghost imaging: a review
• Temporal phase unwrapping using deep learning
• Deep-learning-driven Reliable Single-pixel Imaging with Uncertainty Approximation
• Design of optimal illumination patterns in single-pixel imaging using image dictionaries
• True color night vision correlated imaging based on intensity correlation of light
• Computational ghost imaging using a field-programmable gate array