1,161 Hits in 3.3 sec

Astronomical image reconstruction with convolutional neural networks [article]

Rémi Flamary
2017 arXiv   pre-print
We investigate in this work the use of convolutional neural networks for image reconstruction in astronomy.  ...  State of the art methods in astronomical image reconstruction rely on the resolution of a regularized or constrained optimization problem.  ...  CONVOLUTIONAL NEURAL NETWORK FOR IMAGE RECONSTRUCTION A.  ... 
arXiv:1612.04526v2 fatcat:o6c65ujpnjhkrgtracxbzexq24

Astronomical Image Reconstruction With Convolutional Neural Networks

Rémi Flamary
2018 Zenodo  
CONVOLUTIONAL NEURAL NETWORK FOR IMAGE RECONSTRUCTION A.  ...  Again we see that the 3-layer convolutional neural network leads to a more detailed reconstruction. C.  ... 
doi:10.5281/zenodo.1159216 fatcat:pueesbuwyzgqdouk6f3h6driie

Predicting galaxy spectra from images with hybrid convolutional neural networks [article]

John F. Wu, J. E. G. Peek
2020 arXiv   pre-print
We present a powerful new approach using a hybrid convolutional neural network with deconvolution instead of batch normalization; this hybrid CNN outperforms other models in our tests.  ...  We are able to robustly predict and reconstruct galaxy spectra directly from broad-band imaging.  ...  the head of our neural networks.  ... 
arXiv:2009.12318v1 fatcat:i4ephedeirgahcirrectrta23q

Recognizing three-dimensional phase images with deep learning [article]

Weiru Fan, Tianrun Chen, Xingqi Xu, Ziyang Chen, Huizhu Hu, Delong Zhang, Da-Wei Wang, Jixiong Pu, Shi-Yao Zhu
2021 arXiv   pre-print
Optical phase contains key information for biomedical and astronomical imaging.  ...  To address this challenge, we developed a speckle three-dimensional reconstruction network (STRN) to recognize phase objects behind scattering media, which circumvents the limitations of memory effect.  ...  The generator is an encode-decode structured neural network that generates reconstructed phase images from the input speckle images.  ... 
arXiv:2107.10584v1 fatcat:zwbzte677rcqnjl3v5rtmd4fqy

Learning to Denoise Astronomical Images with U-nets [article]

Antonia Vojtekova, Maggie Lieu, Ivan Valtchanov, Bruno Altieri, Lyndsay Old, Qifeng Chen, Filip Hroch
2020 arXiv   pre-print
We propose Astro U-net, a convolutional neural network for image de-noising and enhancement.  ...  Our network is able to produce images with noise characteristics as if they are obtained with twice the exposure time, and with minimum bias or information loss.  ...  METHOD To denoise and enhance the astronomical images, we use convolutional neural networks.  ... 
arXiv:2011.07002v1 fatcat:d4yv7xt2xzaoxdhi7qoouk5f7q

Convolutional Neural Networks Approach for Solar Reconstruction in SCAO Configurations

Suárez Gómez, González-Gutiérrez, García Riesgo, Sánchez Rodríguez, Javier Iglesias Rodríguez, Santos
2019 Sensors  
These corrections are performed classically with reconstruction algorithms; between them, neural networks showed good results.  ...  A reconstruction algorithm is presented, "Shack-Hartmann reconstruction with deep learning on solar–prototype" (proto-HELIOS), to correct on fixed solar images, achieving an average 85.39% of precision  ...  At present, the tomographic reconstruction approach with convolutional neural networks is an open line of investigation.  ... 
doi:10.3390/s19102233 fatcat:smndqbyx6nbknbqkvpz3xaer34

Deep learning wavefront sensing and aberration correction in atmospheric turbulence

Kaiqiang Wang, MengMeng Zhang, Ju Tang, Lingke Wang, Liusen Hu, Xiaoyan Wu, Wei Li, Jianglei Di, Guodong Liu, Jianlin Zhao
2021 PhotoniX  
AbstractDeep learning neural networks are used for wavefront sensing and aberration correction in atmospheric turbulence without any wavefront sensor (i.e. reconstruction of the wavefront aberration phase  ...  from the distorted image of the object).  ...  The authors thank the Lijiang Astronomical Observatory of the Chinese Academy of Sciences for providing an experimental site.  ... 
doi:10.1186/s43074-021-00030-4 fatcat:swzlp43d65b57nx7j5gt5pdp2y

Real-time regression analysis with deep convolutional neural networks [article]

E. A. Huerta, Daniel George, Zhizhen Zhao, Gabrielle Allen
2018 arXiv   pre-print
We showcase the application of this new method with a timely case study, and then discuss the applicability of this approach to tackle similar challenges across science domains.  ...  In the context of image classification, we have applied deep learning for the classification of noise anomalies with spectrogram images as inputs to convolutional neural networks (CNNs) [17] , [15] ,  ...  techniques to increase the sensitivity of neural nets to extract low signal-to-noise ratio signals from noisy time-series; iii) systematic exploration to elucidate why deep convolutional neural networks  ... 
arXiv:1805.02716v1 fatcat:sp5mghuiy5d5fd5ecbbjl3x2ay

Correlated Read Noise Reduction in Infrared Arrays Using Deep Learning

Guillaume Payeur, Étienne Artigau, Laurence Perreault Levasseur, René Doyon
2022 Astronomical Journal  
We train a convolutional recurrent neural network on simulated astrophysical scenes added to laboratory darks to estimate the flux on each pixel of science images.  ...  We present a new procedure rooted in deep learning to construct science images from data cubes collected by astronomical instruments using HxRG detectors in low-flux regimes.  ...  Despite the presence of systematic biases, the fact that the neural network can reconstruct this image with acceptable accuracy despite not having been trained using data resembling this image highlights  ... 
doi:10.3847/1538-3881/ac69d2 fatcat:34fjja7kazdkxaitfibumwbhdq

Blind Image Deconvolution By Neural Recursive Function Approximation

Jiann-Ming Wu, Hsiao-Chang Chen, Chun-Chang Wu, Pei-Hsun Hsu
2010 Zenodo  
Based on the estimated blurring matrix, reconstruction of an original source image from a blurred image is further resolved by an annealed Hopfield neural network.  ...  This work explores blind image deconvolution by recursive function approximation based on supervised learning of neural networks, under the assumption that a degraded image is linear convolution of an  ...  X Minimization of ( ) E θ with respect to θ is the goal of supervised learning of RBF neural networks.  ... 
doi:10.5281/zenodo.1333964 fatcat:5vzlnbyjlrawxpbzikzu4h2rtq

2020 Index IEEE Transactions on Computational Imaging Vol. 6

2020 IEEE Transactions on Computational Imaging  
., +, TCI 2020 1017-1032 Convolutional neural networks CNF+CT: Context Network Fusion of Cascade-Trained Convolutional Neu- ral Networks for Image Super-Resolution.  ...  Coherent Plug-and-Play: Digital Holographic Imaging Through Atmospheric Turbulence Using Model-Based Iterative Reconstruction and Convolutional Neural Networks.  ... 
doi:10.1109/tci.2021.3054596 fatcat:puij7ztll5ai7alxrmqzsupcny

Experience with Artificial Neural Networks Applied in Multi-object Adaptive Optics

Sergio Luis Suárez Gómez, Carlos González-Gutiérrez, Enrique Díez Alonso, Jesús Daniel Santos, María Luisa Sánchez Rodríguez, Tim Morris, James Osborn, Alastair Basden, Laura Bonavera, Joaquín González-Nuevo González, Francisco Javier de Cos Juez
2019 Publications of the Astronomical Society of the Pacific  
The use of artificial neural networks has evolved to the extent of the creation of a reconstruction technique that is capable of estimating the wavefront of light after being deformed by the atmosphere  ...  These techniques have landed in the field of adaptive optics, and are being used to correct distortions caused by atmospheric turbulence in astronomical images obtained by ground-based telescopes.  ...  Figure 5 . 5 Example of the topology of a convolutional neural network.  ... 
doi:10.1088/1538-3873/ab1ebb fatcat:n67o5dy32vdq3jbo5vjbq2nxi4

The analysis of VERITAS muon images using convolutional neural networks

Qi Feng, Tony T. Y. Lin
2016 Proceedings of the International Astronomical Union  
We present preliminary results of a precise classification of a small set of muon events using a convolutional neural networks model with the raw images as input features.  ...  We also show the possibility of using the convolutional neural networks model for regression problems, such as the radius and brightness measurement of muon events, which can be used to calibrate the throughput  ...  fully-connected neural network classification model after the convolutional layers.  ... 
doi:10.1017/s1743921316012734 fatcat:xaurhwxowvfevbkzwn4jy52h6m

GammaLearn - first steps to apply Deep Learning to the Cherenkov Telescope Array data

Thomas Vuillaume, Jacquemont Mikael, Luca Antiga, Alexandre Benoit, Patrick Lambert, Gilles Maurin, Giorgia Silvestri, A. Forti, L. Betev, M. Litmaath, O. Smirnova, P. Hristov
2019 EPJ Web of Conferences  
Moreover, the trained neural networks show very good computing performances during execution.  ...  Due to its very high sensitivity, CTA will record a colossal amount of data that represent a computing challenge to the reconstruction software.  ...  A common approach, allowing to use traditional image processing frameworks and in particular convolutional neural network ones, is to re-sample these unconventional images into ones with a rectangular  ... 
doi:10.1051/epjconf/201921406020 fatcat:gr4zoz7gazfzdfignauazc6eg4

Adaptive optics based on machine learning: a review

Youming Guo, The Key Laboratory on Adaptive Optics, Chinese Academy of Sciences, Chengdu 610209, China, Libo Zhong, Lei Min, Jiaying Wang, Yu Wu, Kele Chen, Kai Wei, Changhui Rao, The Laboratory on Adaptive Optics, Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu 610209, China, University of Chinese Academy of Sciences, Beijing 100049, China
2022 Opto-Electronic Advances  
In recent years, with the rapid development of artificial intelligence, adaptive optics will be boosted dramatically.  ...  presented a method using convolutional neural network (CNN) as a reconstruction alternative in MOAO 74 .  ...  With suitable computer hardware, it is anticipated that on-site real-time reconstruction of astronomical images will be possible in the near future.  ... 
doi:10.29026/oea.2022.200082 fatcat:fkuhbsrwpvcxnca35tz54hx2lm
« Previous Showing results 1 — 15 out of 1,161 results