ترغب بنشر مسار تعليمي؟ اضغط هنا

Solar Image Deconvolution by Generative Adversarial Network

93   0   0.0 ( 0 )
 نشر من قبل Long Xu
 تاريخ النشر 2020
والبحث باللغة English




اسأل ChatGPT حول البحث

With Aperture synthesis (AS) technique, a number of small antennas can assemble to form a large telescope which spatial resolution is determined by the distance of two farthest antennas instead of the diameter of a single-dish antenna. Different from direct imaging system, an AS telescope captures the Fourier coefficients of a spatial object, and then implement inverse Fourier transform to reconstruct the spatial image. Due to the limited number of antennas, the Fourier coefficients are extremely sparse in practice, resulting in a very blurry image. To remove/reduce blur, CLEAN deconvolution was widely used in the literature. However, it was initially designed for point source. For extended source, like the sun, its efficiency is unsatisfied. In this study, a deep neural network, referring to Generative Adversarial Network (GAN), is proposed for solar image deconvolution. The experimental results demonstrate that the proposed model is markedly better than traditional CLEAN on solar images.



قيم البحث

اقرأ أيضاً

This chapter reviews recent developments of generative adversarial networks (GAN)-based methods for medical and biomedical image synthesis tasks. These methods are classified into conditional GAN and Cycle-GAN according to the network architecture de signs. For each category, a literature survey is given, which covers discussions of the network architecture designs, highlights important contributions and identifies specific challenges.
In order to assure a stable series of recorded images of sufficient quality for further scientific analysis, an objective image quality measure is required. Especially when dealing with ground-based observations, which are subject to varying seeing c onditions and clouds, the quality assessment has to take multiple effects into account and provide information about the affected regions. In this study, we develop a deep learning method that is suited to identify anomalies and provide an image quality assessment of solar full-disk H$alpha$ filtergrams. The approach is based on the structural appearance and the true image distribution of high-quality observations. We employ a neural network with an encoder-decoder architecture to perform an identity transformation of selected high-quality observations. The encoder network is used to achieve a compressed representation of the input data, which is reconstructed to the original by the decoder. We use adversarial training to recover truncated information based on the high-quality image distribution. When images with reduced quality are transformed, the reconstruction of unknown features (e.g., clouds, contrails, partial occultation) shows deviations from the original. This difference is used to quantify the quality of the observations and to identify the affected regions. We apply our method to full-disk H$alpha$ filtergrams from Kanzelhohe Observatory recorded during 2012-2019 and demonstrate its capability to perform a reliable image quality assessment for various atmospheric conditions and instrumental effects, without the requirement of reference observations. Our quality metric achieves an accuracy of 98.5% in distinguishing observations with quality-degrading effects from clear observations and provides a continuous quality measure which is in good agreement with the human perception.
The choice of parameters, and the design of the network architecture are important factors affecting the performance of deep neural networks. Genetic Algorithms (GA) have been used before to determine parameters of a network. Yet, GAs perform a finit e search over a discrete set of pre-defined candidates, and cannot, in general, generate unseen configurations. In this paper, to move from exploration to exploitation, we propose a novel and systematic method that autonomously and simultaneously optimizes multiple parameters of any deep neural network by using a GA aided by a bi-generative adversarial network (Bi-GAN). The proposed Bi-GAN allows the autonomous exploitation and choice of the number of neurons, for fully-connected layers, and number of filters, for convolutional layers, from a large range of values. Our proposed Bi-GAN involves two generators, and two different models compete and improve each other progressively with a GAN-based strategy to optimize the networks during GA evolution. Our proposed approach can be used to autonomously refine the number of convolutional layers and dense layers, number and size of kernels, and the number of neurons for the dense layers; choose the type of the activation function; and decide whether to use dropout and batch normalization or not, to improve the accuracy of different deep neural network architectures. Without loss of generality, the proposed method has been tested with the ModelNet database, and compared with the 3D Shapenets and two GA-only methods. The results show that the presented approach can simultaneously and successfully optimize multiple neural network parameters, and achieve higher accuracy even with shallower networks.
Generative adversarial networks (GANs) have been a popular deep generative model for real-world applications. Despite many recent efforts on GANs that have been contributed, mode collapse and instability of GANs are still open problems caused by thei r adversarial optimization difficulties. In this paper, motivated by the cooperative co-evolutionary algorithm, we propose a Cooperative Dual Evolution based Generative Adversarial Network (CDE-GAN) to circumvent these drawbacks. In essence, CDE-GAN incorporates dual evolution with respect to the generator(s) and discriminators into a unified evolutionary adversarial framework to conduct effective adversarial multi-objective optimization. Thus it exploits the complementary properties and injects dual mutation diversity into training to steadily diversify the estimated density in capturing multi-modes and improve generative performance. Specifically, CDE-GAN decomposes the complex adversarial optimization problem into two subproblems (generation and discrimination), and each subproblem is solved with a separated subpopulation (E-Generator} and E-Discriminators), evolved by its own evolutionary algorithm. Additionally, we further propose a Soft Mechanism to balance the trade-off between E-Generators and E-Discriminators to conduct steady training for CDE-GAN. Extensive experiments on one synthetic dataset and three real-world benchmark image datasets demonstrate that the proposed CDE-GAN achieves a competitive and superior performance in generating good quality and diverse samples over baselines. The code and more generated results are available at our project homepage: https://shiming-chen.github.io/CDE-GAN-website/CDE-GAN.html.
State-of-the-art techniques in Generative Adversarial Networks (GANs) have shown remarkable success in image-to-image translation from peer domain X to domain Y using paired image data. However, obtaining abundant paired data is a non-trivial and exp ensive process in the majority of applications. When there is a need to translate images across n domains, if the training is performed between every two domains, the complexity of the training will increase quadratically. Moreover, training with data from two domains only at a time cannot benefit from data of other domains, which prevents the extraction of more useful features and hinders the progress of this research area. In this work, we propose a general framework for unsupervised image-to-image translation across multiple domains, which can translate images from domain X to any a domain without requiring direct training between the two domains involved in image translation. A byproduct of the framework is the reduction of computing time and computing resources, since it needs less time than training the domains in pairs as is done in state-of-the-art works. Our proposed framework consists of a pair of encoders along with a pair of GANs which learns high-level features across different domains to generate diverse and realistic samples from. Our framework shows competing results on many image-to-image tasks compared with state-of-the-art techniques.
التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا