Galaxy morphology classification with deep convolutional neural networks

Zhu, Xiaopan; Dai, Jia-Ming; Bian, Chunjiang; Chen, Yu; Shi, Chen; Hu, Chen

doi:10.1007/s10509-019-3540-1

Cited by 90 publications

(66 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The goal was to predict the participants answers to a set of questions about morphological traits featured by the galaxy. The winner CNN architecture [23] established a benchmark for this problem that has been widely employed thereafter [24], [64]. However, these models make use of datasets of moderate size to make feasible their training and employ larger resources in terms of computational means and runtime.…”

Section: ) Convolutional Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Galaxy Image Classification Based on Citizen Science Data: A Comparative Study

et al. 2020

View full text Add to dashboard Cite

Many research fields are now faced with huge volumes of data automatically generated by specialised equipment. Astronomy is a discipline that deals with large collections of images difficult to handle by experts alone. As a consequence, astronomers have been relying on the power of the crowds, as a form of citizen science, for the classification of galaxy images by amateur people. However, the new generation of telescopes that will produce images at a higher rate highlights the limitations of this approach, and the use of machine learning methods for automatic classification is considered essential. The goal of this paper is to shed light on the automated classification of galaxy images exploring two distinct machine learning strategies. First, following the classical approach consisting of feature extraction together with a classifier, we compare the state-of-the-art feature extractor for this problem, the WND-CHARM, with our proposal based on autoencoders for feature extraction on galaxy images. We then compare these results with an end-to-end classification using convolutional neural networks. To better leverage the available citizen science data, we also investigate a pre-training scheme that exploits both amateur-and expert-labelled data. Our experiments reveal that autoencoders greatly speed up feature extraction in comparison with WND-CHARM and both classification strategies, either using convolutional neural networks or feature extraction, reach comparable accuracy. The use of pre-training in convolutional neural networks, however, has allowed us to provide even better results.

show abstract

Section: ) Convolutional Neural Networkmentioning

confidence: 99%

“…Nonetheless, the next generation of astronomical surveys that will produce billions of galaxy images [20] shows the limitations of this approach. ML methods are needed, pursuing a robust automation of the classification task, and several efforts have recently been developed in this direction [21]- [24].…”

Section: Introductionmentioning

confidence: 99%

Galaxy Image Classification Based on Citizen Science Data: A Comparative Study

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Algo semelhante foi feito em [Zhu et al 2019] propondo a classificação morfológica por meio de redes neurais residuais profundas (ResNets), utilizando imagenś opticas com conjunto de treinamento de aproximadamente 25.000 imagens classificadas manualmente pelo projeto Galaxy Zoo. O conjunto de dados foi originalmente distribuído no The Galaxy Challenge [Kaggle 2014].…”

Section: Trabalhos Correlatosunclassified

“…Este trabalho se aproxima do estudo de [Zhu et al 2019], utilizando a mesma base de dados, mas divergindo da arquitetura, tentando obter melhores resultados.…”

Section: Trabalhos Correlatosunclassified

Classificação Morfológica de Galáxias Por Meio de Redes Neurais

Silva¹,

Ventura²

2019

Anais Da X Escola Regional De Informática De Mato Grosso (ERI-MT 2019)

View full text Add to dashboard Cite

This paper proposes the development of a convolutional neural network for the morphological classification of galaxies through optical images, classifying them into six distinct classes based on the Hubble Tuning Fork model. In order to automate the mass identification and separation of the huge volume of data generated in recent astronomical observatories, deep learning and data augmentation techniques are used to generate increased data variation and consequently improve network accuracy. Our model achieved an average precision of 88%.

show abstract

“…In recent years there have been several fields of use of CNNs that, nowadays, allow the development of important applications. Some examples are: the antispoofing of the face and iris [11], recognition of highway traffic congestion [12], the image steganography and steganalysis [13], the galaxy morphology classification [14], drone detection, and classification [15,16]. However, the analysis of IIF images, as a whole, and in particular, in regards to the analysis of intensity, is extremely complex and linked to the experience of the immunologist [4].…”

Section: Introductionmentioning

confidence: 99%

Performance of Fine-Tuning Convolutional Neural Networks for HEp-2 Image Classification

et al. 2020

View full text Add to dashboard Cite

The search for anti-nucleus antibodies (ANA) represents a fundamental step in the diagnosis of autoimmune diseases. The test considered the gold standard for ANA research is indirect immunofluorescence (IIF). The best substrate for ANA detection is provided by Human Epithelial type 2 (HEp-2) cells. The first phase of HEp-2 type image analysis involves the classification of fluorescence intensity in the positive/negative classes. However, the analysis of IIF images is difficult to perform and particularly dependent on the experience of the immunologist. For this reason, the interest of the scientific community in finding relevant technological solutions to the problem has been high. Deep learning, and in particular the Convolutional Neural Networks (CNNs), have demonstrated their effectiveness in the classification of biomedical images. In this work the efficacy of the CNN fine-tuning method applied to the problem of classification of fluorescence intensity in HEp-2 images was investigated. For this purpose, four of the best known pre-trained networks were analyzed (AlexNet, SqueezeNet, ResNet18, GoogLeNet). The classifying power of CNN was investigated with different training modalities; three levels of freezing weights and scratch. Performance analysis was conducted, in terms of area under the ROC (Receiver Operating Characteristic) curve (AUC) and accuracy, using a public database. The best result achieved an AUC equal to 98.6% and an accuracy of 93.9%, demonstrating an excellent ability to discriminate between the positive/negative fluorescence classes. For an effective performance comparison, the fine-tuning mode was compared to those in which CNNs are used as feature extractors, and the best configuration found was compared with other state-of-the-art works.

show abstract

Galaxy morphology classification with deep convolutional neural networks

Cited by 90 publications

References 27 publications

Galaxy Image Classification Based on Citizen Science Data: A Comparative Study

Galaxy Image Classification Based on Citizen Science Data: A Comparative Study

Classificação Morfológica de Galáxias Por Meio de Redes Neurais

Performance of Fine-Tuning Convolutional Neural Networks for HEp-2 Image Classification

Contact Info

Product

Resources

About