Classification of galaxy images using vision transformers

Document Type : Research Article

Authors

Faculty of Electrical Engineering, Sahand University of Technology, Tabriz, Iran

Abstract

The deep gaze of humans into the night sky, aimed at uncovering the mysteries of the cosmos using advanced telescopes, has generated an immense volume of data. The classification of stars and galaxies present in these images, due to the vast amount of data, was a highly time-consuming process for astronomers. As a result, the "Galaxy Zoo" citizen science project, in which volunteers participated in the classification of this data, was introduced by researchers, significantly reducing the classification time. In recent decades, the introduction of machine learning and deep learning models has accelerated the classification of galaxies, leading to the replacement of manual classification methods with automated machine-based approaches. Recently, Vision Transformers (ViTs) have emerged as a significant innovation in machine learning, demonstrating substantial potential in various research fields. These models have particularly garnered attention in the analysis, detection, and classification of images and computer vision, due to their ability to process large datasets and learn complex patterns. The need to develop advanced methods for the automatic analysis of galaxy images to increase detection and classification accuracy in the shortest possible time motivated the current research to classify galaxy images from the Galaxy10 DECaLS dataset into 10 classes with an accuracy of 99.85% using the ViT model. The results obtained have been promising in comparison with other competitors.

Keywords

Main Subjects

References

[1] G. De Vaucouleurs, ‘‘Classification and morphology of external galaxies”. In:Astrophysik iv: ternsysteme/astrophysics iv: Stellar systems. Springer, Vol.53, pp.275–310, July. 1959
[2] C. J. Lintott, K. Schawinski, A. Slosar, et al, ‘‘Galaxy Zoo: morphologies derived from visual inspection of galaxies from the sloan digital sky survey”. Monthly Notices of the Royal Astronomical Society, Vol.389, No.3, pp.1179–1189, Sep. 2008
[3] C. J. Conselice, ‘‘The relationship between stellar light distributions of galaxies and their formation histories”. The Astrophysical Journal Supplement Series, Vol.147, No.1, July. 2003
[4] J. M. Lotz, J. Primack, P. Madau, ‘‘A new nonparametric approach to galaxy morphological classification”. The Astronomical Journal, Vol.128, No.1, pp.163–182, July. 2004
[5] P. Freeman, R. Izbicki, et al, ‘‘New image statistics for detecting disturbed galaxy morphologies at high redshift”. Monthly Notices of the Royal Astronomical Society, Vol.434, No.1, pp.282–295, Jun. 2013
[6] J. Vega-Ferrero, H. Domínguez Sánchez, M. Bernardi, et al, ‘‘Pushing automated morphological classifications to their limits with the dark energy survey”. Monthly Notices of the Royal Astronomical Society, Vol.506, No.2, pp.1927–1943, Sep. 2021
[7] M. Walmsley, C. Lintott, T. G´eron, S. Kruk, et al,‘‘Galaxy zoo decals: Detailed visual morphology measurements from volunteers and deep learning for 314000 galaxies”. Monthly Notices of the Royal Astronomical Society, Vol.509, No.3, pp.3966–3988, Jan. 2022
[8] R. Gupta, P. Srijith, S. Desai, ‘‘Galaxy morphology classification using neural ordinary differential equations”. Astronomy and Computing, Vol.38, No.5533, pp.100543, Jan. 2022
[9] H. Farias, D. Ortiz, G. Damke, M. J. Arancibia, M. Solar, ‘‘Mask galaxy: Morphological segmentation of galaxies.Astronomy and Computing”,Vol.33, No.100420, Aug. 2020
[10] P. H. Barchi, R. R. de Carvalho, R. R. Rosa, R. Sautter, et al, ‘‘Machine and deep learning applied to galaxy morphology-a comparative study”. Astronomy and Computing, Vol.30, No.100334, Jan. 2020
[11] H. Domínguez Sánchez's, M. Huertas-Company, M. Bernardi, D. Tuccillo, J. L. Fischer, ‘‘Improving galaxy morphologies for sdss with deep learning. Monthly Notices of the Royal Astronomical Society, Vol.476, No.3, pp.3661–3676, May. 2018
[12] M. Banerji, O. Lahav, C. J. Lintott, et al, ‘‘Galaxy Zoo: reproducing galaxy morphologies via machine learning. Monthly Notices of the Royal Astronomical Society, Vol.406, No.1, pp.342–353, July. 2010
[13] F. Ferrari, R.R. de Carvalho, M. Trevisan, ‘‘Morfometryka—a new way of establishing morphological classification of galaxies”, The Astrophysical Journal, Vol. 814, No.1, pp.55, Nov. 2015
[14] M. Abd el aziz, K. M. Hosny, I.M. selim, ‘‘Galaxies imageclassification using artificial bee colony basedonorthogonal Gegenbauer moments”, springer, Soft Comput, Vol.23, No.19, pp.9573–9583, Oct. 2019.
[15] L. Shamir, ‘‘Automatic morphological classification of galaxy images”, Monthly Notices of the Royal Astronomical Society, Vol.399, No.3, pp.1367–1372, Nov. 2009
[16] M. Marin, L.E. Sucar, J.A. Gonzalez, R. Diaz, ‘‘A Hierarchical Model for Morphological Galaxy Classification”, in: Proceedings of the Twenty-Sixth International Florida Artificial Intelligence Research Society Conference, Jan. 2013
[17] M. E. Abd el aziz, I. M. selim., and X. Shengwu., ‘‘Automatic Detection of Galaxy Type From Datasets of Galaxies Image Based on Image Retrieval Approach”, Scientific Reports (www.nature.com/scientificreports) , Jun. 2017
[18] R. E. González, R. P. Muñoz, C. A. Hernández, ‘‘Galaxy detection and identi_cation using deep learning and data augmentation”, Astronomy and Computing, Vol.25, pp.103-109, Oct. 2018
[19] D. G. York, J. Adelman, J. E. Jr. Anderson, et al, ‘‘The sloan digital sky survey:Technical summary”, The Astronomical Journal, Vol.120, No.3, pp.1579-1587, Sep. 2000
[20] J. P. Gardner, J. C. Mather, M. Clampin, R. Doyon, M. A. Greenhouse, H. B. Hammel, J. B. Hutchings, P. Jakobsen, S. J. Lilly, K. S. Long, et al, ‘‘The james webb space telescope”. Space Science Reviews, Vol.123, No.4, pp.485–606, Apr. 2006
[21] N. A. Grogin, D. D. Kocevski, S. M. Faber, et al, ‘‘Candels: the cosmic assembly near-infrared deep extragalactic legacy survey”. The Astrophysical Journal Supplement Series, Vol.197, No.2, pp.39, Dec. 2011
[22] M. J. Baumstark, G. Vinci, ‘‘Spiral-Elliptical automated galaxy morphology classification from telescope images”. Astronomy and Computing, Vol. 46, No.100770, Oct. 2023
[23] K.W. Willett, C. J. Lintott, S. P. Bamford, et al, ‘‘Galaxy Zoo 2: detailed morphological classifications for 304 122 galaxies from the Sloan Digital Sky Survey”. Monthly Notices of the Royal Astronomical Society, Vol. 435, Issue 4, pp 2835–2860, Nov. 2013
[24] P. H. Barchi, R. R. de Carvalho, R. R. Rosa, et al, ‘‘Machine and Deep Learning Applied to Galaxy Morphology - A Comparative Study”. Astronomy and Computing, Vol. 30, N. 100334, Nov. 2019
[25] S. Gharat, Y. Dandawate, ‘‘Galaxy Classification: A deep learning approach for classifying Sloan Digital Sky Survey images”, Monthly Notices of the Royal Astronomical Society, Vol.511, No.4, pp.5120–5124, Apr. 2022
[26] K. Mohale, M. Lochner, ‘‘Enabling Unsupervised Discovery in Astronomical Images through Self-Supervised Representations”. MNRAS, Vol. 530, Issue 1, pp. 1274--1295, May 2024
[27] X.Tan, ‘‘Accurate and efficient galaxy classification based on mobile vision transformer”. Applied and Computational Engineering, Vol.33(1), pp.118-125, Jan. 2024
[28] S. Dieleman, K. W. Willett, J. Dambre, ‘‘Rotation-invariant convolutional neural networks for galaxy morphology prediction”, Monthly Notices of the Royal Astronomical Society, Vol450, No.2, pp.1441–1459, Jun. 2015
[29] N. E. M. Khalifa, M. H. N. Taha, A. E. Hassanien, I. M. Selim, ‘‘Deep Galaxy: Classification of Galaxies based on Deep Convolutional Neural Networks”, Computer Vision and Pattern Recognition (cs.CV), Sep. 2017
[30] J. M. Dai, J. Tong, ‘‘Galaxy Morphology Classification with Deep Convolutional Neural Networks”.Astrophysics and Space Science, Vol. 364(4), Jul. 2018
[31] J. Y. Y. Lin, S. M. Liao, H. J. Huang, W. T. Kuo, O. H. Min Ou, ‘‘Galaxy Morphological Classification with Efficient Vision Transformer”. accepted by the NeurIPS Machine Learning and the Physical Sciences workshop, Oct. 2021
[32] J. Cao, T. Xu, Y. Deng, et al, ‘‘Galaxy morphology classification based on Convolutional vision Transformer (CvT)”. A&A,Vol. 683, pp.11, A42, Mar. 2024
[33] A. Vaswani, N. Shazeer, N. Parmar, et al, ‘‘Attention Is All You Need”. Advances in Neural Information Processing Systems 30 (NIPS 2017), Jun. 2017
[34] M. Vafaeezadeh, H. Behnam, P. Gifani, ‘‘Ultrasound Image Analysis with Vision Transformers—Review”. Diagnostics, Vol. 14, No.5, pp. 542, Mar. 2024
[35] M. Eassa, I. M. Selim, W. Dabour, P. Elkafrawy, ‘‘Automated detection and classification of galaxies based on their brightness patterns”, Alexandria Engineering Journal, Vol.61, No.2, pp.1145-1158, Feb. 2022
[36] S. Kang, M. S. Shin, T. Kim, ‘‘Galaxy Morphological Classification with Deformable Attention Transformer”, Machine Learning and the Physical Sciences workshop, NeurIPS. 2022
[37] K. Alrfou, A. Kordijazi, T. Zhao, ‘‘Computer Vision Methods for the Microstructural Analysis of Materials: The State-of-the-art and Future Perspectives”, Materials Science, Computer Science, Engineering, Jul. 2022

Files

Share

How to cite

Statistics