Abstract
The classification of Art media requires careful analysis due to the physical characteristics of the author’s work, such as shape, color, texture, medium, and historical period, which must be considered to correctly categorize the different Art media. This paper presents an experimental study of Art media classification based on pre-trained Convolutional Neural Networks (CNN), such as VGG16, ResNet50, and Xception, to demonstrate the robustness and improvement of the learning models. We trained them on WikiArt dataset, which is a reference in Art media. The same five art classes (Drawings, Engraving, Iconography, Painting, and Sculptures) are considered to validate the accuracy of the classification model. We trained using an NVIDIA Tesla K80 GPU in the Google Colaboratory (Colab) environment, and the Keras API with TensorFlow as Backend. The results show that all the CNNs tested present high correlation in the classification of Engravings and Drawings, due to the similarities of both classes. The best performance was obtained with the VGG16 architecture, with an accuracy of 75% using another dataset integrated with different works from the Del Prado and Louvre museums. This study confirms that the classification of Art media presents a challenge for CNN architecture due to the correlation found in the different classes.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Abidin, D.: The effect of derived features on art genre classification with machine learning. Sakarya Univ. J. Sci. 25(6), 1275–1286
Cabrera-Ponce, A.A., Martinez-Carranza, J.: Onboard CNN-based processing for target detection and autonomous landing for MAVs. In: Figueroa Mora, K.M., Anzurez Marín, J., Cerda, J., Carrasco-Ochoa, J.A., Martínez-Trinidad, J.F., Olvera-López, J.A. (eds.) MCPR 2020. LNCS, vol. 12088, pp. 195–208. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-49076-8_19
Chollet, F.: Xception: Deep learning with depthwise separable convolutions. CoRR abs/ arXiv: 1610.02357 (2016). https://arxiv.org/abs/1610.02357
Chu, W.T., Wu, Y.L.: Deep correlation features for image style classification. In: Proceedings of the 24th ACM International Conference on Multimedia, pp. 402–406 (2016)
Chu, W.T., Wu, Y.L.: Image style classification based on learnt deep correlation features. IEEE Trans. Multimedia 20(9), 2491–2502 (2018)
Dataset. https://github.com/JanManuell/Art-Media-Classification--Dataset.git
Fortuna-Cervantes, J.M., Ramírez-Torres, M.T., Mejía-Carlos, M., Martínez-Carranza, J., Murguía-Ibarra, J.S.: Texture classification for object detection in aerial navigation using transfer learning and wavelet-based features. In: Martinez-Carranza, J. (ed.) 12\(^{th}\) International Micro Air Vehicle Conference, Puebla, México. pp. 210–215 (Nov 2021). https://www.imavs.org/papers/2021/27.pdf, paper no. IMAV2021-27
Gao, J., Zhou, H., Zhang, Y.: The performance of two cnn methods in artworks aesthetic feature recognition. In: Proceedings of the 2020 12th International Conference on Machine Learning and Computing, pp. 289–296 (2020)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR abs/ arXiv: 1512.03385 (2015). https://arxiv.org/abs/1512.03385
Ibarra-Vazquez, G., Olague, G., Chan-Ley, M., Puente, C., Soubervielle-Montalvo, C.: Brain programming is immune to adversarial attacks: Towards accurate and robust image classification using symbolic learning. Swarm Evol. Comput. 71, 101059 (2022)
Ibarra-Vazquez, G., Olague, G., Puente, C., Chan-Ley, M., Soubervielle-Montalvo, C.: Automated design of accurate and robust image classifiers with brain programming. In: Proceedings of the Genetic and Evolutionary Computation Conference Companion, pp. 1385–1393 (2021)
Kandel, I., Castelli, M.: Transfer learning with convolutional neural networks for diabetic retinopathy image classification a review. Appli. Sci. 10(6), 2021 (2020)
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Kovalev, V.Y., Shishkin, A.G.: Painting style classification using deep neural networks. In: 2020 IEEE 3rd International Conference on Computer and Communication Engineering Technology (CCET), pp. 334–337. IEEE (2020)
Lombardi, T.E.: The classification of style in fine-art painting. Pace University (2005)
du Louvre, M.: https://collections.louvre.fr/en/
Masilamani, G.K., Valli, R.: Art classification with pytorch using transfer learning. In: 2021 International Conference on System, Computation, Automation and Networking (ICSCAN), pp. 1–5. IEEE (2021)
Mikołajczyk, A., Grochowski, M.: Data augmentation for improving deep learning in image classification problem. In: 2018 international interdisciplinary PhD workshop (IIPhDW), pp. 117–122. IEEE (2018)
Olague, G., Ibarra-Vázquez, G., Chan-Ley, M., Puente, C., Soubervielle-Montalvo, C., Martinez, A.: A deep genetic programming based methodology for art media classification robust to adversarial perturbations. In: Bebis, G., et al. (eds.) ISVC 2020. LNCS, vol. 12509, pp. 68–79. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-64556-4_6
del Prado, M.N.: https://www.museodelprado.es/coleccion/obras-de-arte
Research, G.: https://colab.research.google.com/
Rodriguez, C.S., Lech, M., Pirogova, E.: Classification of style in fine-art paintings using transfer learning and weighted image patches. In: 2018 12th International Conference on Signal Processing and Communication Systems (ICSPCS), pp. 1–7. IEEE (2018)
Rojas-Aranda, J.L., Nunez-Varela, J.I., Cuevas-Tello, J.C., Rangel-Ramirez, G.: Fruit classification for retail stores using deep learning. In: Figueroa Mora, K.M., Anzurez Marín, J., Cerda, J., Carrasco-Ochoa, J.A., Martínez-Trinidad, J.F., Olvera-López, J.A. (eds.) MCPR 2020. LNCS, vol. 12088, pp. 3–13. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-49076-8_1
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323(6088), 533–536 (1986)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Srivastava, N.: Improving neural networks with dropout, vol. 182(566), p. 7. University of Toronto (2013)
Acknowledgements
This work was founded by CONACYT through the grant “Convocatoria de Ciencia Básica y/o Ciencia de Frontera 2022”, project ID 320036.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Fortuna-Cervantes, J.M., Soubervielle-Montalvo, C., Perez-Cham, O.E., Peña-Gallardo, R., Puente, C. (2023). Experimental Study of the Performance of Convolutional Neural Networks Applied in Art Media Classification. In: Rodríguez-González, A.Y., Pérez-Espinosa, H., Martínez-Trinidad, J.F., Carrasco-Ochoa, J.A., Olvera-López, J.A. (eds) Pattern Recognition. MCPR 2023. Lecture Notes in Computer Science, vol 13902. Springer, Cham. https://doi.org/10.1007/978-3-031-33783-3_16
Download citation
DOI: https://doi.org/10.1007/978-3-031-33783-3_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-33782-6
Online ISBN: 978-3-031-33783-3
eBook Packages: Computer ScienceComputer Science (R0)
