Machine Learning Pattern Analysis of Visual Arts Metadata: Style–Genre Structure, Baseline Classification, and Cultural Heritage Interpretation
Main Article Content
Abstract
This study develops a metadata-driven machine-learning framework for analyzing visual patterns and organizational structure in a large WikiArt visual-arts corpus. The empirical analysis evaluates 103,250 artwork records across 2,319 artists, 136 style labels, and 42 genre labels, partitioned into an official training set of 79,433 records (76.93%) and a testing set of 23,817 records (23.07%). Missingness analysis indicates that style (0.95% missing) and genre (1.21% missing) are mostly complete, whereas production date exhibits substantial missingness (25.53% missing). The corpus displays strong class concentration: Impressionism (10,643 artworks; 10.41%) and Realism (10,523 artworks; 10.29%) represent the largest style categories, while portrait (16,847 artworks; 16.52%) and landscape (15,006 artworks; 14.71%) dominate genre labels. Normalized entropy measures for style (0.726) and genre (0.740) confirm significant class imbalance. A chi-square association test reveals a statistically significant, moderate relationship between style and genre ($\chi^2 = 494,553.56, p < 0.001$, Cramer's $V = 0.345$). Metadata-only baseline modeling using a decision tree achieved a macro F1-score of 0.466 for top-10 style classification and 0.426 for top-10 genre classification, outperforming random baselines. The paper establishes a transparent computational pipeline for dataset profiling, statistical evaluation, baseline modeling, and similarity retrieval in digital cultural heritage management.
Article Details
Issue
Section

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
How to Cite
References
[1] Abgaz, Y. M., Souza, R. R., Methuku, J., Koch, G., & Dorn, A. (2021). A methodology for semantic enrichment of cultural heritage images using artificial intelligence technologies. Journal of Imaging, 7(8), Article 121.
[2] Bar, Y., Levy, N., & Wolf, L. (2014). Classification of artistic styles using binarized features derived from a deep neural network. In European Conference on Computer Vision Workshops.
[3] Castellano, G., & Vessio, G. (2021). Deep learning approaches to pattern extraction and recognition in paintings and drawings: An overview. Neural Computing and Applications, 33, 12263-12282.
[4] Cetinic, E., Lipic, T., & Grgic, S. (2018). Fine-tuning convolutional neural networks for fine art classification. Expert Systems with Applications, 114, 107-118.
[5] Crowley, E. J., & Zisserman, A. (2014). The state of the art: Object retrieval in paintings using discriminative regions. In British Machine Vision Conference.
[6] David, E., & Netanyahu, N. S. (2017). DeepPainter: Painter classification using deep convolutional autoencoders. arXiv preprint arXiv:1711.08763.
[7] Elgammal, A., Liu, B., Elhoseiny, M., & Mazzone, M. (2018). The shape of art history in the eyes of the machine. In AAAI Conference on Artificial Intelligence.
[8] Fiorucci, M., Khoroshiltseva, M., Pontil, M., Traviglia, A., Del Bue, A., & James, S. (2020). Machine learning for cultural heritage: A survey. Pattern Recognition Letters, 133, 102-108.
[9] Gatys, L. A., Ecker, A. S., & Bethge, M. (2016). Image style transfer using convolutional neural networks. In IEEE Conference on Computer Vision and Pattern Recognition (pp. 2414-2423).
[10] Hamilton, M., Fu, S., Lu, M., Bui, J., Bopp, D., Chen, Z., Tran, F., Wang, M., Rogers, M., Zhang, L., Hoder, C., & Freeman, W. T. (2020). MosAIc: Finding artistic connections across culture with conditional image retrieval. arXiv preprint arXiv:2007.07177.
[11] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In IEEE Conference on Computer Vision and Pattern Recognition (pp. 770-778).
[12] Hicsonmez, S., Samet, N., Sener, F., & Duygulu, P. (2017). DRAW: Deep networks for recognizing styles of artists who illustrate children's books. arXiv preprint arXiv:1704.03057.
[13] Huang, G., Liu, Z., van der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In IEEE Conference on Computer Vision and Pattern Recognition (pp. 4700-4708).
[14] Johnson, J., Alahi, A., & Fei-Fei, L. (2016). Perceptual losses for real-time style transfer and super-resolution. In European Conference on Computer Vision (pp. 694-711).
[15] Joshi, A., Agrawal, A., & Nair, S. (2020). Art style classification with self-trained ensemble of autoencoding transformations. arXiv preprint arXiv:2012.03377.
[16] Karayev, S., Trentacoste, M., Han, H., Agarwala, A., Darrell, T., Hertzmann, A., & Winnemoller, H. (2014). Recognizing image style. In British Machine Vision Conference.
[17] Karterouli, K., & Batsaki, Y. (2021). AI and cultural heritage image collections: Opportunities and challenges. In Proceedings of EVA London 2021 (pp. 193-198).
[18] Khan, F. S., Beigpour, S., van de Weijer, J., & Felsberg, M. (2014). Painting-91: A large-scale database for computational painting categorization. Machine Vision and Applications, 25(6), 1385-1397.
[19] Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems (Vol. 25).
[20] Lecoutre, A., Negrevergne, B., & Yger, F. (2017). Recognizing art style automatically in painting with deep learning. In Proceedings of the Ninth Asian Conference on Machine Learning (PMLR, Vol. 77, pp. 327-342).
[21] McInnes, L., Healy, J., & Melville, J. (2018). UMAP: Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426.
[22] Pancaroglu, D. (2020). Artist, style and year classification using face recognition and clustering with convolutional neural networks. arXiv preprint arXiv:2012.01009.
[23] Razavian, A. S., Azizpour, H., Sullivan, J., & Carlsson, S. (2014). CNN features off-the-shelf: An astounding baseline for recognition. In IEEE Conference on Computer Vision and Pattern Recognition Workshops (pp. 806-813).
[24] Saleh, B., & Elgammal, A. (2015). Large-scale classification of fine-art paintings: Learning the right metric on the right feature. International Journal for Digital Art History, 2, 71-93.
[25] Sandoval, C., Pirogova, E., & Lech, M. (2019). Two-stage deep learning approach to the classification of fine-art paintings. IEEE Access, 7, 41770-41781.
[26] Seguin, B., Striolo, C., Kaplan, F., & di Lenardo, A. (2016). Visual link retrieval in a database of paintings. In European Conference on Computer Vision Workshops (pp. 753-767).
[27] Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Grad-CAM: Visual explanations from deep networks via gradient-based localization. In IEEE International Conference on Computer Vision (pp. 618-626).
[28] Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. In International Conference on Learning Representations.
[29] Strezoski, G., & Worring, M. (2017). OmniArt: Multi-task deep learning for artistic data analysis. arXiv preprint arXiv:1708.00684.
[30] Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015). Going deeper with convolutions. In IEEE Conference on Computer Vision and Pattern Recognition (pp. 1-9).
[31] Tan, M., & Le, Q. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. In International Conference on Machine Learning (pp. 6105-6114).
[32] Xie, S., Girshick, R., Dollar, P., Tu, Z., & He, K. (2017). Aggregated residual transformations for deep neural networks. In IEEE Conference on Computer Vision and Pattern Recognition (pp. 1492-1500).
[33] Zhao, W., Jiang, W., & Qiu, X. (2022). Big transfer learning for fine art classification. Computational Intelligence and Neuroscience, 2022, Article 1764606.
[34] Zhu, Y., Ji, Y., Zhang, Y., Xu, L., Zhou, A. L., & Chan, E. (2019). Machine: The new art connoisseur. arXiv preprint arXiv:1911.10091.