FOLK ART RECOGNITION USING DEEP LEARNING ALGORITHMS
DOI:
https://doi.org/10.29121/shodhkosh.v6.i2s.2025.6721Keywords:
Folk Art Recognition, Deep Learning, Vision Transformers, CLIP Models, Cultural Heritage AI, Fine-Grained Classification, Image RetrievalAbstract [English]
The given work offers a deep learning-driven architecture of identifying Indian folk art traditions with the help of a hybrid framework that integrates convolutional networks and Vision Transformers and CLIP-driven semantic alignment. A curated and annotated multi-source dataset was prepared based on a culturally informed tradition, region and sub style taxonomy. The issues of visual diversity and imbalance of the classes were resolved with rigorous preprocessing, motif-preserving augmentations, and training based on classes. It was found that the hybrid architecture performed well both with classification and retrieval tasks, and showed strong macro-F1 scores and clearly separated embedding clusters of the major folk traditions. Confusion analysis showed styles that were visually overlapping and embedding-space visualizations ensured that the model was capable of capturing significant cultural differences. These findings suggest that deep learning can be effectively used in complex artistic areas that encourage scalable cultural documentation, digital archiving, and heritage education. The suggested framework forms a powerful foundation on upcoming improvements of generative augmentation, cross-domain adaptation and interactive cultural exploration tools.
References
Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Alemi (2023). GPT-4 Technical Report. arXiv.
Kumar, S., Tyagi, A., Sahu, T., Shukla, P., and Mittal, A. (2018). Indian Art form Recognition Using Convolutional Neural Networks. In Proceedings of the 5th International Conference on Signal Processing and Integrated Networks (SPIN), IEEE, 800-804. DOI: https://doi.org/10.1109/SPIN.2018.8474290
Milani, F., and Fraternali, P. (2021). A Dataset and a Convolutional Model for Iconography Classification in Paintings. Journal on Computing and Cultural Heritage, 14(4), 1–8. https://doi.org/10.1145/3459996 DOI: https://doi.org/10.1145/3458885
Mondal, K., and Anita, H. B. (2021). Categorization of Artwork Images Based on Painters Using CNN. Journal of Physics: Conference Series, 1818(1), Article 012223. https://doi.org/10.1088/1742-6596/1818/1/012223 DOI: https://doi.org/10.1088/1742-6596/1818/1/012223
Munir, A., Kong, J., and Qureshi, M. A. (2024). Overview of Convolutional Neural Networks. In Accelerators for Convolutional Neural Networks. IEEE, 13–37. https://doi.org/10.1002/9781394171910.ch2 DOI: https://doi.org/10.1002/9781394171910.ch2
Partarakis, N., Zabulis, X., Patsiouras, N., Adami, I., Chatziantoniou, A., and Stephanidis, C. (2020). An Approach to the Creation and Presentation of Reference Gesture Datasets for the Preservation of Traditional Crafts. Applied Sciences, 10(20), 7325. https://doi.org/10.3390/app10207325
Podder, D., Shashaank, M. A., Mukherjee, J., and Sural, S. (2021). IHIRD: A Dataset for Indian Heritage Image Retrieval. In Digital Techniques for Heritage Presentation and Preservation. Springer, 51-73. https://doi.org/10.1007/978-3-030-47135-6_4 DOI: https://doi.org/10.1007/978-3-030-57907-4_4
Sharma, A., and Jadon, R. S. (2023). Indian Visual Arts Classification Using Neural Network Algorithms. In Proceedings of the International Conference on Innovative Computing and Communication. Springer, 483–493. https://doi.org/10.1007/978-981-19-2821-5_38 DOI: https://doi.org/10.1007/978-981-99-4071-4_38
Sharma, E. K. (2015). Tribal Folk arts of India. Journal of International Academic Research for Multidisciplinary, 3(5), 300–308.
Sultana, F., Sufian, A., and Dutta, P. (2020). Evolution of Image Segmentation Using Deep Convolutional Neural Network: A Survey. Knowledge-Based Systems, 201, Article 106062. https://doi.org/10.1016/j.knosys.2020.106062 DOI: https://doi.org/10.1016/j.knosys.2020.106062
Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A. (2017). Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning. In Proceedings of the AAAI Conference on Artificial Intelligence, 31(1). DOI: https://doi.org/10.1609/aaai.v31i1.11231
Varshney, S., Lakshmi, C. V., and Patvardhan, C. (2023). Madhubani Art Classification Using Transfer Learning with Deep Feature Fusion and Decision Fusion Based Techniques. Engineering Applications of Artificial Intelligence, 119, Article 105734. https://doi.org/10.1016/j.engappai.2022.105734 DOI: https://doi.org/10.1016/j.engappai.2022.105734
Wang, D., and Liu, X. (2015). A Resource Scheduling Strategy for Cloud Computing Platform of Power System Simulation Based on Dynamic Migration of Virtual Machines. Automation of Electric Power Systems, 39(12), 97–105. https://doi.org/10.7500/AEPS20140711008
Wang, X. (2016). Deep Learning in Object Recognition, Detection, and Segmentation. Foundations and Trends in Signal Processing, 8(4), 217–382. https://doi.org/10.1561/2000000039 DOI: https://doi.org/10.1561/2000000071
Williams, E. (2017). The image data resource: A Scalable Platform for Biological Image Data Access, Integration, and Dissemination. Nature Methods, 14, 775–781. https://doi.org/10.1038/nmeth.4326 DOI: https://doi.org/10.1101/089359
Yang, H., and Min, K. (2020). Classification of Basic Artistic Media Based on a Deep Convolutional Approach. Applied Sciences, 10(20), 7325. https://doi.org/10.3390/app10207325 DOI: https://doi.org/10.3390/app10207325
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Dr. Shashikant Patil, Kalpana Rawat, Jagdish Pimple, Dr. Asit Kumar Subudhi, Lakshay Bareja, Nitish Vashisht
This work is licensed under a Creative Commons Attribution 4.0 International License.
With the licence CC-BY, authors retain the copyright, allowing anyone to download, reuse, re-print, modify, distribute, and/or copy their contribution. The work must be properly attributed to its author.
It is not necessary to ask for further permission from the author or journal board.
This journal provides immediate open access to its content on the principle that making research freely available to the public supports a greater global exchange of knowledge.
