CROWD-SOURCED FOLK ART CLASSIFICATION MODELS
DOI:
https://doi.org/10.29121/shodhkosh.v6.i4s.2025.6866Keywords:
Folk Art Classification, Crowd-Sourced Annotation, Deep Learning, Cultural Heritage Informatics, Probabilistic Label FusionAbstract [English]
Folk art is a diverse nexus of place identities, craft systems of knowledge and intergenerational cultural memory. However, its visual heterogeneity, including motifs, materials, techniques, and vocabularies of symbols, creates tremendous problems of scalable digital classification. The conventional manual classification of folk art collections is usually limited by a short pool of expertise, subjective knowledge, and archival diversity. To fill in these gaps, this work presents a folk art classification framework based on a complete crowd-sourced approach to folk art, which incorporates both community engagement and contemporary deep learning architectural designs. Multi source dataset is created by pulling together images of museums, cultural archives, festivals, and local artisan communities. Motifs, geometric patterns, material categories, stylistic markers and region-specific attributes are broken down into structured set of guidelines in terms of annotation. Redundancy checks, worker reliability scoring, means of probabilistic label fusion as well as hierarchical review are used to design a quality-controlled annotation pipeline. The model architecture is based on the integration of the baseline convolutional neural networks with transformer-based visual encoders in order to learn the fine-grained and multi-label folk art descriptors. The probabilistic integration module uses the crowd-sourced annotations in order to address the issue of label noise and enhance robustness. Experimental analysis shows that there is significant improvement in attribute recognition accuracy, hierarchical tagging coherence and cross-regional generalizability.
References
Ajorloo, S., Jamarani, A., Kashfi, M., Haghi Kashani, M., and Najafizadeh, A. (2024). A Systematic Review of Machine Learning Methods in Software Testing. Appl. Soft Comput., 162, 111805. https://doi.org/10.1016/j.asoc.2024.111805
Alzubaidi, M., Agus, M., Makhlouf, M., Anver, F., Alyafei, K., and Househ, M. (2023). Large-Scale Annotation Dataset for Fetal Head Biometry in Ultrasound Images. Data Brief, 51, 109708. https://doi.org/10.1016/j.dib.2023.109708
Asgari, M., and Hurtut, T. (2024). A Design Language for Prototyping and Storyboarding Data-Driven Stories. Appl. Sci., 14, 1387. https://doi.org/10.3390/app14031387
Brauwers, G., and Frasincar, F. (2023). A General Survey on Attention Mechanisms in Deep Learning. IEEE Trans. Knowl. Data Eng., 35, 3279–3298. https://doi.org/10.1109/TKDE.2023.3284278
Dobbs, T., and Ras, Z. (2022). On Art Authentication and the Rijksmuseum Challenge: A Residual Neural Network Approach. Expert Syst. Appl., 200, 116933. https://doi.org/10.1016/j.eswa.2022.116933
Fu, Y., Wang, W., Zhu, L., Ye, X., and Yue, H. (2024). Weakly Supervised Semantic Segmentation Based on Superpixel Affinity. J. Vis. Commun. Image Represent., 101, 104168. https://doi.org/10.1016/j.jvcir.2024.104168
Kittichai, V., Sompong, W., Kaewthamasorn, M., Sasisaowapak, T., Naing, K.M., Tongloy, T., Chuwongin, S., Thanee, S., and Boonsang, S. (2024). A Novel Approach for Identification of Zoonotic Trypanosome Utilizing Deep Metric Learning and Vector Database-Based Image Retrieval System. Heliyon, 10, e30643. https://doi.org/10.1016/j.heliyon.2024.e30643
Messer, U. (2024). Co-Creating Art with Generative Artificial Intelligence: Implications for Artworks and Artists. Comput. Hum. Behav. Artif. Hum., 2, 100056. https://doi.org/10.1016/j.chbai.2024.100056
Schaerf, L., Postma, E., and Popovici, C. (2024). Art Authentication with Vision Transformers. Neural Comput. Appl., 36, 11849–11858. https://doi.org/10.1007/s00521-024-08814-7
Trichopoulos, G., Alexandridis, G., and Caridakis, G. (2023). A Survey on Computational and Emergent Digital Storytelling. Heritage, 6, 1227–1263. https://doi.org/10.3390/heritage60301227
Turpin, H., Cain, R., and Wilson, M. (2024). Towards a Co-Creative Immersive Digital Storytelling Methodology to Explore Experiences of Homelessness in Loughborough. Soc. Sci., 13, 59. https://doi.org/10.3390/socsci13010059
Zaurín, J.R., and Mulinka, P. (2023). Pytorch-Widedeep: A Flexible Package for Multimodal Deep Learning. J. Open Source Softw., 8, 5027. https://doi.org/10.21105/joss.05027
Zeng, Z., Zhang, P., Qiu, S., Li, S., and Liu, X. (2024). A Painting Authentication Method Based on Multi-Scale Spatial-Spectral Feature Fusion and Convolutional Neural Network. Comput. Electr. Eng., 118, 109315. https://doi.org/10.1016/j.compeleceng.2024.109315
Zhang, Z., Sun, K., Yuan, L., Zhang, J., Wang, X., Feng, J., and Torr, P.H. (2021). Conditional DETR: A Modularized DETR Framework for Object Detection. arXiv, arXiv:2108.08902. https://arxiv.org/abs/2108.08902
Zhao, S., Fan, Q., Dong, Q., Xing, Z., Yang, X., and He, X. (2024). Efficient Construction and Convergence Analysis of Sparse Convolutional Neural Networks. Neurocomputing, 597, 128032. https://doi.org/10.1016/j.neucom.2024.128032
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Fazil Hasan, Smitha K, Dr. Murari Devakannan Kamalesh, Lehar Isarani, Dr. Swetarani Biswal, Sakshi Sobti, Pawan Wawage
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.
