Proceedings of the International Conference on Sustainable Innovation with Artificial Intelligence and Machine Learning 2025 (ICSIAIML 2025)

YakshaVarnika- A Journey into the Soul of Yakshagana’s Legendary Characters using Deep Learning

Authors
G. K. Roopa1, *, P. Santhi Thilagam1, 2, B. Annappa2, A. Aparna2, K. S. Poorvika2, V. S. Swapna2, M. Tejaswini2
1Department of Computer Science and Engineering, National Institute of Technology, Karnataka, Surathkal, Mangalore, India
2Department of CSE (Data Science), Vivekananda College of Engineering & Technology, Puttur, India
*Corresponding author. Email: roopagk.227cs500@nitk.edu.in
Corresponding Author
G. K. Roopa
Available Online 6 January 2026.
DOI
10.2991/978-94-6463-948-3_41How to use a DOI?
Keywords
Yakshagana; Artificial Intelligence (AI); Convolutional Neural Networks (CNNs); Dataset
Abstract

YakshaVarnika is a system that combines cultural tradition and modern technology by recognizing characters from Yakshagana performances using images. Our method uses customized Convolutional Neural Networks (CNNs) to uniquely identify characters by analyzing their distinct crown patterns, costume elements, and facial makeup. Unlike general vision systems, YakshaVarnika is designed for the Indian theatrical tradition, improving recognition accuracy. The YakshaVarnika system provides a rapid and user-friendly tool for scholars, students, and cultural enthusiasts. This solution facilitates the accessible study of Yakshagana’s visual language, providing a valuable resource for research and artistic appreciation. YakshaVarnika makes it easy for anyone without expert knowledge to recognize and understand Yakshagana characters in seconds. A key factor in achieving significantly higher accuracy than alternative systems was deploying our uniquely curated labeled data set. We generated a specialized, labeled dataset for this work, consisting of around 5000 images that capture the diverse visual characteristics of unique Yakshagana characters, ranging from gods and demons to sages and various Stree Veshas.

Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

Volume Title
Proceedings of the International Conference on Sustainable Innovation with Artificial Intelligence and Machine Learning 2025 (ICSIAIML 2025)
Series
Advances in Intelligent Systems Research
Publication Date
6 January 2026
ISBN
978-94-6463-948-3
ISSN
1951-6851
DOI
10.2991/978-94-6463-948-3_41How to use a DOI?
Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

TY  - CONF
AU  - G. K. Roopa
AU  - P. Santhi Thilagam
AU  - B. Annappa
AU  - A. Aparna
AU  - K. S. Poorvika
AU  - V. S. Swapna
AU  - M. Tejaswini
PY  - 2026
DA  - 2026/01/06
TI  - YakshaVarnika- A Journey into the Soul of Yakshagana’s Legendary Characters using Deep Learning
BT  - Proceedings of the International Conference on Sustainable Innovation with Artificial Intelligence and Machine Learning 2025 (ICSIAIML 2025)
PB  - Atlantis Press
SP  - 581
EP  - 592
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-948-3_41
DO  - 10.2991/978-94-6463-948-3_41
ID  - Roopa2026
ER  -