Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{182988,
        author = {SREENA. S and SHIBILI.T and AKHILA. M and LALJI CYRIAC},
        title = {CNN-Based Novel Deep Learning Ensemble Model for Kathakali Hand Mudra Recognition and Classification},
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {12},
        number = {no},
        pages = {86-92},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=182988},
        abstract = {Kathakali, a classical dance form originating from Kerala, India, is characterized by intricate hand gestures (mu- dras), body movements, facial expressions, and background mu- sic. These mudras play a pivotal role in conveying emotions and storytelling, but their complexity often makes them challenging for non-experts to interpret. This paper explores the use of deep learning techniques, specifically Convolutional Neural Networks (CNNs) and Artificial Neural Networks (ANNs) to automatically classify Kathakali hand gestures across five distinct classes. We investigate various methods for data preprocessing and classification, leveraging pre-trained models such as ResNet50, VGG16 and InceptionV3 for feature extraction. Our aim is to enhance the understanding and recognition of Kathakali mudras, making them more accessible to the public and aiding in their preservation.},
        keywords = {Feature extraction, Image classification, CNN, Deep learning},
        month = {},
        }