التفاصيل البيبلوغرافية
| العنوان: |
Identification and Classification of Eye Movements in Bharatanatyam using Deep Learning Techniques. |
| المؤلفون: |
Manikandan, Pavithra, Vijayaraghavan, Aravind, Karthika, S., Srinivasan, R. |
| المصدر: |
Grenze International Journal of Engineering & Technology (GIJET); 2023, Vol. 9 Issue 2, p566-573, 8p |
| مصطلحات موضوعية: |
DEEP learning, EYE tracking, CONVOLUTIONAL neural networks, EYE movements, BHARATA natyam, ARTIFICIAL intelligence, FEATURE extraction, MODERN dance |
| مستخلص: |
This paper is centred around the topic of Image Processing in Bharatnatyam, specifically based on the identification and classification of eye movements in classical Indian dance forms. These eight eye movements, also known as dhristi bedas, are extremely significant in the portrayal of the dance form and convey distinct emotions when acted out by the dancer. It would be very beneficial for Bharatnatyam students and avid classical dance enthusiasts to be able to easily identify the eye movements performed by a dancer so they can understand the story being conveyed. Hence, this paper aims to develop an algorithmic system using artificial intelligence and deep learning to process a dance video as input data and display the category of eye movements performed by the dancer in the video. The framework of the system is as follows: A convolutional neural network is developed with multiple layers and the frames from the video data undergo various stages in our methodology such as pre-processing, feature extraction and mapping the recognized patterns using the softmax activation function to each eye movement. The implementation of our proposed algorithm is done using Tensorflow and Keras. The proposed algorithm will allow the audience and students to comprehend the messages of the story through the dancer's eyes. [ABSTRACT FROM AUTHOR] |
|
Copyright of Grenze International Journal of Engineering & Technology (GIJET) is the property of GRENZE Scientific Society and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| قاعدة البيانات: |
Complementary Index |
