An Empirical Analysis of Three Moments on Sattriya Dance Single-Hand Gestures Dataset
The single-hand gestures of Indian classical dance are termed as ‘Asamyukta Hastas,’ which is a combination of two Sanskrit words, asamyukta meaning ‘single’ and hastas meaning ‘hand gestures’. There are eight officially recognized classical dance forms i
- PDF / 270,871 Bytes
- 9 Pages / 439.37 x 666.142 pts Page_size
- 45 Downloads / 198 Views
Abstract The single-hand gestures of Indian classical dance are termed as ‘Asamyukta Hastas,’ which is a combination of two Sanskrit words, asamyukta meaning ‘single’ and hastas meaning ‘hand gestures’. There are eight officially recognized classical dance forms in India. This paper focuses on the 29 single-hand gestures of Sattriya dance which is one of the Indian classical dance forms. It presents an analysis on recognition of single-hand gestures of Sattriya dance form images using different classifiers such as k-nearest neighbor (k-NN), naive Bayes, Bayesian network, decision tree, and Support Vector Machine (SVM). In this work, we have used Hu’s seven invariant moments, Zernike moments, and Legendre moments up to tenth order each. In this analysis, it indicates that Legendre moments show a better performance compared to other moments for all variation of dataset, and could achieve an accuracy of 96.03%.
Keywords Sattriya classical dance Hand gestures recognition Moments features Machine learning classifiers
1 Introduction Sattriya dance originated in the state of Assam. It is one of the popular dance forms among the eight Indian classical dance forms. This classical dance uses several hand gestures, most of them are similar to other classical dances which is performed by both male and female dancers. The Indian classical dances on which research work of gesture recognition have been done are Bharat Natyam [1–3], Odissi [4, 5]. However, no work has been reported in the literature on Sattriya dance. One of the M. Devi (&) S. Saharia Department of Computer Science and Engineering, Tezpur University, Tezpur 784028, Assam, India e-mail: [email protected] S. Saharia e-mail: [email protected] © Springer Nature Singapore Pte Ltd. 2018 A. Kalam et al. (eds.), Advances in Electronics, Communication and Computing, Lecture Notes in Electrical Engineering 443, https://doi.org/10.1007/978-981-10-4765-7_69
665
666
M. Devi and S. Saharia
applications of this research is to create universal communication environment for a dance drama which is independent of the language of the associated song. It has also applications in the self-judgement and e-learning of dances. In the art of dance learning, hand gestures are first and the most important step to learn because of its flexibility and utility. The hand gestures used in classical dance form are known as mudras, where as in Sattriya dance they are known as hastas [6]. The single-hand gestures which are used in Sattriya dance are known as Asamyukta hastas. It is mentioned in the book ‘Sattriya Nrittyar Rup Darshan’ by Borah [6], there are totally 76 hastas used in Sattriya dance. Among them 29 are single-hand gestures and remaining 47 are double hand gestures. These double hand gestures are divided into Samyukta hastas and Nritya hastas. This paper focuses on single-hand gestures of Sattriya dance. The main challenges of hand gesture recognition are the feature extraction which is the most important step for any recognition system. Moments features are considered
Data Loading...
