A Comparative Study of Certain Classifiers for Bharatanatyam Mudra Images' Classification using Hu-Moments

Abstract

India is rich in culture and heritage where various traditional dances are practiced. Bharatanatyam is an Indian classical dance, which is composed of various body postures and hand gestures. This ancient art of dance has to be studied under guidance of dance teachers. In present days there is a scarcity of Bharatanatyam dance teachers. There is a need to adopt technology to popularize this dance form. This article presents a 3-stage methodology for the classification of Bharatanatyam mudras. In the first stage, acquired images of Bharatanatyam mudras are preprocessed to obtain contours of mudras using canny edge detector. In the second stage, Hu-moments are extracted as features. In the third stage, rule-based classifiers, artificial neural networks, and k-nearest neighbor classifiers are used for the classification of unknown mudras. The comparative study of classification accuracies of classifiers is provided at the end. The work finds application in e-learning of ‘Bharatanatyam' dance in particular and dances in general and automation of commentary during concerts.