A syntactical modeling and classification for performance evaluation of Bali traditional dance

This paper presents a linguistically motivated approach for dance gesture performance evaluation using skeleton tracking to robustly classify arbitrary dance gesture into one of predefined gesture classes and provide performance score in regards to the dance master's gesture. The gesture class in this study is a set common gesture of Bali traditional dances. The dance gesture is represented as a set of skeleton feature descriptors that are extracted from images captured using Kinect depth sensor. A set of rules are learned from the training examples to capture the structure of the gesture motion using grammar inference method. The empiric results showed that elbow and foot of dance performer are the most discriminative features for representing dance gesture of Bali traditional dance. Probabilistic and deterministic grammars achieved 0.92 and 0.95 of average precision for recognizing the tested dance gestures.