Indian Classical Dance Mudra Classification Using HOG Features and SVM Classifier
Digital understanding of Indian classical dance is least studied work, though it has been a part of Indian Culture from around 200 BC. This work explores the possibilities of recognizing classical dance mudras in various dance forms in India. The images of hand mudras of various classical dances are collected from the internet, and a database is created for this job. Histogram of oriented (HOG) features of hand mudras input the classifier. Support vector machine (SVM) classifies the HOG features into mudras as text messages. The mudra recognition frequency (MRF) is calculated for each mudra using graphical user interface (GUI) developed from the model. Popular feature vectors such as SIFT, SURF, LBP, and HAAR are tested against HOG for precision and swiftness. This work helps new learners and dance enthusiastic people to learn and understand dance forms and related information on their mobile devices.
KeywordsIndian classical dance mudras HOG features SVM classifier Mudra recognition frequency Scale invariant feature transform
- 1.Naidu, N., Naidu, B.V., Pantulu, P.R.: Tandava Lakshanam: the fundamentals of ancient hindu dancing. A Karana in dance is defined as “the coordination of the movements of the hands and feet”. New Delhi, Munshiram Manoharlal, 1971, p. 19 (1980)Google Scholar
- 5.Kishore, P.V.V., Anil Kumar, D., Goutham, E.N.D., Manikanta, M.: Continuous sign language recognition from tracking and shape features using fuzzy inference engine. In: International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET), pp. 2165–2170. IEEE (2016)Google Scholar
- 6.Kishore, P.V.V., Kishore, S.R.C., Prasad, M.V.D.: Conglomeration of hand shapes and texture information for recognizing gestures of Indian sign language using feed forward neural networks. Int. J. Eng. Technol. (IJET), ISSN: 0975-4024 (2013)Google Scholar
- 7.Anandh, A., Mala, K., Suganya, S.: Content based image retrieval system based on semantic information using color, texture and shape features. In: International Conference on Computing Technologies and Intelligent Data Engineering (ICCTIDE), pp. 1–8. IEEE (2016)Google Scholar
- 10.Lee, S.-H., et al.: An efficient selection of HOG feature for SVM classification of vehicle. In: 2015 International Symposium on Consumer Electronics (ISCE). IEEE (2015)Google Scholar