Abstract
The algorithm proposed in this paper aims to achieve pose recognition in Indian classical dance domain. Three different dance forms namely Bharatnatyam, Kathak and Odissi, all together with 15 poses have been considered for pose classification problem. An initial database is created consisting of 100 images and split into training and testing dataset. Hu moments have been chosen as the feature extraction technique to describe the shape context of an image since they are scale, translation and rotation invariant. To extract Hu moments from the image, the foreground and the background of the images must be separated. The resultant images are then converted to binary. Since it is a multiclass classification problem, SVM using one vs one approach as well as one vs all approach has been implemented and the results are contrasted with linear and RBF kernels for both the approaches.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
http://onlinebharatanatyam.com/2007/07/21/more-about-adavus/
Samanta, S., Purkait, P., Chanda, B.: Indian classical dance classification by learning dance pose bases. In: 2012 IEEE Workshop on Applications of Computer Vision (WACV). IEEE (2012)
Saha, S.: Pose recognition from dance video for Elearning application. Diss. Jadavpur University, Kolkata-700032, India (2011)
Sugathan, A., et al.: Attributed relational graph based feature extraction of body poses in indian classical dance bharathanatyam. Int. J. Eng. Res. Appl. 4(5), 11–17 (2014). ISSN 2248-9622, www.ijera.com
Ming-Kuei, H.: Visual pattern recognition by moment invariants. IRE Trans. Inf. Theor. 8(2), 179–187 (1962)
Rother, C., Kolmogorov, V., Blake, A.: Grabcut: interactive foreground extraction using iterated graph cuts. ACM Trans. Graph. (TOG) 23(3), 309–314 (2004)
Milgram, J., Cheriet, M., Sabourin, R.: “One Against One” or “One Against All”: which one is better for handwriting recognition with SVMs? In: Lorette, G. (ed.) Tenth International Workshop on Frontiers in Handwriting Recognition, La Baule (France), Suvisoft, October 2006. Inria-00103955
Allwein, E.L., Schapire, R.E., Singer, Y.: Reducing multiclass to binary: a unifying approach for margin classifiers. J. Mach. Learn. Res. 1, 113–141 (2001)
Rifkin, R., Klautau, A.: In defense of one-vs-all classification. J. Mach. Learn. Res. 5, 101–141 (2004)
Joutsijoki, H., Juhola, M.: Comparing the one-vs-one and one-vs-all methods in benthic macroinvertebrate image classification. In: Perner, P. (ed.) MLDM 2011. LNCS (LNAI), vol. 6871, pp. 399–413. Springer, Heidelberg (2011). doi:10.1007/978-3-642-23199-5_30
Zokovich, S., Tuba, M.: Hu moments based handwritten digits recognition algorithm. Ministry of Science, Republic of Serbia, Project No. 44006 (2013)
Naemura, M., Suzuki, M.: Extraction of rhythmical factors on dance actions thorough motion analysis. In: Seventh IEEE Workshops on Application of Computer Vision, WACV/MOTIONS 2005, vol. 1. IEEE (2005)
Megavannan, V., Agarwal, B., Babu, R.V.: Human action recognition using depth maps. In: 2012 International Conference on Signal Processing and Communications (SPCOM). IEEE (2012)
Mozarkar, S., Warnekar, C.S.: Recognizing bharatnatyam mudra using principles of gesture recognition gesture recognition. Int. J. Comput. Sci. Netw. 2(2), 46–52 (2013)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Shubhangi, Tiwary, U.S. (2017). Classification of Indian Classical Dance Forms. In: Basu, A., Das, S., Horain, P., Bhattacharya, S. (eds) Intelligent Human Computer Interaction. IHCI 2016. Lecture Notes in Computer Science(), vol 10127. Springer, Cham. https://doi.org/10.1007/978-3-319-52503-7_6
Download citation
DOI: https://doi.org/10.1007/978-3-319-52503-7_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-52502-0
Online ISBN: 978-3-319-52503-7
eBook Packages: Computer ScienceComputer Science (R0)