Implementation of VGG Models for Recognizing Mudras in Bharathanatyam Dance
Keywords:
Mudras, Bharathanatyam, Hand Gestures, Convolutional Neural NetworkAbstract
Hand gestures were the first known form of communication amongst humans, prior to the development of language and civilizations. Recognizing hand gestures have gained lime light in the recent years due to various applications. This work aims to recognize 4 single handed Mudras (Paataka, Mushti, Kapittha, Katakamuha) and 4 double handed mudras (Anjali, Swastika, Pushpaputa and Garuda) that have been used predominantly in Bharathanatyam which is a classical dance form of India. The proposed system uses 4000 images collected from the dancers from various dance schools using Canon EOS 760D camera. The acquired images were resized and, the images depicting each Mudra were used for training the Convolutional Neural Network (CNN). VGG16 and VGG19 architectures of CNN were employed for single and double handed mudra recognition. While VGG16 yielded an accuracy of 94.7% for single handed mudras and 96.3% for double handed mudras, VGG19 gave an accuracy of 98.5% and 98.5% for single and double handed mudras respectively.
Downloads
References
Niveditha Parthasarathy, “Novel Video Benchmark Dataset Generation and Real-Time Recognition of Symbolic Hand Gestures in Indian Dance Applying Deep Learning Techniques”, Journal on Computing and Cultural Heritage, March 2023.
Gopa Bhaumik and Mahesh Chandra Govil, “Recognition of Hasta Mudra Using Star Skeleton—Preservation of Buddhist Heritage”, Pattern Recognition and Image Analysis, Vol. 31, No. 2, pp. 251–260, 2021.
Divya Hariharan, Tinku Acharya, and Sushmita Mitra, “Recognizing Hand Gestures of a Dancer”, Springer, pp. 186–192, 2011.
Saba Naaz, Dr. K. B. ShivaKumar, Dr. Parameshachari B. D., “Aggregation Signature of Multi Scale Features from Super Resolution Images for Bharathanatyam Mudra Classification for Augmented Reality Based Learning”, International Journal of Intelligent Systems and Applications in Engineering IJISAE, 11(3s), 224–234, 2023.
Basavaraj S. Anami, Venkatesh A. Bhandage, “Combined Hu moments, orientation knowledge, and grid intersections feature based identification of Bharathanatyam mudra
Images”, Springer : Pattern Analysis and Applications, 22:1439–1454, 2019.
Basavaraj S. Anami & Venkatesh A. Bhandage, “A vertical-horizontal-intersections feature based method for identification of bharathanatyam double hand mudra images”, Springer : Multimed Tools Appl , 77:31021–31040, 2018.
Prof. Bhavana R Maale, Unnati Ukanal, “Normalized Chain Codes and Oriented Distances based Bharathanatyam Hand Gesture Recognition”, International Journal for Research in Applied Science & Engineering Technology (IJRASET), Volume 8, Issue VII, July 2020.
Shweta Mozarkar, Dr.C.S.Warnekar “Recognizing Bharatnatyam Mudra Using Principles of Gesture Recognition”, IJCSN International Journal of Computer Science and Network, Volume 2, Issue 4, August 2013.
Gautham Jayadeep, Vishnupriya N V, Vyshnavi Venugopal, Vishnu S, Geetha M, “Mudra: Convolutional Neural Network based Indian Sign Language Translator for Banks”, International Conference on Intelligent Computing and Control Systems (ICICCS), 2020.
M.Kalaimani, Dr.B.Latha, Dr. AN.Sigappi, “Survey on Hand Gesture Recognition in Bharathanatyam Mudras”, TELEMATIQUE Volume 21, Issue 1, 2022
Sriparna Saha, Amit Konar, Deblina Gupta, Anasuya Ray, Abhinaba Sarkar, Pritha Chatterjee, Ramadoss Janarthanan, . “Bharathanatyam Hand Gesture Recognition Using Polygon Representation”, IEEE International Conference on Control, Instrumentation, Energy & Communication(CIEC), 2014.
Karishma Dixit, Anand Singh Jalal, “Automatic Indian Sign Language Recognition System”, IEEE International Advance Computing Conference (IACC), 2013.
K.V.V. Kumar, P.V.V. Kishore, “Indian Classical Dance Mudra Classification Using HOG Features and SVM Classifier”, International Journal of Electrical and Computer Engineering (IJECE), Vol. 7, No. 5, pp. 2537 - 2546, October 2017.
Basavaraj S. Anami, Venkatesh A. Bhandage, “A Comparative Study of Suitability of Certain Features in Classification of Bharathanatyam Mudra Images Using Artificial Neural Network”, Springer Nature : Neural Processing Letters, 50:741–769, 2019.
Anami, B.S. and Bhandage, V.A., “Artificial neural network based identification of
Bharathanatyam Mudra images using eigen values”, Int. J. Applied Pattern Recognition, Vol. 5, No. 3, pp.191–205, 2018.
Sriparna Saha, Lidia Ghosh, Amit Konar, Ramadoss Janarthanan, “Fuzzy L Membership Function Based Hand Gesture Recognition for Bharathanatyam Dance”, International Conference on Computational Intelligence and Communication Networks, 2013.
Mr. Kriti Verma, “A Survey on Dance Gesture Recognition”, International Journal of ICT and Management, Vol VI, Issue – 2, Dec 2018.
Anuja P. Parameshwaran, Heta P. Desai, Rajshekhar Sunderraman, Michael Weeks, “Transfer Learning for Classifying Single Hand Gestures on Comprehensive Bharathanatyam Mudra Dataset”, IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2019.
Ming Yan and Zhe He, “Dance Action Recognition Model Using Deep Learning Network in Streaming Media Environment”, Journal of Environmental and Public Health, Volume 2022, 2022.
Pravin R Futane, Dr. Rajiv V. Dharaskar, “HASTA MUDRA: An Interpretation of Indian Sign Hand Gestures”, IEEE International Conference on Electronics Computer Technology (ICECT), 2011.
Reddy, A. ., & Waheeb , M. Q. . (2022). Enhanced Pre-Processing Based Cardiac Valve Block Detection Using Deep Learning Architectures. Research Journal of Computer Systems and Engineering, 3(1), 84–89. Retrieved from https://technicaljournals.org/RJCSE/index.php/journal/article/view/47
Kumar, P. ., Gupta, M. K. ., Rao, C. R. S. ., Bhavsingh, M. ., & Srilakshmi, M. (2023). A Comparative Analysis of Collaborative Filtering Similarity Measurements for Recommendation Systems. International Journal on Recent and Innovation Trends in Computing and Communication, 11(3s), 184–192. https://doi.org/10.17762/ijritcc.v11i3s.6180
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
