How to Cite: Abarna, S., Rathikarani, V., & Dhanalakshmi, P. (2022). SIFT and SURF features based classification of yoga hand mudras using machine learning techniques. International Journal of Health Sciences, 6(S1), 1971–1984. https://doi.org/10.53730/ijhs.v6nS1.4946 International Journal of Health Sciences ISSN 2550-6978 E-ISSN 2550-696X © 2022. Corresponding author: Abarna, S. Manuscript submitted: 09 Nov 2021, Manuscript revised: 27 Feb 2022, Accepted for publication: 18 March 2022 1971 SIFT and SURF Features based Classification of Yoga Hand Mudras Using Machine Learning Techniques S. Abarna Research Scholar, Department of Computer Science and Engineering, Annamalai University, Chidambaram, Tamilnadu, India V. Rathikarani Assistant Professor, Department of Computer Science and Engineering, Annamalai University, Chidambaram, Tamilnadu, India P. Dhanalakshmi Professor, Department of Computer Science and Engineering, Annamalai University, Chidambaram, Tamilnadu, India Abstract---Yoga is a unique spiritual discipline of self-development and self-realization that teaches us how to live our lives to the fullest. Yoga's integrative approach brings deep harmony and unwavering balance to body and mind to awaken our dormant capacity for higher consciousness, which is the true purpose of human evolution. The numerous documented physical and mental benefits of yoga have played a large part in the interest in yoga. Due to a lack of datasets and thus the necessity to identify mudra in real time, distinguishing yoga hand mudras seems to be a tough undertaking. The yoga hand mudras are used as input in the proposed study, and the two components Scale Invariant Feature Transform (SIFT) and Speeded Up Robust Features (SURF) are extracted, followed by classification utilising machine learning techniques including Support Vector Machine (SVM) and Random Forest. By comparing the experimental results the performance of SIFT with SVM yields better results. Keywords---random forest, SIFT, support vector machine, SURF, yoga hand mudras.