INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
In this paper, we propose a novel system for yoga pose detection, classification, and correction using machine learning techniques. The system utilizes computer vision algorithms, such as Convolutional Neural Networks (CNNs), to accurately detect and classify up to 10 different types of yoga poses in real-time. Furthermore, we implement a custom heuristic algorithm to evaluate the form of each pose and provide personalized feedback and recommendations to users on how to improve their technique. The system is evaluated using a large dataset of labeled yoga videos, and the results demonstrate its effectiveness and efficiency in detecting and classifying poses with high accuracy. The proposed system has the potential to significantly enhance the practice of yoga and provide a new level of convenience and accessibility for yoga enthusiasts and instructors. This study contributes to the advancement of the application of machine learning in the field of physical exercise and wellness.
"Yoga Pose - Detection, Classification and Correction Using ML", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.8, Issue 4, page no.1496 - 1499, April-2023, Available :http://www.ijsdr.org/papers/IJSDR2304239.pdf
Downloads:
000336256
Publication Details:
Published Paper ID: IJSDR2304239
Registration ID:205312
Published In: Volume 8 Issue 4, April-2023
DOI (Digital Object Identifier):
Page No: 1496 - 1499
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn