Live Yoga Pose Classification Using Image Processing, Deep Learning and LR Algorithm

Live Yoga Pose Classification Using Image Processing, Deep Learning and LR Algorithm

Prof. Rupal More¹,  Pallavi Late², Yukta Taral³,  Nilima Ahire⁴,

Bhagyashri Baviskar⁵

¹Assistant Professor  ^{2 3 4 5}Student ^{1 2 3 4 5}Department of Computer Engineering

^{1 2 3 4 5}Sandip Institute of Technology and Research Center, Nashik, India

---------------------------------------------------------------------***---------------------------------------------------------------------

Abstract - An approach to accurately acknowledge various Yoga pose Assess deep learning algorithms has been presented during this work. During system, our purpose to access a Yoga pose assessment technique using pose  detection to assist the self-learning of Yoga. The system first detects a Yoga pose using multi human joint parts detection only with laptop camera. During this system, we have a tendency to additionally propose AN improved formula to calculate scores which will of all poses. Our application is evaluated on completely different Yoga poses. A hybrid Machine learning model is proposed using linear Regression  algorithm  for Yoga recognition on real-time videos, where Linear regression is used to extract features from key-points of each frame obtained from Open-Pose.

Keywords:  - Linear Regression, Machine Learning, Yoga Pose detection etc.