Yoga is a new way to look at the disciplines of our lives, such as physical, mental, and spiritual practices. Yoga started many years ago. Because of the many benefits of yoga, medical professionals and many celebrities suggest doing yoga for a healthy lifestyle. Taking care of your body, mind, and breath is a simple definition of yoga. However, depending on the COVID-19 situation, everything happening from home in this situation it is important to maintain your health. You need to do exercise daily. To do the exercise properly an instructor is needed at home that you cannot do in the COVID-19 situation. It is injurious to our health to do yoga poses without an instructor. So here we are going to represent a proposed model for yoga pose detection using a machine-learning algorithm to identify and detect the yoga pose form. Our system works on 8 yoga poses. We have developed a GUI-based desktop application using the Tkinter library. The input is preprocessed in the form of an image, the object is detected, and the core of the human body is identified using the media pipe and OpenCV library. For training and testing data, we use CSV files downloaded from Kaggle. We use logistic regression models for training and testing. The system gets an accuracy score of 100%.



Software And Hardware