• Nikshepa T
• Sai Ram S A
• Tarun M
• Sri Saagar G N
• Sanjay M S

Exercise requires self-learning, but if one performs exercises incorrectly, their muscles and ligaments may suffer severe damage. In order to avoid this, it provides a natural method based on machine learning techniques to adjust the exerciser's posture. With the help of the suggested system, practitioners should be able to identify incorrect poses, receive succinct feedback to help them correct them, and receive appropriate feedback to help them advance their familiarity with a specific position and prevent injuries. Human joint localization model and (CNN) for pose recognition are combined in a proposed deep learning framework, which is then used to identify pose errors in order to develop the system. Once the system has all the information on the user’s posture and offers guidance to the user either straighten or improve their alignment.

Pose estimation, blaze pose, activity identification, computer vision, real-time pose detection, mediapipe.

"Detection and Emendation of Postures in Fitness Using CNN and BlazePose Model ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 3, page no.f277-f281, March-2024, Available :http://www.jetir.org/papers/JETIR2403532.pdf

"Detection and Emendation of Postures in Fitness Using CNN and BlazePose Model ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 3, page no. ppf277-f281, March-2024, Available at : http://www.jetir.org/papers/JETIR2403532.pdf