International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Al-Enabled Pose Detection System for Automated Physiotherapy Feedback |
|---|---|
| ABSTRACT | Recovery from neurological conditions, musculoskeletal injuries, and post-operative rehabilitation all depend on physiotherapy. Unsupervised at-home workouts, however, frequently lead to bad posture, decreased efficacy, and a higher risk of injury. In this paper, a computer vision and machine learning-based real-time physiotherapy pose recognition and feedback system is presented. The system uses logistic regression to categorise seven essential rehabilitation exercises and uses MediaPipe's holistic model to extract body landmarks. Users can dynamically adjust their posture with the help of a graphical user interface (GUI) based on TKINTER, which offers real-time visual and aural feedback. The system provides a scalable solution for home-based rehabilitation by improving remote physiotherapy's consistency, safety, and accessibility. |
| TITLE | |
| AUTHOR | TEJAS AVHAD, ADITYA CHIPADE, RUCHITA DHAWALE, HARSHWARDHAN PATIL, PROF. PRIYANKA FULSUNDAR |
| PUBLICATION DATE | 2025-11-01 |
| VOLUME | 175 |
| DOI | DOI: 10.15680/IJIRCCE.2025.1310027 |
| pdf/27_Al-Enabled Pose Detection System for Automated Physiotherapy Feedback.pdf | |
| KEYWORDS |
