Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{174058,
        author = {Chitrakshi Jadaun and Ekta Pawar and Priyanka and Hemlata Chaudhary},
        title = {POSTURE DETECTION using Machine Learning ( libraries OpenCV , Media pipe and Numpy )},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {10},
        pages = {4513-4520},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=174058},
        abstract = {A key component of healthcare, fitness tracking, and human-computer interaction is posture detection. Using the Python libraries MediaPipe and OpenCV, this study offers an effective method for real-time posture identification. MediaPipe offers pre-trained models for estimating human stance, while OpenCV delivers powerful image processing and computer vision features. Our system effectively recognizes and evaluates human postures in photos and video streams by utilizing these technologies.The suggested model analyzes video data, recognizes important body landmarks, and assesses the accuracy of posture. 33 keypoints are retrieved using MediaPipe's Pose module, and these are then examined further to ascertain the angles and locations of the joints. To improve detection accuracy, OpenCV helps with picture pre-processing tasks like background separation and noise reduction. Applications such as ergonomic evaluation, physiotherapy, and fitness tracking can benefit from the system's ability to categorize postures, identify abnormalities, and give real-time feedback.},
        keywords = {},
        month = {March},
        }