Copyright © 2026 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{178245,
        author = {Shubham U M and Prof. Nethravathy V and Chinthan M I and Sowmya M},
        title = {HUMAN ACTIVITY RECOGNITION USING MACHINE LEARNING LIKE RUNNING,WALKING,BOXING AND CLAPPING},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {4437-4441},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=178245},
        abstract = {Human action recognition is a vital area in computer vision with applications in security, healthcare, and robotics. This paper presents a robust hierarchical method to extract motion information while minimizing the impact of background movements. The proposed approach begins with segmenting the subject from video frames, followed by Motion History Image (MHI) computation to capture motion patterns over time. Significant features are extracted using the Blob Algorithm, which identifies regions of interest. These features are then classified using Support Vector Machine (SVM) and Gaussian Mixture Model (GMM) techniques. The combination of SVM's discriminative power and GMM's probabilistic framework ensures accurate prediction and classification of human actions. Experimental results validate the effectiveness of the approach, showcasing its capability to handle complex scenarios with background noise, making it a promising solution for action recognition in dynamic environments.},
        keywords = {Human Action Recognition, Computer Vision, Motion History Image (MHI), Blob Algorithm, Support Vector Machine (SVM), Gaussian Mixture Model (GMM), Feature Extraction, Background Noise Reduction, Dynamic Environments, Motion Analysis},
        month = {May},
        }