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{172822,
        author = {Siddabattula Madhu and Ranga Jyothika Vijaya Sravya and Shaik Shahnaz Begum and Pilla Pavan Sailendra and Dr.D.Kavitha},
        title = {Gesture Controlled Virtual Mouse using Deep Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {9},
        pages = {1130-1136},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=172822},
        abstract = {As human-computer interaction is evolving rapidly, new approaches to touchless device control are becoming essential. Our system implements computer vision and machine learning techniques to create foundational technologies for future AR applications. Gesture-controlled virtual mouse system comprises three main components: gesture recognition, gesture training, and control implementation. Our system enables users to control computer operations through hand gestures captured by a webcam. At its core, the system uses a hand landmark detection model that identifies 21 key points on the hand, enabling precise tracking of finger positions and movements. The gesture recognition module analyzes these landmarks to classify hand poses into predefined gestures, while the custom gesture training component allows users to define and save their own gesture mappings. Our project provides real-time gesture detection and control by utilizing MediaPipe for hand tracking with the help of Computer Vision (CV) for video capturing and Machine Learning (ML) algorithms for customization. The implementation combines MediaPipe and Pybind11 to track hand movements accurately for smooth real-time detection. Our system offers intuitive cursor control, adjustable system parameters, and support for multiple hand tracking with dynamic gesture recognition. This comprehensive approach enables fluid and natural human-computer interaction.},
        keywords = {},
        month = {February},
        }