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{197906,
        author = {J Priyadharshini and E Yeswanth and R Iniya Akash and S Sivaranjani and L Vasundra},
        title = {TOUCH – FREE HCI USING CNN},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {10062-10066},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=197906},
        abstract = {A growing world need touchless and smart ways to interact with computers. Traditional input devices like the mouse and keyboard require physical contact, which is not suitable for hygienic places, smart environments, or for people who need assistive technologies. To solve this problem, this project introduces a Touch free Real-time virtual Using Hand Gestures, developed using CNN in Python.
The system focuses on improving usability, flexibility, long-distance interaction, and security. The proposed system allows users to control mouse functions such as moving the cursor, clicking, dragging, long pressing, scrolling, volume levels, and multiple accessing files using simple hand gestures. A camera captures live video of the user’s hand, and the video is processed continuously to detect and recognize gestures. Instead of depending on a fixed number of fingers, the system understands gestures based on hand shape and movement.
It can also work for users with flexible hands, bent fingers, or even six fingers. One of the main highlights of this project is its ability to support hand gesture control from a long distance. With the help of high-quality or zoom-enabled cameras, the system is designed to work from a distance of about 30 to 40 feet. The system automatically adjusts cursor movement speed and sensitivity based on how far the user is from the camera, ensuring smooth and accurate control. The project also includes basic security features to protect the system and user data.
The camera checks the background before allowing gesture control, and unauthorized access can block the system from working. File access through gestures is controlled, and no camera video is stored, which helps protect user privacy. Overall, this virtual mouse system provides a simple, safe, and touchless way to interact with computers.
It can be used in places like smart classrooms, offices, hospitals, assistive technology systems, and secure work areas. The system can also be improved further in the future with better hardware, support for multiple users, and stronger security features.},
        keywords = {Touch–Free Interaction, HCI, Media pipe, CNN, Gestures},
        month = {April},
        }