Gesture-Based Control of Presentation Slides using OpenCV

This research work proposes a Human Machine Interaction (HMI) system that enables users to control PowerPoint presentations using hand gestures. By analyzing hand movements captured by a camera and utilizing computer vision algorithms, the system accurately recognizes and interprets gestures as comm...

Full description

Saved in:
Bibliographic Details
Published in:2023 Second International Conference on Augmented Intelligence and Sustainable Systems (ICAISS) pp. 1786 - 1791
Main Authors: Vidya, M., Vineela, S., Sathish, P., Reddy, A. Supraja
Format: Conference Proceeding
Language:English
Published: IEEE 23.08.2023
Subjects:
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This research work proposes a Human Machine Interaction (HMI) system that enables users to control PowerPoint presentations using hand gestures. By analyzing hand movements captured by a camera and utilizing computer vision algorithms, the system accurately recognizes and interprets gestures as commands. The proposed system implementation incorporates machine learning techniques and the OpenCV module, allowing users to change slides without the need for keyboards or specialized gadgets. With real-time gesture recognition, users can control their presentations effortlessly and enhance accessibility. The system's potential applications include improving interaction with digital devices for individuals with limited access to traditional input devices.This proposed system highlights the significance of presentations and offers an innovative approach to nonverbal communication and human-computer interaction. By utilizing a camera and leveraging OpenCV Python, MediaPipe and PyWin32, the hand gesture presentation control system provides a user-friendly and efficient alternative for controlling PowerPoint slides. The system enhances the overall presentation experience by offering a more intuitive and natural means of interaction. The average accuracy of the proposed system is more than 93% for any distance from the camera.
DOI:10.1109/ICAISS58487.2023.10250520