Paper Contents
Abstract
This paper presents a novel approach to creating an intuitive and interactive air canvas system, leveraging OpenCV and MediaPipe for real-time hand gesture recognition. By integrating a hybrid combination of Convolutional Neural Networks (CNN) and Graph Convolutional Networks (GCN), the system achieves robust hand gesture analysis for a gesture-controlled display interface. The proposed system architecture enables efficient hand detection, tracking, and virtual drawing, supplemented by features such as dynamic color selection, brush thickness control, and canvas management. Experiments demonstrate the system's accuracy, responsiveness, and user satisfaction, highlighting its potential for applications in education, art, and virtual interaction.
Copyright
Copyright © 2025 Sakthi Ravi M. This is an open access article distributed under the Creative Commons Attribution License.
