This paper presents an interactive virtual painting system that utilizes computer vision and hand-tracking technologies to create a natural and intuitive digital art experience. The system employs Media Pipe for real-time hand landmark detection and Open CV for image processing, allowing users to paint on a virtual canvas using hand gestures. The implementation includes features such as color selection, canvas cleaning, and comprehensive analytics of user interactions. Real- time visualization of hand tracking data and movement patterns provides insight into user behavior and system performance. The system demonstrates successful integration of computer vision techniques with interactive graphics, achieving responsive performance with minimal latency. The analytics reveal patterns in user behavior, color preferences, and gesture accuracy, contributing to the understanding of human-computer interaction in the creation of virtual art.
Hand tracking, virtual painting, computer vision, gesture recognition, interactive art, MediaPipe, OpenCV, real-time processing, human-computer interaction, digital art creation, machine learning, artificial intelligence, computer graphics, image processing, motion tracking, gesture-based interfaces, visual computing, interactive systems, user experience design, deep learning, neural networks, real-time rendering, 3D visualization, augmented reality, digital media, user interaction analysis, performance optimization, visual analytics, computer-aided art, creative computing
IRE Journals:
Sameer Mankotia
"Deep Learning-Powered Interactive Art: A Framework for Gesture Recognition and Multi-Style Digital Painting using Media Pipe and Tensor Flow" Iconic Research And Engineering Journals Volume 8 Issue 6 2024 Page 508-522
IEEE:
Sameer Mankotia
"Deep Learning-Powered Interactive Art: A Framework for Gesture Recognition and Multi-Style Digital Painting using Media Pipe and Tensor Flow" Iconic Research And Engineering Journals, 8(6)