Roshani Gawand,
Sanskruti Zaware,
Prajakta Jadhav,
- Student, Department of Computer Engineering Mumbai University, Vishwaniketan’s Institute of Management Entrepreneurship and Engineering Technology [iMEET], Maharashtra, India
- Student, Department of Computer Engineering Mumbai University, Vishwaniketan’s Institute of Management Entrepreneurship and Engineering Technology [iMEET], Maharashtra, India
- Assistant Professor, Department of Computer Engineering Mumbai University, Vishwaniketan’s Institute of Management Entrepreneurship and Engineering Technology [iMEET], Maharashtra, India
Abstract
AirDraw represents a transformative advancement in artificial intelligence, creating fluid touch-free human-computer interfaces through real-time interpretation of hand gestures as precise design control signals. This paper introduces AirDraw—a revolutionary webcam-powered virtual canvas that redefines creative workflows and educational interactions. Particularly valuable for design students prototyping ideas, senior creators exploring digital art, and users with motor impairments who find traditional peripherals challenging, AirDraw delivers truly inclusive technology access. Unlike conventional gesture systems limited to rudimentary sketching with sparse color palettes and basic tools, AirDraw leverages OpenCV’s robust video processing pipeline and MediaPipe’s sophisticated 21-landmark hand tracking to achieve sub-50 ms response times. A standard webcam captures live video streams, enabling an intuitive gesture vocabulary: sweeping finger motions for smooth freehand sketching, pinch gestures for geometric primitives (circles, rectangles, polygons), thumb flicks for palette switching, and palm sweeps for precise erasing—all executed without physical contact. The gesture recognition engine maps natural hand trajectories to canvas rendering at 30+ FPS on consumer-grade laptops, while multi-modal operation extends functionality to immersive presentation control. Users advance PowerPoint slides with pointing gestures, zoom via spread-finger expansion, and annotate live during lectures, transforming static presentations into dynamic design demonstrations. User validation studies conducted in Pimpri, India (2026) with 50 diverse participants demonstrated 44% faster sketching task completion compared to mouse-based inputs, with 93% reporting enhanced creative flow. The system’s lightweight architecture maintains 89% gesture recognition accuracy under variable classroom lighting conditions, ensuring deployment feasibility across resource-constrained educational environments. AirDraw establishes a new benchmark for gesture-driven design interfaces, blending accessibility, performance, and immersive interaction. By eliminating hardware barriers and amplifying natural human motion, this innovation unlocks creative potential for designers and learners worldwide, while paving pathways for future multi-user collaborative sketching and augmented reality integration.
Keywords: Gesture recognition, virtual sketching, OpenCV, MediaPipe, immersive HCI, touchless design, educational technology
[This article belongs to Journal of Image Processing & Pattern Recognition Progress ]
References
- Ramachandra HV, Balaraju G, Deepika K, Navya MS, Sebastian SR. Virtual air canvas using OpenCV and MediaPipe. In: Proceedings of the 2022 International Conference on Futuristic Technologies (INCOFT); 2022; Belgaum, India. p.1-4. doi:10.1109/INCOFT55651.2022.10094385.
- Zaman Khan R. Hand gesture recognition: a literature review. Int J Artif Intell Appl. 2012;3(4):161-74. doi:10.5121/ijaia.2012.3412.
- Tripathi SL, Kumar OP, Stalin AD, Ali T, editors. Innovations in computer vision, communication systems, and computational intelligence. Boca Raton (FL): CRC Press; 2025. doi:10.1201/9781003724988.
- Tripathi R, Verma B. Survey on vision-based dynamic hand gesture recognition. Vis Comput. 2024;40(9):6171-99. doi:10.1007/s00371-023-03160-x.
- Ohn-Bar E, Trivedi MM. Hand gesture recognition in real time for automotive interfaces: a multimodal vision-based approach and evaluations. IEEE Trans Intell Transp Syst. 2014;15:2368-77. doi:10.1109/TITS.2014.2337331.
- Kalaivani KS, Deepanraj S, Veenas KS, Aswath M. Hand sign and gesture recognition using deep learning. In: Advanced AI and Data Science Applications. Boca Raton (FL): Auerbach Publications; 2025. p. 180-96. doi:10.1201/9781003543527-13.
- Subramaniam RR, Nethranand M, Srija M. Virtual painter using hand gesture recognition with OpenCV and MediaPipe. In: Proceedings of the International Conference on Computational Robotics, Testing and Engineering Evaluation (ICCRTEE); 2025. p. 1-6. doi:10.1109/ICCRTEE64519.2025.11053081.
- Kumar BA, Vinod T, Rao MS. Interaction through computer vision air canvas. In: Proceedings of the International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC); 2022. p. 1-3. doi:10.1109/ASSIC55218.2022.10088318.
- Shanthi R, Azeez SA, Kumar ND. Virtual painting through hand gestures: a machine learning J Ubiquitous Comput Commun Technol. 2024;6(1):39-49. doi:10.36548/jucct.2024.1.004.
- Khanum H, Pramod HB. Smart presentation control by hand gestures using computer vision and Google’s MediaPipe. Int Res J Eng Technol. 2022;9(7):2657-62.
- Gulati S, Rastogi AK, Virmani M, Jana R, Pradhan R, Gupta C. Paint/writing application through webcam using MediaPipe and OpenCV. In: Proceedings of the 2nd International Conference on Innovative Practices in Technology and Management (ICIPTM). Vol. 2; 2022. p. 287-91. doi:10.1109/ICIPTM54933.2022.9753939.
- Vasavi R, Rahul N, Snigdha A, Moses KJ, Simha SV. Painting with hand gestures using MediaPipe. Int J Innov Sci Res Technol. 2022;7(12):1285-91.
- Ming C, Yunbing Y. Perception-free calibration of eye opening and closing threshold for driver fatigue monitoring. IEEE Access. 2022;10:125469-76. doi:10.1109/ACCESS.2022.3225453
Journal of Image Processing & Pattern Recognition Progress
| Volume | 13 | |
| Issue | 02 | |
| Received | 05/03/2026 | |
| Accepted | 12/04/2026 | |
| Published | 10/05/2026 | |
| Publication Time | 66 Days |