International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | AeroText: Air-Writing Recognition Based on Deep Convolutional Neural Network |
|---|---|
| ABSTRACT | This paper presents AEROText, a novel human computer interaction system designed to interpret in-air finger gestures as written characters, captured in real-time via a standard webcam. The system facilitates a touchless and intuitive method of text input, thereby eliminating the need for physical writing instruments. The architecture incorporates a secure user management module with One-Time Password (OTP) email verification, a robust finger tracking algorithm employing OpenCV for hand segmentation and contour analysis, and a deep learning model for character recognition. The core of the recognition engine is a Convolutional Neural Network (CNN), constructed with PyTorch and trained on the EMNIST dataset, which accurately translates mid-air finger trajectories into digital text. The system demonstrates successful recognition of English alphabets and exhibits a unique capability by mapping certain predictions to the Devanagari script, indicating its potential for multilingual applications. This work constitutes a comprehensive proof-of-concept for the development of accessible, next-generation HCI interfaces, with significant implications for assistive technology and public interactive systems. Index Terms—human-computer interaction, computer vision, deep learning, air handwriting, gesture recognition, OpenCV, PyTorch, touchless interface, EMNIST |
| AUTHOR | SAMYAK KAMBLE, SAHIL SHARMA, RITESH ZANWAR, PROF. KIRAN PATIL Department of Information Technology, G.H. Raisoni College of Engineering and Management, Pune, India |
| VOLUME | 182 |
| DOI | DOI: 10.15680/IJIRCCE. 2026.1403098 |
| pdf/98_AeroText Air-Writing Recognition Based on Deep Convolutional Neural Network.pdf | |
| KEYWORDS | |
| References | [1] G. Bradski, “The OpenCV Library,” Dr. Dobb’s Journal of Software Tools, vol. 25, no. 1, pp. 120–123, 2000. [2] A. Paszke et al., “PyTorch: An Imperative Style, High-Performance Deep Learning Library,” in Advances in Neural Information Processing Systems, vol. 32, pp. 8024–8035, 2019. [3] G. Cohen, S. Afshar, J. Tapson, and A. van Schaik, “EMNIST: An Extension of MNIST to Handwritten Letters,” arXiv preprint arXiv:1702.05373, 2017. [4] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-Based Learning Applied to Document Recogni-tion,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2324, 1998. [5] J. C. Russ, The Image Processing Handbook, 7th ed. Boca Raton, FL: CRC Press, 2016. [6] R. C. Gonzalez and R. E. Woods, Digital Image Processing, 4th ed. Pearson, 2018. [7] S. Mitra and T. Acharya, “Gesture Recognition: A Survey,” IEEE Transactions on Systems, Man, and Cy-bernetics, Part C, vol. 37, no. 3, pp. 311–324, May 2007. [8] P. Viola and M. Jones, “Rapid Object Detection Using a Boosted Cascade of Simple Features,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), vol. 1, pp. I-511–I-518, 2001. [9] K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), pp. 770–778, 2016. [10] D. G. Lowe, “Distinctive Image Features from Scale-Invariant Keypoints,” International Journal of Com-puter Vision, vol. 60, no. 2, pp. 91–110, 2004. [11] M. Z. Alom et al., “The History Began from AlexNet: A Comprehensive Survey on Deep Learning Ap-proaches,” arXiv preprint arXiv:1803.01164, 2018. [12] S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 6, pp. 1137–1149, 2017. [13] T.-Y. Lin et al., “Microsoft COCO: Common Objects in Context,” in Proc. European Conf. Computer Vision (ECCV), pp. 740–755, 2014. [14] D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” arXiv preprint arXiv:1412.6980, 2014. [15] J. R. Quinlan, “Induction of Decision Trees,” Machine Learning, vol. 1, no. 1, pp. 81–106, 1986. [16] C. Cortes and V. Vapnik, “Support-Vector Networks,” Machine Learning, vol. 20, no. 3, pp. 273–297, 1995. [17] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” in Advances in Neural Information Processing Systems, vol. 25, pp. 1097–1105, 2012. [18] S. Ioffe and C. Szegedy, “Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift,” in Proc. Int. Conf. Machine Learning (ICML), pp. 448–456, 2015. [19] J. Shotton et al., “Real-Time Human Pose Recognition in Parts from Single Depth Images,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), pp. 1297–1304, 2011. [20] M. Young, The Technical Writer’s Handbook. Mill Valley, CA: University Science, 1989. |
