Available Issues
Authors:
| Fahmida Islam | Department of Computer Science and Engineering, The People’s University of Bangladesh |
| Prome Saha Resha | Department of Computer Science and Engineering, The People’s University of Bangladesh |
https://oajea.hafizlab.com/article/01-02-004 
https://doi.org/10.64886/oajea.0102.004 
Index Terms:
English alphabets, Sign Language, TensorFlow, CNN, OpenCVAbstract:
Pattern recognition, computer vision, and image processing all are benefitted from hand-written alphabet recognition and categorization. A profusion of applications based on this domain have been created in the last few decades, such as sign identification, multilingual learning systems, and so on. This research shows how neural networks may be used to create a system that recognizes hand-written English alphabets in the air using hand gestures. Because of the acoustic similarities between the letters of the alphabet, this is a challenging undertaking to complete. The main problem is dealing with enormous different ways to write used by multiple peoples. There are a variety of alphabet-writing approaches in these complicated handwritten styles. The recognition of handwritten English alphabets has been the subject of several research studies. Several studies have been conducted on this subject, but none have proven effective in detecting English alphabets instantly moving your fingers in the breeze. Therefore, this article explains how to create an English Alphabet model of awareness that uses a Convolution Neural Network (CNN) to identify English alphabets based on hand motions the gap in the air. After a full analysis, this recommended approach achieved 93.08\% accurate responses over the EMNIST dataset.Conclusion:
Despite advances in object recognition techniques, the challenge of Realtime English Alphabet Recognition through Hand Gestures (REARG) remains unsolved due to a number of issues. In reality, many of the most advanced existing techniques fail to deliver satisfactory outcomes. This work offers a CNN paradigm for handwritten digit recognition, written on air gathered using a camera, which functions well in real time in recognizing the majority of the input letters. The results show that the test accuracy rate for detecting 26 English alphabets is 93.08 percent. This clearly demonstrates that basic CNNs are capable of tackling even the most difficult categorization problems. Furthermore, this research endeavor will serve as a model for future projects that will shed light on this topic for future machine learning researchers. I intend to expand our research into Real Time English Character Recognition using hand gestures in the next stage of our work (RECRG). Recognizing handwriting in real time utilizing OpenCV is one of the remaining hurdles, even though I can retrain our system for the character dataset sections of the BanglaLekhaIsolated dataset. Our goal is to develop a technology that allows for greater human machine connection.License:
Articles published in OAJEA are licensed under a Creative Commons Attribution 4.0 International License.Cite This Paper:
Fahmida Islam,Prome Saha Resha, “Real Time English Alphabet Recognition Through Hand Gestures on Air Using Deep Learning and OpenCV”, Open Access Journal on Engineering Applications (OAJEA), Volume No. 01, Issue No. 02, Page 34-41, March, 2026. https://doi.org/10.64886/oajea.0102.004Reference:
P. R. and S. S, "Online and off-line handwriting recognition: a comprehensive survey," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, pp. 63-84. https://doi.org/10.1109/34.824821
Cohen G, S. A. J. T. and A. V. T., "EMNIST: Extending MNIST to handwritten letters," IEEE International Joint Conference on Neural Networks (IJCNN), pp. 2921-2926, 2017
Claus B, H. B. and B. H., "Online handwriting recognition with support vector machines - a kernel approach," Eighth International Workshop on Frontiers in Handwriting Recognition, pp. 49-54, 2002
English at Ethnologue, 22nd ed., 2019
Ethnologue, 2010. https://doi.org/10.1080/17449057.2010.502305
C. L. and C. Y. Suen, "A new benchmark on the recognition of handwritten Bangla and Farsi numeral characters," Pattern Recognition, vol. 42, no. 12, pp. 3287–3295, 2009. https://doi.org/10.1016/j.patcog.2008.10.007
N. Das et al., "A genetic algorithm based region sampling for selection of local features in handwritten digit recognition application," Applied Soft Computing, vol. 12, no. 5, pp. 1592–1606, 2012. https://doi.org/10.1016/j.asoc.2011.11.030
J.W. Xu and Y. L., "Handwritten Bangla digit recognition using hierarchical Bayesian network," 3rd International Conference on Intelligent System (ISKE), Xiamen, China, 2008. https://doi.org/10.1109/ISKE.2008.4731093
A. A. H. Khan et al., "Handwritten Bangla digit recognition using sparse representation classifier," IEEE Conference, Dhaka, Bangladesh, 2014
N. Das et al., "Handwritten Bangla basic and compound character recognition using MLP and SVM classifier," 2010. https://doi.org/10.48550/arXiv.1002.4040
J. A. J. Alsayaydeh et al., "Handwritten text recognition system using Raspberry Pi with OpenCV TensorFlow," International Journal of Electrical and Computer Engineering, vol. 15, no. 2, p. 2291, 2025. https://doi.org/10.11591/ijece.v15i2.pp2291-2303
M. A. M. Ali et al., "Real-Time recognition of NZ sign language alphabets by optimal use of machine learning," Bioengineering, vol. 12, no. 10, p. 1068, 2025. https://doi.org/10.3390/bioengineering12101068
A. A. Qedear et al., "Real-Time Air-Writing Recognition for Arabic letters using deep learning," Sensors, vol. 24, no. 18, p. 6098, 2024. https://doi.org/10.3390/s24186098
Y. R. Shravya et al., "Air writing with Effective Communication Enhancement for Dyslexic Learners," Procedia Computer Science, vol. 235, pp. 2056–2068, 2024. https://doi.org/10.1016/j.procs.2024.04.195
K. M. O. N. et al., "Recognition of Arabic Air-Written Letters: machine learning, convolutional neural networks, and OCR techniques," Sensors, vol. 23, no. 23, p. 9475, 2023. https://doi.org/10.3390/s23239475
Journal Information
| Frequency: Quarterly |
| Submission to First Decision: 7 days |
| Submission to Acceptance: 30 days |
| Accept to Publish: 15 days |
| Article Processing Charges (APCs): None |
