Abstract :

Digit Recognition in real time through hand gestures has achieved great attention in machine learning and computer vision applications. This article focuses on identifying Bangla numerals in the air using hand motions. This research leads to the stairwell, allowing for more investigation in the same subject for various Bangla characters and even phrases. The major issue, however, is coping with the wide range of handwriting styles employed by various users. Many studies have been done on the identification of Bangla handwritten digits, but none has proven successful at recognizing Bangla digits in real time using hand gestures in the air. As a result, this article describes the creation of a Bangla digit recognition model that employs a Convolution Neural Network (CNN) to predict Bangla digits by observing hand movements in the air space.  After a thorough examination, the suggested system attained a 98.37% accuracy on the BanglaLekha-Isolated dataset.

---

Keywords :

Convolution Neural Network (CNN); Human-computer interaction (HCI); Multilayer Perceptron (MLP); Rectified Layer Unit (ReLU); Real time Bangla Digit Recognition through Hand Gestures (RBDRHG).

---

References :

1. Chaudhuri, “A complete handwritten numeral database of Bangla–amajor Indic script,” in Proceedings of Tenth International Workshop onFrontiers in Handwriting Recognition, Suvisoft, Baule, France, October2006.
2. Cortes and V. Vapnik, “Support­vector networks,” Machine Learning,vol. 20, no. 3, pp. 273–297, 1995.
3. ­L. Liu and C. Y. Suen, “A new benchmark on the recognition ofhandwritten Bangla and Farsi numeral characters,” Pattern Recognition,vol. 42, no. 12, pp. 3287–3295, 2009J. Clerk Maxwell, A Treatise on Electricity and Magnetism, 3rd ed., vol. 2. Oxford: Clarendon, 1892, pp.68–73.
4. E. Rumelhart, J. L. McClelland, P. R. Group et al., Parallel DistributedProcessing, vol. 1, MIT Press, Cambridge, MA, USA, 1987.
5. A. Khan, A. Al Helal, and K. I. Ahmed, “Handwritten Bangla digitrecognition using sparse representation classifier,” in Proceedings of2014 International Conference on Informatics, Electronics and Vision(ICIEV), pp. 1–6, IEEE, Dhaka, Bangladesh, May 2014.
6. ­W. Xu, J. Xu, and Y. Lu, “Handwritten Bangla digit recognition usinghierarchical Bayesian network,” in Proceedings of 3rd InternationalConference on Intelligent System and Knowledge Engineering, vol. 1,pp. 1096–1099, IEEE, Xiamen, China, November 2008.
7. Khalil Ahammad, Jubayer Ahmed Bhuiyan Shawon, Partha Chakraborty,Md Jahidul Islam, Saiful Islam, “Recognizing Bengali Sign LanguageGestures for Digits in Real Time using Convolutional Neural Network,”International Journal of Computer Science and Information Security,Vol. 19 No. 1 JANUARY 2021.
8. Das, B. Das, R. Sarkar, S. Basu, M. Kundu, and M. Nasipuri,“Handwritten Bangla basic and compound character recognition usingMLP and SVM classifier,” 2010.
9. Das, R. Sarkar, S. Basu, M. Kundu, M. Nasipuri, and D. K. Basu, “Agenetic algorithm based region sampling for selection of local featuresin handwritten digit recognition application,” Applied Soft Computing,vol. 12, no. 5, pp. 1592–1606, 2012.
10. Surinta, L. Schomaker, and M. Wiering, “A comparison of featureand pixel­based methods for recognizing handwritten Bangla digits,” inProceedings of 12th International Conference on Document Analysis andRecognition (ICDAR), pp. 165–169, IEEE, Buffalo, NY, USA, 2013.
11. Basu, N. Das, R. Sarkar, M. Kundu, M. Nasipuri, and D. K. Basu, “AnMLP based approach for recognition of handwritten Bangla numerals,”2012.
12. Pal and B. Chaudhuri, “Automatic recognition of unconstrainedoff­line Bangla handwritten numerals,” in Proceedings of Advancesin Multimodal Interfaces–ICMI 2000, pp. 371–378, Springer, Beijing,China, October 2000.