Handwritten Digit Recognition With Machine Learning Algorithms

Abstract

Nowadays, the scope of machine learning and deep learning studies is increasing day by day. Handwriting recognition is one of the examples in daily life for this field of work. Data storage in digital media is a method that almost everyone is using nowadays. At the same time, it has become a necessity for people to store their notes in digital media and even take notes directly in the digital environment. As a solution to this need, applications have been developed that can recognize numbers, characters, and even text from handwriting using machine learning and deep learning algorithms. Moreover, these applications can recognize numbers, characters, and text from handwriting and convert them into visual characters. This project, investigated the performance comparison of machine learning algorithms commonly used in handwriting recognition applications and which of them are more efficient. As a result of the study, the accuracy was 98.66% with artificial neural network, 99.45% with convolutional neural network, 97.05% with K-NN, 83.57% with Naive Bayes, 97.71% with support vector machine and 88.34% with decision tree. This study also developed a handwriting recognition system for numbers similar to these mentioned applications. A desktop application interface was developed for end users to show the instant performance of some of these algorithms and allow them to experience the handwriting recognition system.

Keywords

• Machine Learning
• Handwriting Recognition
• Deep Learning
• MNIST

References

1. I. S. MacKenzie and K. Tanaka-Ishii, Text entry systems: mobility, accessibility, universality. San Francisco, Calif: Morgan Kaufmann, 2007. doi: 10.1016/B978-0-12-373591-1.X5000-1.
2. P. Duygulu, “El Yazısı Tanıma,” in Bilişim Ansiklopedisi, Papatya Yayıncılık, 2006.
3. M. R. Shamsuddin, S. Abdul-Rahman, and A. Mohamed, “Exploratory Analysis of MNIST Handwritten Digit for Machine Learning Modelling,” Communications in Computer and Information Science, vol. 937, pp. 134–145, 2019, doi: 10.1007/978-981-13-3441-2_11.
4. A. F. M. Agarap, “An Architecture Combining Convolutional Neural Network (CNN) and Support Vector Machine (SVM) for Image Classification,” arXiv, pp. 5–8, 2019.
5. M. A. Günler Pirim, “Neural Network Based Feature Extraction for Handwriting Digit Recognition,” Ankara, 2017.
6. A. El-Sawy, M. Loey, and H. El-Bakry, “Arabic Handwritten Characters Recognition using Convolutional Neural Network,” WSEAS Transactions on Computer Research, vol. 5, pp. 11–19, 2017.
7. A. Salouhou, “Deep Learning Approaches in Handwritting Character Recognition and Image Classification,” Istanbul, 2019.
8. R. Karakaya, “Maki̇ne Öğrenmesi̇ Yöntemleri̇yle El Yazısı Tanıma,” Sakarya, 2020.

9. S. S. Mor, S. Solanki, S. Gupta, S. Dhingra, M. Jain, and R. Saxena, “Handwritten Text Recognition: With Deep Learning and Android,” International Journal of Engineering and Advanced Technology, vol. 8, no. 2, pp. 172–178, 2019.
10. “THE MNIST DATABASE of handwritten digits.” url: http://yann.lecun.com/exdb/mnist/ (accessed Nov. 08, 2020).
11. J. M. Banda, R. A. Angryk, and P. C. Martens, “Steps Toward a Large-Scale Solar Image Data Analysis to Differentiate Solar Phenomena,” Solar Physics, vol. 288, no. 1, pp. 435–462, 2013, doi: 10.1007/s11207-013-0304-x.
12. “Scikit-Learn.” url: https://scikit-learn.org/stable/modules/model_evaluation.html#precision-recall-f-measure-metrics (accessed Dec. 20, 2020).
13. “Thresholding Process.” url: http://www.atasoyweb.net/Otsu-Esik-Belirleme-Metodu (accessed Dec. 02, 2020).
14. A. Vinciarelli and J. Luettin, “A New Normalization Technique for Cursive Handwritten Words,” Pattern Recognition Letters, vol. 22, no. 9, pp. 1043–1050, 2001, doi: 10.1016/S0167-8655(01)00042-3.
15. B. Yılmaz, “Design of A Mobile Device Application with Handwriting Recognition to Make Learning Easy For Students Who Have Learning Disabilities,” Istanbul, 2014.
16. H. H. Çelik, “Recognition of Handwritten Numerals by Using Neural Network,” Istanbul, 1999.
17. O. A. Erdem and E. Uzun, “Turkish Times New Roman, Arial, And Handwriting Characters Recognition by Neural Network,” journal of the Faculty of Engineering and Architecture of Gazi University, vol. 20, no. 1, pp. 13–19, 2005.
18. H. A. Şahin, “Comparison of Artificial Neural Networks and Different Optimization Methods,” Samsun, 2020.
19. E. Öztemel, Yapay Si̇ni̇r Ağlari. İstanbul: Papatya Yayıncılık, 2012. [Online]. Available: http://papatyabilim.com.tr/PDF/yapay_sinir_aglari.pdf
20. B. Ma, X. Li, Y. Xia, and Y. Zhang, “Autonomous deep learning: A genetic DCNN designer for image classification,” Neurocomputing, vol. 379, pp. 152–161, 2020, doi: 10.1016/j.neucom.2019.10.007.
21. E. Yalçın, “Binary-Data Multi-Criteria Recommender Systems Based on Naive Bayes Classifier,” Eskişehir, 2016.
22. M. W. Berry and M. Browne, Eds., Lecture Notes In Data Mining. World Scientific, 2006.
23. F. Köktürk, “Comparing Classification Success of K-Nearest Neighbor, Artifical Neural Network and Decision Trees,” Zonguldak, 2012.
24. N. Turdaliev, “Destek Vektör Makineleri ile Otel Öneri Sistemi,” 2018.
25. C. D. Manning, P. Raghavan, and H. Schutze, Introduction to Information Retrieval. Cambridge University Press, 2008. Accessed: Feb. 10, 2021. [Online]. Available: https://nlp.stanford.edu/IR-book/information-retrieval-book.html
26. E. Dağdeviren, “El Yazısı Rakam Tanıma İçin Destek Vektör Makinelerinin ve Yapay Sinir Ağlarının Karşılaştırması,” 2013.
27. G. Sakkis, “A Memory-Based Approach to Anti-Spam Filtering for Mailing Lists.”
28. E. Taşcı and A. Onan, “The Investigation of Performance Effects of K-Nearest Neighbor Algorithm Parameters on Classification,” in Xviii. Akademi Bi̇li̇şi̇m Konferansı, 2016, p. 8.