Handwritten Math Symbol Recognition Based on Multiple Machine Learning Algorithms: A Comparative Study

DOI

10.2991/978-94-6463-300-9_67How to use a DOI?

Keywords

handwritten math symbol recognition; random forest; machine learning

Abstract

The primary focus of this research paper is addressing the difficulty of identifying handwritten mathematical symbols, which holds significant importance in diverse fields including education, scientific research, and data analysis. The recognition of these symbols is challenging due to their diverse appearance and inconsistencies in individual handwriting styles. Previous research has mainly focused on recognizing handwritten numerals, leaving a research gap in recognizing a wider range of math symbols. To bridge this gap, this study proposes a machine learning approach using the random forest algorithm. The approach utilizes a meticulously collected dataset from Kaggle. The dataset undergoes preprocessing steps including grayscale conversion, average pooling, and resizing to enhance recognition accuracy. The study implemented and evaluated K-Nearest Neighbors (KNN), decision tree, and random forest. The results demonstrate that the random forest model outperforms the other models, achieving a macro average accuracy of 0.99321 and a weighted average accuracy of 0.99412. The ensemble nature of the random forest algorithm contributes to its superior performance in handwritten math symbol recognition. The results support the hypothesis that the random forest model is highly effective in recognizing handwritten math symbols. The findings emphasize the significance of recognizing math symbols in developing intelligent systems for mathematical analysis and understanding and its vast potential for future application.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Zhihao Xu
PY  - 2023
DA  - 2023/11/27
TI  - Handwritten Math Symbol Recognition Based on Multiple Machine Learning Algorithms: A Comparative Study
BT  - Proceedings of the 2023 International Conference on Image, Algorithms and Artificial Intelligence (ICIAAI 2023)
PB  - Atlantis Press
SP  - 647
EP  - 655
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-300-9_67
DO  - 10.2991/978-94-6463-300-9_67
ID  - Xu2023
ER  -