Handwritten Math Symbol Recognition Based on Multiple Machine Learning Techniques

DOI

10.2991/978-94-6463-300-9_24How to use a DOI?

Keywords

Machine Learning; Convolutional Neural Network; Deep Learning Model

Abstract

With the inherent complexity and variability of handwritten symbols, accurate recognition is crucial for various applications. This research aims to enhance the recognition of handwritten math symbols through a deep learning model named Convolutional Neural Network (CNN). In particular, the study utilizes a diverse dataset of approximately 370,000 images representing 82 math symbol categories, employing preprocessing and data augmentation techniques to enhance model performance. The implemented CNN model, built with TensorFlow, achieves an accuracy of 0.04. Comparative analysis with Random Forest, Support Vector Machine (SVM), and K-Nearest Neighbor categorization algorithm (KNN) demonstrates the CNN model's inferior performance in terms of accuracy, recall, and F1-scores. This highlights the need for further refinement and optimization of symbol recognition models. Future research should focus on larger and more diverse datasets, exploring different CNN architectures, and optimizing hyperparameters to improve classification accuracy. Despite its limitations, this study contributes to the field of handwritten math symbol recognition, emphasizing the importance of developing reliable and effective solutions for automated interpretation of mathematical expressions.

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  - Dazhi Song
PY  - 2023
DA  - 2023/11/27
TI  - Handwritten Math Symbol Recognition Based on Multiple Machine Learning Techniques
BT  - Proceedings of the 2023 International Conference on Image, Algorithms and Artificial Intelligence (ICIAAI 2023)
PB  - Atlantis Press
SP  - 236
EP  - 243
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-300-9_24
DO  - 10.2991/978-94-6463-300-9_24
ID  - Song2023
ER  -