English Character Recognition based on Deep Learning
- DOI
- 10.2991/978-94-6463-370-2_39How to use a DOI?
- Keywords
- Deep learning; English characters; Image enhancement; PCA
- Abstract
Since the traditional method of English character recognition had already reach its limit, there’s a need of a new pattern which can deal with various problems such as noises, distorted words, obstacles and more. Deep learning is a way out. The unique neural network structure of deep learning determines its advantages in the field of recognition, but at the same time, it will also face the interference of the noise of input data. Therefore, using the preprocessing algorithm for input images can effectively improve the recognition accuracy. In this paper, an English character recognition framework based on Convolutional Neural Network is proposed. The framework is based on VGG-19 model and was trained by datasets from ImageNet, a pretreatment based on principal component analysis is used to reduce noise in the image, and a untreated version of the same test set was entered into the model as a control group for comparison. In the experiment, the framework work successfully and shows a high accuracy in the self-collected test set. And with pretreatment dealt by PCA algorithm, a higher accuracy is shown.
- Copyright
- © 2024 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.
Cite this article
TY - CONF AU - Yuanhong Su PY - 2024 DA - 2024/02/14 TI - English Character Recognition based on Deep Learning BT - Proceedings of the 2023 International Conference on Data Science, Advanced Algorithm and Intelligent Computing (DAI 2023) PB - Atlantis Press SP - 369 EP - 378 SN - 1951-6851 UR - https://doi.org/10.2991/978-94-6463-370-2_39 DO - 10.2991/978-94-6463-370-2_39 ID - Su2024 ER -