| Issue |
ITM Web Conf.
Volume 43, 2022
The International Conference on Artificial Intelligence and Engineering 2022 (ICAIE’2022)
|
|
|---|---|---|
| Article Number | 01008 | |
| Number of page(s) | 6 | |
| DOI | https://doi.org/10.1051/itmconf/20224301008 | |
| Published online | 14 March 2022 | |
Character Recognition Using Pre-Trained Models and Performance Variants Based on Datasets Size: A Survey
1 Department of Mathematics and Computer Science, Data Sciences and Competitive Intelligence team (DSCI), Laboratory of applied Science, National School of Applied Science, Al Hoceima, Morocco
2 Department of Mathematics and Computer Science, Data Sciences and Competitive Intelligence team (DSCI), Laboratory of applied Science, National School of Applied Science, Al Hoceima, Morocco
3 Computer Science department faculty of science and technology Errachidia, Morocco
4 Computer Science, Signals, Automation and Cognitivism Laboratory Faculty of science, Dhar El Mahraz University Fez, Maroc
The most efficient and beneficial mechanism to the feature of extracting data from an image, has been the Convolutional Neural Network (CNN) and it is used in many fields (Optical character recognition, image classification, object recognition and Facial recognition etc.). In this papier, we studied the character classification problems, using pre-trained models based on Convolutional Neural Network (CNN), and how the performance can change the outcome of dataset that is given. For that, we have used five pre-trained models’ such as VGG16/19, ResNet, Xception et MobileNet. The experiment shows that Xception had the best performance rate compared to other models for all datasets, VGG16/19 performance rate are variants depend on dataset. However, Experiments shows that ResNet achieve the worst accuracy rate compared to other methods.
Key words: Character detection / Character recognition / Image classification / pre-trained models / Keras Library / Transfer Learning
© The Authors, published by EDP Sciences, 2022
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.