Advancements and Challenges in Character Recognition: A Comparative Analysis of CNN and Deep Learning Approaches
This paper provides a comprehensive review of character recognition technologies, focusing on the application of Convolutional Neural Networks (CNN) and deep learning methodologies. Through an analysis of three key studies, the research highlights the strengths and limitations of current approaches....
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2025-01-01
|
| Series: | ITM Web of Conferences |
| Online Access: | https://www.itm-conferences.org/articles/itmconf/pdf/2025/01/itmconf_dai2024_03010.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This paper provides a comprehensive review of character recognition technologies, focusing on the application of Convolutional Neural Networks (CNN) and deep learning methodologies. Through an analysis of three key studies, the research highlights the strengths and limitations of current approaches. Study by Zib emphasizes the challenges in segmenting and recognizing English characters using CNN, revealing the need for supplementary techniques to mitigate errors. Research by Nikitha explores the impact of increasing the dimensionality of analysis, demonstrating that higher dimensions improve accuracy but also extend training times. Similarly, work conducted by Pradeep shows that larger vector sizes enhance recognition accuracy but at the cost of greater computational resources. The collective findings suggest that while CNN and deep learning models have significantly advanced character recognition, there remains a need for enhanced segmentation techniques and a balanced approach to optimizing training efficiency and accuracy. Future research should focus on integrating supportive methods to improve segmentation and finding an optimal trade-off between variable complexity and computational efficiency, thereby advancing the practical application of character recognition systems across various domains. |
|---|---|
| ISSN: | 2271-2097 |