Comparative analysis of CNN models for handwritten digit recognition
The paper discusses the subject of convolutional neural networks used for handwritten digit classification. The purpose of the research is to evaluate the accuracy, performance, training, and classification time of three OCR networks (VGG-16, VGG-19 and AlexNet) and compare them with each other whi...
Saved in:
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Lublin University of Technology
2024-09-01
|
Series: | Journal of Computer Sciences Institute |
Subjects: | |
Online Access: | https://ph.pollub.pl/index.php/jcsi/article/view/6239 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
_version_ | 1832570001973837824 |
---|---|
author | Krystyna Banaszewska Małgorzata Plechawska-Wójcik |
author_facet | Krystyna Banaszewska Małgorzata Plechawska-Wójcik |
author_sort | Krystyna Banaszewska |
collection | DOAJ |
description |
The paper discusses the subject of convolutional neural networks used for handwritten digit classification. The purpose of the research is to evaluate the accuracy, performance, training, and classification time of three OCR networks (VGG-16, VGG-19 and AlexNet) and compare them with each other while selecting the most optimal one. The popular MNIST dataset of 70,000 images was used for the study. For each model, a preliminary study was conducted to determine the optimal parameters in the form of the number of input data and number of training epochs. The result of the work indicates that, despite the longer training and classification time, the AlexNet model achieved the highest precision, recall, and F1-score, indicating its ability to effectively classify images.
|
format | Article |
id | doaj-art-632a570f00f64bd0ae1f031ed5a586bb |
institution | Kabale University |
issn | 2544-0764 |
language | English |
publishDate | 2024-09-01 |
publisher | Lublin University of Technology |
record_format | Article |
series | Journal of Computer Sciences Institute |
spelling | doaj-art-632a570f00f64bd0ae1f031ed5a586bb2025-02-02T18:01:26ZengLublin University of TechnologyJournal of Computer Sciences Institute2544-07642024-09-013210.35784/jcsi.6239Comparative analysis of CNN models for handwritten digit recognitionKrystyna Banaszewska0Małgorzata Plechawska-Wójcik1https://orcid.org/0000-0003-1055-5344Lublin University of TechnologyLublin University of Technology The paper discusses the subject of convolutional neural networks used for handwritten digit classification. The purpose of the research is to evaluate the accuracy, performance, training, and classification time of three OCR networks (VGG-16, VGG-19 and AlexNet) and compare them with each other while selecting the most optimal one. The popular MNIST dataset of 70,000 images was used for the study. For each model, a preliminary study was conducted to determine the optimal parameters in the form of the number of input data and number of training epochs. The result of the work indicates that, despite the longer training and classification time, the AlexNet model achieved the highest precision, recall, and F1-score, indicating its ability to effectively classify images. https://ph.pollub.pl/index.php/jcsi/article/view/6239convolutional neural networks handwriting classification |
spellingShingle | Krystyna Banaszewska Małgorzata Plechawska-Wójcik Comparative analysis of CNN models for handwritten digit recognition Journal of Computer Sciences Institute convolutional neural networks handwriting classification |
title | Comparative analysis of CNN models for handwritten digit recognition |
title_full | Comparative analysis of CNN models for handwritten digit recognition |
title_fullStr | Comparative analysis of CNN models for handwritten digit recognition |
title_full_unstemmed | Comparative analysis of CNN models for handwritten digit recognition |
title_short | Comparative analysis of CNN models for handwritten digit recognition |
title_sort | comparative analysis of cnn models for handwritten digit recognition |
topic | convolutional neural networks handwriting classification |
url | https://ph.pollub.pl/index.php/jcsi/article/view/6239 |
work_keys_str_mv | AT krystynabanaszewska comparativeanalysisofcnnmodelsforhandwrittendigitrecognition AT małgorzataplechawskawojcik comparativeanalysisofcnnmodelsforhandwrittendigitrecognition |