Comparative analysis of CNN models for handwritten digit recognition
Krystyna Lidia Banaszewska
s100787@pollub.edu.plLublin University of Technology (Poland)
Małgorzata Plechawska-Wójcik
Lublin University of Technology (Poland)
https://orcid.org/0000-0003-1055-5344
Abstract
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.
Keywords:
convolutional neural networks, handwriting classificationReferences
A. Przegalińska, L. Ciechanowski, Wykorzystanie algorytmów sztucznej inteligencji w instytucjach kultury, Ministerstwo Kultury i Dziedzictwa Narodowego, Ekspertyza Ministerialna, Warszawa, 2019-2020.
Google Scholar
P. Norvig, S. Russel, Artificial Intelligence: a modern approach, Fourth Edition, Pearson, University of California at Berkeley, 2021.
Google Scholar
K. Simonyan, A. Zisserman, Very Deep convolutional networks for large-scale image recognition, In International Conference on Learning Representations (ICLR) 6 (2016) 1-11.
Google Scholar
A. Krizhevsky, I. S Sutskever, G. E. Hinton, ImageNet Classification with Deep Convolutional Neural Networks, Communications of the ACM 6 (2017) 84-90.
Google Scholar
Lecture MIT 6.S191 (2023): Convolutional Neural Networks, Massachusetts Institute of Technology https://www.youtube.com/watch?v=NmLK_WQBxB4 [01.03.2024]
Google Scholar
Y. LeCun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition in Proceedings of the IEEE 11 (1998) 2278-2324.
Google Scholar
A. Baldominos, Y. Saez, P. Isasi, A Survey of handwritten character recognition with MNIST and EMNIST, Applied Sciences 9 (2019) 15-31.
Google Scholar
G. S. Handelman, et al. Peering into the black box of artificial intelligence: evaluation metrics of machine learning methods, American Journal of Roentgenology 1 (2019) 38-43.
Google Scholar
J. Lever, M. Krzywinski, N. Altman, Classification evaluation, Nature Methods 13 (2016) 603-604.
Google Scholar
S. Mascarenhas, M. Agarwal, A comparison between VGG16, VGG19 and ResNet50, architecture frameworks for Image Classification In International conference on disruptive technologies for multi-disciplinary research and applications (Centon) IEEE 1 (2021) 96-99
Google Scholar
Authors
Małgorzata Plechawska-WójcikLublin University of Technology Poland
https://orcid.org/0000-0003-1055-5344
Statistics
Abstract views: 86PDF downloads: 101
