Research on Image Classification Based on Convolutional Neural Network

DOI

10.2991/978-94-6463-300-9_99How to use a DOI?

Keywords

Image classification; LeNet-5; AlexNet; Visual Geometry Group Network; Residual Neural Network

Abstract

The convolutional neural networks (CNNs) are widely used for image classification tasks because CNNs can successfully capture spatial hierarchies and patterns in images. A dataset can be utilized to evaluate the performance of various types of CNNs. To compare the effectiveness of four CNN models for image classification on specific datasets, this study utilizes the MNIST dataset to train four classic CNNs and subsequently compares and evaluates the classification outcomes. The four models are LeNet (LeNet), AlexNet, Visual Geometry Group Network (VGGNet) and Visual Geometry Group Network (ResNet). In order to address the performance of four neural network models in image classification, a controlled experiment is conducted. The results of this study indicate LeNet is the most suitable model on the MNIST dataset. While the other three models also exhibit commendable classification results, they fall short of the overall performance achieved by the LeNet model. The other three models can be used with challenging datasets.

Copyright

© 2023 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.

Download article (PDF)

TY  - CONF
AU  - Ziling Luo
PY  - 2023
DA  - 2023/11/27
TI  - Research on Image Classification Based on Convolutional Neural Network
BT  - Proceedings of the 2023 International Conference on Image, Algorithms and Artificial Intelligence (ICIAAI 2023)
PB  - Atlantis Press
SP  - 980
EP  - 990
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-300-9_99
DO  - 10.2991/978-94-6463-300-9_99
ID  - Luo2023
ER  -