The study of Advantages and Applications of Convolutional Neural Networks in Computer Vision Tasks

DOI

10.2991/978-94-6463-300-9_104How to use a DOI?

Keywords

Convolutional Neural Network; Image classification; Lenet-5; Alexnet

Abstract

There are some deficiencies in the current Convolutional Neural Network (CNN) system. Some deep and complex CNN models take a long time to train, requiring a lot of computing resources and time for the training. At the same time, some CNN models may have overfitting problems, resulting in a decline in generalization ability. This paper provides an application case of CNN in computer vision tasks to help some people understand the actual application field of CNN. This paper takes Alexnet as an example, compares it with the Lenet-5 algorithm, and discusses the advantages of deep complex CNN models, especially in terms of transfer learning, which is very helpful for specific tasks in practical applications. In experimental results, through network architecture search and automated design methods, this paper finds a more suitable CNN architecture to improve model performance and generalization capabilities and explores how to improve the adaptability of the algorithm through structural updates and hyperparameter adjustments.

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  - Zhonghao Xie
PY  - 2023
DA  - 2023/11/27
TI  - The study of Advantages and Applications of Convolutional Neural Networks in Computer Vision Tasks
BT  - Proceedings of the 2023 International Conference on Image, Algorithms and Artificial Intelligence (ICIAAI 2023)
PB  - Atlantis Press
SP  - 1034
EP  - 1045
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-300-9_104
DO  - 10.2991/978-94-6463-300-9_104
ID  - Xie2023
ER  -