Image Recognition Methods Based on Convolutional Neural Networks

DOI

10.2991/978-94-6463-821-9_67How to use a DOI?

Keywords

Convolutional Neural Networks; Image Recognition; Product Detection

Abstract

In recent years, with the rapid development of artificial intelligence technology and deep learning technology, convolutional neural network has made a major breakthrough in the field of image recognition, and has become the mainstream method in this field. In this paper, the image recognition methods based on convolutional neural networks are reviewed systematically through three analytical dimensions. Firstly, The most important structures of convolutional neural networks and their functions are introduced, there are three main parts and they include these parts such as convolutional layer(Extract feature), pooling layer(reducing the dimension of sampling features) and fully connected layer( integrate the key features). Subsequently it elaborates the models and algorithms used by CNN in some common image recognition tasks in different scenarios such as text recognition, portrait recognition, and product detection and so on. Finally, this paper summarizes the advantages of CNN application at this stage and the future development trend of convolutional neural networks in image recognition is prospected.

Copyright

© 2025 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  - Weiqing Zhang
PY  - 2025
DA  - 2025/08/31
TI  - Image Recognition Methods Based on Convolutional Neural Networks
BT  - Proceedings of the 2025 2nd International Conference on Mechanics, Electronics Engineering and Automation (ICMEEA 2025)
PB  - Atlantis Press
SP  - 691
EP  - 701
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-821-9_67
DO  - 10.2991/978-94-6463-821-9_67
ID  - Zhang2025
ER  -