Studies on the Application of Machine Learning and Deep Learning in Image Recognition

DOI

10.2991/978-94-6463-304-7_12How to use a DOI?

Keywords

Machine Learning; Deep Learning; Support Vector Machine; Deep Belief Network; Image Recognition

Abstract

In recent years, with the rapid development of the Internet and mobile technology, the image data in the network has shown explosive growth. It has been widely used in social security, military security, information security, identity authentication, and traffic supervision. Image data is simple and intuitive, contains rich information, and is widely used as a carrier of information exchange. Especially in recent years, the application of machine learning algorithms in the field of image recognition has provided new technical means for image classification, recognition, and feature extraction, making it a research hotspot in this field. Image recognition has received more and more attention due to its broad application value in agriculture, commerce, military affairs, and daily life. The technology serves as the basis of machine vision. For computers, there is no direct connection between the underlying features of an image and the high-level image semantics, so solving the "semantic gap" is the primary focus and difficulty of image recognition. The development of machine learning has gone through two stages shallow learning and deep learning. Experts and scholars have proposed many algorithm models and achieved many achievements in image recognition, speech recognition, and artificial intelligence. In recent years, with the successful promotion and application of deep learning technology in various application fields, image target recognition technology based on deep learning has gradually become the focus of many researchers. Different algorithms have also achieved varying degrees of research progress in image recognition. This paper analyzes and introduces the working principles of two typical machine learning algorithms (Support Vector Machine and Deep Belief Network). The conclusion of this paper confirms the effectiveness and vast application space of virtual samples in machine learning algorithms. Also, it provides powerful help for solving minor sample problems in machine learning.

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  - Zongjian Wu
PY  - 2023
DA  - 2023/12/04
TI  - Studies on the Application of Machine Learning and Deep Learning in Image Recognition
BT  - Proceedings of the 3rd International Conference on Digital Economy and Computer Application (DECA 2023)
PB  - Atlantis Press
SP  - 96
EP  - 107
SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6463-304-7_12
DO  - 10.2991/978-94-6463-304-7_12
ID  - Wu2023
ER  -