Research on image recognition technology based on improved YOLOv5

Jianfeng Chen; Yixiang Wang

doi:10.1117/12.3055396

12 December 2024 Research on image recognition technology based on improved YOLOv5

Jianfeng Chen, Yixiang Wang

Proceedings Volume 13439, Fourth International Conference on Testing Technology and Automation Engineering (TTAE 2024); 134392L (2024) https://doi.org/10.1117/12.3055396
Event: Fourth International Conference on Testing Technology and Automation Engineering (TTAE 2024), 2024, Xiamen, China

Abstract

In order to improve the performance of image recognition, the traditional YOLOv5s network was improved and applied to wheat pest recognition. Based on the analysis of YOLOv5s, the activation function, attention module, feature fusion network and loss function are improved. By comparing YOLOv5s with other image recognition technologies, it is pointed out that the improved YOLOv5s network has good performance in three aspects: accuracy, recall rate and average accuracy. Compared with other target recognition algorithms, the improved YOLOv5s network can be better applied to target recognition in complex scenes containing small targets. It has certain practical value for improving the efficiency of wheat pest detection and realizing the transformation from traditional agriculture to modern agriculture.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Jianfeng Chen and Yixiang Wang "Research on image recognition technology based on improved YOLOv5", Proc. SPIE 13439, Fourth International Conference on Testing Technology and Automation Engineering (TTAE 2024), 134392L (12 December 2024); https://doi.org/10.1117/12.3055396

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available