Wheat kernels quality testing based on improved YOLOX

Shiyuan Liu; Huihua Yang; WenYi Zhao; Xi Han

doi:10.1117/12.2657596

18 October 2022 Wheat kernels quality testing based on improved YOLOX

Shiyuan Liu, Huihua Yang, WenYi Zhao, Xi Han

Proceedings Volume 12349, International Conference on Agri-Photonics and Smart Agricultural Sensing Technologies (ICASAST 2022); 123490B (2022) https://doi.org/10.1117/12.2657596
Event: International Conference on Agri-Photonics and Smart Agricultural Sensing Technologies (ICASAST 2022), 2022, Zhengzhou, China

Abstract

The rapid and accurate detection of the quality of wheat kernels, which is the raw material of flour, has been attracting much attention. Some detection methods have been proposed in the last few years. However, these algorithms are incapable of meeting both the requirements of speed and accuracy simultaneously. In order to meet these requirements, we propose a YOLOX_lite model based on the improved YOLOX model. By studying the influence of different color backgrounds on the imaging effect, we design a machine vision system and construct a wheat kernel dataset containing 1746 images of 7844 wheat kernels. The dataset includes moldy damaged wheat kernels, scabbed wheat kernels, sproutdamaged wheat kernels, and undamaged wheat kernels. Using this dataset, we analyze and research the most advanced object detection algorithms. Through optimization operations such as adjusting the CSPDarknet structure and FPN-PAN structure for wheat kernel quality detection. Experimental results show that the proposed method achieves 97.8% accuracy on four kinds of wheat kernels, and the detection speed on the GTX1050 graphics card reaches 49.5FPS, an improvement of 39% to YOLOX_s, which indicates that the YOLOX_lite model meets the requirements of high efficiency, accuracy and reliability applied to the wheat kernel detection system.

Citation Download Citation

Shiyuan Liu, Huihua Yang, WenYi Zhao, and Xi Han "Wheat kernels quality testing based on improved YOLOX", Proc. SPIE 12349, International Conference on Agri-Photonics and Smart Agricultural Sensing Technologies (ICASAST 2022), 123490B (18 October 2022); https://doi.org/10.1117/12.2657596

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

RGB color model

Detection and tracking algorithms

Convolution

Visualization

Machine vision

Reliability

Scene classification

Show All Keywords

Keywords/Phrases

Search In:

Publication Years