Improved two-stage deep learning algorithm and lightweight YOLOv5n for classifying cottonseed damage
Authors:
- Weilong HeWHWeilong He
- Fan WuFWFan Wu
- Lori Unruh SnyderLSLori Unruh Snyder
- Jean ChengJCJean Cheng
- Evelynn WilcoxEWEvelynn Wilcox
- Lirong XiangLXLirong Xiang
Open Access
- 7 February 2025
- journal article
- Published by Elsevier in Computers and Electronics in Agriculture
- Vol. 232
Abstract
No abstract availableFunding Information
- National Institute of Food and Agriculture (7005224)
- U.S. Department of Agriculture
- Cotton (PAM-P23-001629)
This publication has 19 references indexed in Scilit:
- Nondestructive prediction of pepper seed viability using single and fusion information of hyperspectral and X-ray imagesSensors and Actuators A: Physical, 2022
- A novel deep learning based approach for seed image classification and retrievalComputers and Electronics in Agriculture, 2021
- World Cotton Production and Consumption: An Overview2020
- Identification of haploid and diploid maize seeds using convolutional neural networks and a transfer learning approachComputers and Electronics in Agriculture, 2019
- Multispectral imaging – a new tool in seed quality assessment?Seed Science Research, 2018
- Visualizing and Understanding Convolutional Networks2014
- Near-infrared hyperspectral imaging for predicting colour, pH and tenderness of fresh beefJournal of Food Engineering, 2012
- Recent Advances and Applications of Hyperspectral Imaging for Fruit and Vegetable Quality AssessmentFood and Bioprocess Technology, 2011
- Nondestructive measurement of fruit and vegetable quality by means of NIR spectroscopy: A reviewPostharvest Biology and Technology, 2007
- Recent developments in the applications of image processing techniques for food quality evaluationTrends in Food Science & Technology, 2004