首页|A novel nondestructive detection approach for seed cotton lint percentage using deep learning

A novel nondestructive detection approach for seed cotton lint percentage using deep learning

扫码查看
原文链接
  • 国家科技期刊平台
  • NETL
  • NSTL
  • 万方数据
Background The lint percentage of seed cotton is one of the most important parameters for evaluating seed cotton quality and affects its price.The traditional measuring method of lint percentage is labor-intensive and time-consum-ing;thus,an efficient and accurate measurement method is needed.In recent years,classification-based deep learn-ing and computer vision have shown promise in solving various classification tasks.Results In this study,we propose a new approach for detecting the lint percentage using MobileNetV2 and transfer learning.The model is deployed on a lint percentage detection instrument,which can rapidly and accurately deter-mine the lint percentage of seed cotton.We evaluated the performance of the proposed approach using a dataset comprising 66924 seed cotton images from different regions of China.The results of the experiments showed that the model with transfer learning achieved an average classification accuracy of 98.43%,with an average precision of 94.97%,an average recall of 95.26%,and an average F1-score of 95.20%.Furthermore,the proposed classification model achieved an average accuracy of 97.22%in calculating the lint percentage,showing no significant difference from the performance of experts(independent-sample t-test,t=0.019,P=0.860).Conclusion This study demonstrated the effectiveness of the MobileNetV2 model and transfer learning in calculating the lint percentage of seed cotton.The proposed approach is a promising alternative to traditional methods,provid-ing a rapid and accurate solution for the industry.

Neural networkMobileNetV2Nondestructive detectionSmart agricultureSeed cotton lint percentage

GENG Lijie、YAN Pengji、JI Zhikun、SONG Chunyu、SONG Shuaifei、ZHANG Ruiliang、ZHANG Zhifeng、ZHAI Yusheng、JIANG Liying、YANG Kun

展开 >

School of Electronic and Information,Henan Key Laboratory of Magnetoelectronic Information Functional Materials,Zhengzhou University of Light Industry,Zhengzhou 450002,Henan,China

National Natural Science Foundation of ChinaNational Natural Science Foundation of ChinaNational Natural Science Foundation of ChinaTraining Plan of Young Backbone Teachers in Universities of Henan ProvinceHenan Provincial Science and Technology Research ProjectHenan Provincial Science and Technology Research ProjectHenan Provincial Science and Technology Research ProjectProject of Central Plains Science and Technology Innovation Leading Talents

1190432761905223620732992023GGJS087222102110279222102210085242102210157224200510026

2024

10.1186/s42397-024-00178-x

棉花研究(英文)
中国农业科学院棉花研究所,中国农学会

棉花研究(英文)

ISSN：2096-5044
年,卷(期)：2024.7(2)