Identification of varieties of wheat seeds based on multispectral imaging combined with improved YOLOv5

Food Physics Pub Date : 2024-10-18 DOI:10.1016/j.foodp.2024.100042

Wei Liu , Yang Liu , Fei Hong , Jiaming Li , Quan Jiang , Lingfei Kong , Changhong Liu , Lei Zheng

{"title":"Identification of varieties of wheat seeds based on multispectral imaging combined with improved YOLOv5","authors":"Wei Liu , Yang Liu , Fei Hong , Jiaming Li , Quan Jiang , Lingfei Kong , Changhong Liu , Lei Zheng","doi":"10.1016/j.foodp.2024.100042","DOIUrl":null,"url":null,"abstract":"<div><div>The identification of seed variety is important in wheat production because the growth and yield are highly related with its variety. Traditional identification methods for wheat seed varieties were suffered with time consuming and contamination. This study proposed a method for convenient identification of wheat seed varieties by using improved YOLOv5 combined with multispectral images. Three optimal spectral bands images including 405 nm, 570 nm and 890 nm were selected to fuse new image from all 19 bands using Genetic algorithm and confusion matrix. The YOLOv5s model for wheat seed variety identification was improved by adding a convolutional block attention module (CBAM) and the identification model was developed with the fusion images. The identification performance of proposed method achieved an accuracy of 99.38 % in testing set, which was better than traditional VOLOv5 with RGB images or with the multispectral images. Meanwhile, the evaluation indexes of the model such as P/%, R/%, F1/% and mAP/% were all higher than 90 %, which showed that the method was suitable for identification of wheat seeds variety rapidly and non-destructively.</div></div>","PeriodicalId":100545,"journal":{"name":"Food Physics","volume":"2 ","pages":"Article 100042"},"PeriodicalIF":0.0000,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Food Physics","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2950069924000367","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

The identification of seed variety is important in wheat production because the growth and yield are highly related with its variety. Traditional identification methods for wheat seed varieties were suffered with time consuming and contamination. This study proposed a method for convenient identification of wheat seed varieties by using improved YOLOv5 combined with multispectral images. Three optimal spectral bands images including 405 nm, 570 nm and 890 nm were selected to fuse new image from all 19 bands using Genetic algorithm and confusion matrix. The YOLOv5s model for wheat seed variety identification was improved by adding a convolutional block attention module (CBAM) and the identification model was developed with the fusion images. The identification performance of proposed method achieved an accuracy of 99.38 % in testing set, which was better than traditional VOLOv5 with RGB images or with the multispectral images. Meanwhile, the evaluation indexes of the model such as P/%, R/%, F1/% and mAP/% were all higher than 90 %, which showed that the method was suitable for identification of wheat seeds variety rapidly and non-destructively.

查看原文本刊更多论文

基于多光谱成像与改进型 YOLOv5 结合的小麦种子品种鉴定

种子品种的鉴定在小麦生产中非常重要，因为小麦的生长和产量与其品种密切相关。传统的小麦种子品种识别方法存在耗时长、污染严重等问题。本研究提出了一种利用改进的 YOLOv5 结合多光谱图像方便识别小麦种子品种的方法。利用遗传算法和混淆矩阵，从所有 19 个波段的图像中选出三个最佳光谱波段图像（包括 405 nm、570 nm 和 890 nm）来融合新图像。通过添加卷积块注意力模块（CBAM），改进了用于小麦种子品种识别的 YOLOv5s 模型，并利用融合图像开发了识别模型。在测试集中，所提方法的识别准确率达到 99.38%，优于使用 RGB 图像或多光谱图像的传统 VOLOv5。同时，模型的 P/%、R/%、F1/% 和 mAP/% 等评价指标均高于 90%，表明该方法适用于快速、无损地识别小麦种子品种。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Food Physics

自引率

0.00%

发文量