Smart agriculture: real-time classification of green coffee beans by using a convolutional neural network

IF 2.1 Q3 COMPUTER SCIENCE, INFORMATION SYSTEMS

IET Smart Cities Pub Date : 2020-10-13 DOI:10.1049/iet-smc.2020.0068

Nen-Fu Huang, Dong-Lin Chou, Chia-An Lee, Feng-Ping Wu, An-Chi Chuang, Yi-Hsien Chen, Yin-Chun Tsai

{"title":"Smart agriculture: real-time classification of green coffee beans by using a convolutional neural network","authors":"Nen-Fu Huang, Dong-Lin Chou, Chia-An Lee, Feng-Ping Wu, An-Chi Chuang, Yi-Hsien Chen, Yin-Chun Tsai","doi":"10.1049/iet-smc.2020.0068","DOIUrl":null,"url":null,"abstract":"<div>\n <p>Coffee is an important economic crop and one of the most popular beverages worldwide. The rise of speciality coffees has changed people's standards regarding coffee quality. However, green coffee beans are often mixed with impurities and unpleasant beans. Therefore, this study aimed to solve the problem of time-consuming and labour-intensive manual selection of coffee beans for speciality coffee products. The second objective of the authors’ study was to develop an automatic coffee bean picking system. They first used image processing and data augmentation technologies to deal with the data. They then used deep learning of the convolutional neural network to analyse the image information. Finally, they applied the training model to connect an IP camera for recognition. They successfully divided good and bad beans. The false-positive rate was 0.1007, and the overall coffee bean recognition rate was 93%.</p>\n </div>","PeriodicalId":34740,"journal":{"name":"IET Smart Cities","volume":null,"pages":null},"PeriodicalIF":2.1000,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/iet-smc.2020.0068","citationCount":"11","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IET Smart Cities","FirstCategoryId":"1085","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1049/iet-smc.2020.0068","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}

引用次数: 11

Abstract

Coffee is an important economic crop and one of the most popular beverages worldwide. The rise of speciality coffees has changed people's standards regarding coffee quality. However, green coffee beans are often mixed with impurities and unpleasant beans. Therefore, this study aimed to solve the problem of time-consuming and labour-intensive manual selection of coffee beans for speciality coffee products. The second objective of the authors’ study was to develop an automatic coffee bean picking system. They first used image processing and data augmentation technologies to deal with the data. They then used deep learning of the convolutional neural network to analyse the image information. Finally, they applied the training model to connect an IP camera for recognition. They successfully divided good and bad beans. The false-positive rate was 0.1007, and the overall coffee bean recognition rate was 93%.

Abstract Image

查看原文本刊更多论文

智能农业:利用卷积神经网络对生咖啡豆进行实时分类

咖啡是一种重要的经济作物，也是世界上最受欢迎的饮料之一。精品咖啡的兴起改变了人们对咖啡质量的标准。然而，生咖啡豆往往夹杂着杂质和令人不快的咖啡豆。因此，本研究旨在解决精品咖啡产品手工选择咖啡豆费时费力的问题。作者研究的第二个目标是开发一种自动咖啡豆采摘系统。他们首先使用图像处理和数据增强技术来处理数据。然后，他们使用卷积神经网络的深度学习来分析图像信息。最后，他们将训练模型应用于连接IP摄像机进行识别。他们成功地把好豆子和坏豆子分开了。假阳性率为0.1007，总体咖啡豆识别率为93%。

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

IET Smart Cities Social Sciences-Urban Studies

CiteScore

7.70

自引率

3.20%

发文量

审稿时长

21 weeks