Automatic identification of charcoal origin based on deep learning

IF 1.2 4区 农林科学 Q3 MATERIALS SCIENCE, PAPER & WOOD
Ricardo Rodrigues de Oliveira, Larissa Ferreira Rodrigues, J. F. Mari, Murilo Coelho Naldi, Emerson Gomes Milagres, Benedito Rocha Vital, Angélica de Cássia Oliveira Carneiro, Daniel Henrique Breda Binoti, Pablo Falco Lopes, Hélio Garcia Leite
{"title":"Automatic identification of charcoal origin based on deep learning","authors":"Ricardo Rodrigues de Oliveira, Larissa Ferreira Rodrigues, J. F. Mari, Murilo Coelho Naldi, Emerson Gomes Milagres, Benedito Rocha Vital, Angélica de Cássia Oliveira Carneiro, Daniel Henrique Breda Binoti, Pablo Falco Lopes, Hélio Garcia Leite","doi":"10.4067/s0718-221x2021000100465","DOIUrl":null,"url":null,"abstract":"The differentiation between the charcoal produced from (Eucalyptus) plantations and native forests is essential to control, commercialization, and supervision of its production in Brazil. The main contribution of this study is to identify the charcoal origin using macroscopic images and Deep Learning Algorithm. We applied a Convolutional Neural Network (CNN) using VGG-16 architecture, with preprocessing based on contrast enhancement and data augmentation with rotation over the training set images. on the performance of the CNN with fine-tuning using 360 macroscopic charcoal images from the plantation and native forests. The results pointed out that our method provides new perspectives to identify the charcoal origin, achieving results upper 95 % of mean accuracy to classify charcoal from native forests for all compared preprocessing strategies.","PeriodicalId":18092,"journal":{"name":"Maderas-ciencia Y Tecnologia","volume":"18 1","pages":""},"PeriodicalIF":1.2000,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Maderas-ciencia Y Tecnologia","FirstCategoryId":"88","ListUrlMain":"https://doi.org/10.4067/s0718-221x2021000100465","RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"MATERIALS SCIENCE, PAPER & WOOD","Score":null,"Total":0}
引用次数: 3

Abstract

The differentiation between the charcoal produced from (Eucalyptus) plantations and native forests is essential to control, commercialization, and supervision of its production in Brazil. The main contribution of this study is to identify the charcoal origin using macroscopic images and Deep Learning Algorithm. We applied a Convolutional Neural Network (CNN) using VGG-16 architecture, with preprocessing based on contrast enhancement and data augmentation with rotation over the training set images. on the performance of the CNN with fine-tuning using 360 macroscopic charcoal images from the plantation and native forests. The results pointed out that our method provides new perspectives to identify the charcoal origin, achieving results upper 95 % of mean accuracy to classify charcoal from native forests for all compared preprocessing strategies.
基于深度学习的木炭产地自动识别
在巴西,区分桉树人工林和原生森林生产的木炭对其生产的控制、商业化和监督至关重要。本研究的主要贡献是利用宏观图像和深度学习算法识别木炭来源。我们使用了一个使用VGG-16架构的卷积神经网络(CNN),在训练集图像上进行了基于对比度增强和旋转的数据增强的预处理。利用人工林和原生林的360度宏观木炭图像,对CNN的性能进行了微调。结果表明,我们的方法为鉴定木炭来源提供了新的视角,在所有预处理策略的对比中,对原始森林木炭的分类准确率都达到了95%以上。
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
Maderas-ciencia Y Tecnologia
Maderas-ciencia Y Tecnologia 工程技术-材料科学:纸与木材
CiteScore
2.60
自引率
13.30%
发文量
33
审稿时长
>12 weeks
期刊介绍: Maderas-Cienc Tecnol publishes inedits and original research articles in Spanish and English. The contributions for their publication should be unpublished and the journal is reserved all the rights of reproduction of the content of the same ones. All the articles are subjected to evaluation to the Publishing Committee or external consultants. At least two reviewers under double blind system. Previous acceptance of the Publishing Committee, summaries of thesis of Magíster and Doctorate are also published, technical opinions, revision of books and reports of congresses, related with the Science and the Technology of the Wood. The journal have not articles processing and submission charges.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信