Advanced wood species identification based on multiple anatomical sections and using deep feature transfer and fusion

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversidade de São Paulo (USP)-
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.contributorFederal University of Catalão-
Autor(es): dc.contributorRoyal Museum for Central Africa-
Autor(es): dc.contributorGhent University-
Autor(es): dc.creatorZielinski, Kallil M.-
Autor(es): dc.creatorScabini, Leonardo-
Autor(es): dc.creatorRibas, Lucas C.-
Autor(es): dc.creatorda Silva, Núbia R.-
Autor(es): dc.creatorBeeckman, Hans-
Autor(es): dc.creatorVerwaeren, Jan-
Autor(es): dc.creatorBruno, Odemir M.-
Autor(es): dc.creatorDe Baets, Bernard-
Data de aceite: dc.date.accessioned2025-08-21T16:12:42Z-
Data de disponibilização: dc.date.available2025-08-21T16:12:42Z-
Data de envio: dc.date.issued2025-04-29-
Data de envio: dc.date.issued2025-04-01-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.1016/j.compag.2024.109867-
Fonte completa do material: dc.identifierhttps://hdl.handle.net/11449/300621-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/300621-
Descrição: dc.descriptionWood is a versatile and renewable resource, widely used across industries, yet the increasing demand has led to illegal logging with severe environmental, social, and economic consequences. To reduce illegal wood trade and its associated threats to biodiversity, robust methods for wood species identification and accurate datasets are crucial. In recent years, there have been significant advances in this area, but many current techniques face challenges such as high costs, the need for skilled experts for data interpretation, and the lack of good datasets for professional reference. Therefore, most of these methods, and certainly the wood anatomical assessment, may benefit from tools based on Artificial Intelligence. In this paper, we apply two transfer learning techniques with Convolutional Neural Networks (CNNs) to a multi-view Congolese wood species dataset including sections from different orientations and viewed at different microscopic magnifications. We explore two feature extraction methods in detail, namely Global Average Pooling (GAP) and Random Encoding of Aggregated Deep Activation Maps (RADAM), for efficient and accurate wood species identification. Our results indicate superior accuracy on diverse datasets and anatomical sections, surpassing the results of other methods. Our proposal represents a significant advancement in wood species identification, offering a robust tool to support the conservation of forest ecosystems and promote sustainable forestry practices.-
Descrição: dc.descriptionVlaamse regering-
Descrição: dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)-
Descrição: dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)-
Descrição: dc.descriptionCoordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)-
Descrição: dc.descriptionSão Carlos Institute of Physics University of São Paulo-
Descrição: dc.descriptionInstitute of Biosciences Humanities and Exact Sciences São Paulo State University-
Descrição: dc.descriptionFederal University of Catalão-
Descrição: dc.descriptionRoyal Museum for Central Africa-
Descrição: dc.descriptionBIOVISM Dept. of Data Analysis and Mathematical Modelling Ghent University-
Descrição: dc.descriptionKERMIT Dept. of Data Analysis and Mathematical Modelling Ghent University-
Descrição: dc.descriptionInstitute of Biosciences Humanities and Exact Sciences São Paulo State University-
Descrição: dc.descriptionFAPESP: #2018/22214-6-
Descrição: dc.descriptionFAPESP: #2021/08325-2-
Descrição: dc.descriptionFAPESP: #2021/09163-6-
Descrição: dc.descriptionFAPESP: #2022/03668-1-
Descrição: dc.descriptionFAPESP: #2023/04583-2-
Descrição: dc.descriptionFAPESP: #2023/10442-2-
Descrição: dc.descriptionCNPq: #307897/2018-4-
Descrição: dc.descriptionCAPES: #88887.631085/2021-00-
Idioma: dc.languageen-
Relação: dc.relationComputers and Electronics in Agriculture-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subjectConvolutional neural networks-
Palavras-chave: dc.subjectFeature extraction-
Palavras-chave: dc.subjectTexture analysis-
Palavras-chave: dc.subjectTransfer learning-
Palavras-chave: dc.subjectWood species identification-
Título: dc.titleAdvanced wood species identification based on multiple anatomical sections and using deep feature transfer and fusion-
Tipo de arquivo: dc.typelivro digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.