EVALUATION OF TEST SPECIMEN SURFACE PREPARATION ON MACROSCOPIC COMPUTER VISION WOOD IDENTIFICATION

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniv Wisconsin Madison-
Autor(es): dc.contributorUSDA-
Autor(es): dc.contributorMississippi State Univ-
Autor(es): dc.contributorClemson Univ-
Autor(es): dc.contributorUniv Nacl Agr La Molina-
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.creatorRavindran, Prabu-
Autor(es): dc.creatorOwens, Frank C.-
Autor(es): dc.creatorCosta, Adriana-
Autor(es): dc.creatorRodrigues, Brunela Pollastrelli-
Autor(es): dc.creatorChavesta, Manuel-
Autor(es): dc.creatorMontenegro, Rolando-
Autor(es): dc.creatorShmulsky, Rubin-
Autor(es): dc.creatorWiedenhoeft, Alex C.-
Data de aceite: dc.date.accessioned2025-08-21T15:26:14Z-
Data de disponibilização: dc.date.available2025-08-21T15:26:14Z-
Data de envio: dc.date.issued2025-04-29-
Data de envio: dc.date.issued2023-10-31-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.22382/wfs-2023-15-
Fonte completa do material: dc.identifierhttps://hdl.handle.net/11449/308896-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/308896-
Descrição: dc.descriptionPrevious studies on computer vision wood identification (CVWID) have assumed or implied that the quality of sanding or knifing preparation of the transverse surface of wood specimens could influence model performance, but its impact is unknown and largely unexplored. This study investigates how variations in surface preparation quality of test specimens could affect the predictive accuracy of a previously published 24-class XyloTron CVWID model for Peruvian timbers. The model was trained on images of Peruvian wood specimens prepared at 1500 sanding grit and tested on images of independent specimens (not used in training) prepared across a series of progressively coarser sanding grits (1500, 800, 600, 400, 240, 180, and 80) and high-quality knife cuts. The results show that while there was a drop in performance at the lowest sanding grit of 80, most of the higher grits and knife cuts did not exhibit statistically significant differences in predictive accuracy. These results lay the groundwork for a future larger-scale investigation into how the quality of surface preparation in both training and testing data will impact CVWID model accuracy.-
Descrição: dc.descriptionU.S. Department of State via Interagency-
Descrição: dc.descriptionForest Stewardship Council-
Descrição: dc.descriptionWisconsin Idea Baldwin Grant-
Descrição: dc.descriptionU.S. Department of Agriculture (USDA)-
Descrição: dc.descriptionResearch, Education, and Economics (REE)-
Descrição: dc.descriptionAgriculture Research Service (ARS)-
Descrição: dc.descriptionAdministrative and Financial Management (AFM)-
Descrição: dc.descriptionFinancial Management and Accounting Division (FMAD)-
Descrição: dc.descriptionAgreements Management Branch (GAMB)-
Descrição: dc.descriptionUniv Wisconsin Madison, Dept Bot, Madison, WI USA-
Descrição: dc.descriptionUSDA, Forest Serv Forest Prod Lab, Ctr Wood Anat Res, Madison, WI USA-
Descrição: dc.descriptionMississippi State Univ, Dept Sustainable Bioprod, Starkville, MS 39759 USA-
Descrição: dc.descriptionClemson Univ, Dept Forestry & Environm Conservat, Clemson, SC USA-
Descrição: dc.descriptionUniv Nacl Agr La Molina, Dept Wood Ind, Lima, Peru-
Descrição: dc.descriptionUniv Estadual Paulista Botucatu, Dept Ciencias Biol Bot, Botucatu, SP, Brazil-
Descrição: dc.descriptionUniv Estadual Paulista Botucatu, Dept Ciencias Biol Bot, Botucatu, SP, Brazil-
Descrição: dc.descriptionU.S. Department of State via Interagency: 19318814Y0010-
Descrição: dc.descriptionAgreements Management Branch (GAMB): 58-0204-9-164-
Formato: dc.format176-202-
Idioma: dc.languageen-
Publicador: dc.publisherSoc Wood Sci Technol-
Relação: dc.relationWood And Fiber Science-
???dc.source???: dc.sourceWeb of Science-
Palavras-chave: dc.subjectXyloTron-
Palavras-chave: dc.subjectcomputer vision wood identification-
Palavras-chave: dc.subjectmachine learning-
Palavras-chave: dc.subjectdeep learning-
Palavras-chave: dc.subjectsurface preparation-
Título: dc.titleEVALUATION OF TEST SPECIMEN SURFACE PREPARATION ON MACROSCOPIC COMPUTER VISION WOOD IDENTIFICATION-
Tipo de arquivo: dc.typelivro digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.