Use este identificador para citar ou linkar para este item: http://repositorio.ufla.br/jspui/handle/1/43176
Registro completo de metadados
Campo DCValorIdioma
dc.creatorLeite, I. C. C-
dc.creatorSáfadi, T.-
dc.creatorCarvalho, M. L. M.-
dc.date.accessioned2020-09-23T04:15:18Z-
dc.date.available2020-09-23T04:15:18Z-
dc.date.issued2013-08-01-
dc.identifier.citationLEITE, I. C. C.; SÁFADI, T.; CARVALHO, M. L. M. Evaluation of seed radiographic images by independent component analysis and discriminant analysis. Seed Science and Technology, [S.l.], v. 41, n. 2, p. 235-244, Aug. 2013. DOI: 10.15258/sst.2013.41.2.06.pt_BR
dc.identifier.urihttps://www.ingentaconnect.com/contentone/ista/sst/2013/00000041/00000002/art00006pt_BR
dc.identifier.urihttp://repositorio.ufla.br/jspui/handle/1/43176-
dc.description.abstractAlthough subjective, the use of X-ray images of seeds is an important tool for analysing seed lot quality. Here, we applied independent component analysis (ICA) for automatic processing of radiographic images of 600 sunflower seeds. The X-rayed seeds were also subjected to a germination test. The ICA technique was implemented with the FastICA algorithm, which decomposed X-ray images to independent basis images. Based on features extracted by ICA, we used discriminant analysis (DA) to classify seed quality. The classification achieved an overall accuracy of 82%. The results showed that ICA and DA were effective in X-ray analysis to associate seed morphology and seedling performance.pt_BR
dc.languageen_USpt_BR
dc.publisherInternational Seed Testing Association (ISTA)pt_BR
dc.rightsrestrictAccesspt_BR
dc.sourceSeed Science and Technologypt_BR
dc.subjectSeedspt_BR
dc.subjectX-ray imagespt_BR
dc.subjectIndependent component analysispt_BR
dc.subjectDiscriminant analysispt_BR
dc.titleEvaluation of seed radiographic images by independent component analysis and discriminant analysispt_BR
dc.typeArtigopt_BR
Aparece nas coleções:DEX - Artigos publicados em periódicos

Arquivos associados a este item:
Não existem arquivos associados a este item.


Os itens no repositório estão protegidos por copyright, com todos os direitos reservados, salvo quando é indicado o contrário.