Método computacional para identificação do fungo Cercospora Kikuchii em sementes de soja

• Ano de defesa: 2017
• Autor(a) principal: Franco, Jaqueline Rissá
• Orientador(a): Falate, Rosane
• Banca de defesa: Jaccoud Filho, David de Souza , Sanches, Ionildo José
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: UNIVERSIDADE ESTADUAL DE PONTA GROSSA
• Programa de Pós-Graduação: Programa de Pós Graduação Computação Aplicada
• Departamento: Computação para Tecnologias em Agricultura
• País: BR
• Palavras-chave em Português: OpenCV; Glycine max (L.) Merrill; Cercospora kikuchii; Processamento de imagens; CIEL*a*b; RGB; HSV
• Palavras-chave em Inglês: OpenCV; Glycine max (L.) Merrill; Cercospora kikuchii; image processing; CIEL*a*b; RGB; HSV
• Área do conhecimento CNPq: CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO
• Link de acesso: http://tede2.uepg.br/jspui/handle/prefix/146

The condition known as purple spot in soybean seed is caused by the fungus Cercospora kikuchii and can influence both yield and quality losses in the production of soybean derivatives. Seed quality control is essential to avoid such losses, so there are conventional methods, such as visual inspections to identify contaminated seeds. However, these conventional processes are slow and imprecise, since they depend directly on the analyst. The present work had as objective to develop a computational system for the identification of soybean seeds contaminated by the fungus Cercospora kikuchii. The proposed method was developed based on the OpenCV library, using the Java programming language and the integration interface of the WEKA tool. Samples of 150 healthy seeds and 150 contaminated seeds were considered. The individual image acquisition of each seed, for purposes of classification in healthy or contaminated, was performed and was consided in the process the individual quality of each stage. The obtained result was 88% of correct classifications, using crossvalidation in the constructed neural network model and 100% correct classifications in the used images. The best results found in studies of other authors, specifically considering the fungus Cercospora kikuchii, were 66% to 83% of the correct classifications.