Image analysis of coffee seeds submitted to the LERCAFE test/Analise de imagens de sementes de cafe submetidas ao Teste LERCAFE

The aim of this experiment was to quantify the stained areas of coffee seeds submitted to the LERCAFE test using image analysis. The seeds used were of the Catuai Vermelho IAC 99 and Paradise cultivars. The physiological quality of the lots was assessed using germination tests, moisture content and a germination speed index. The LERCAFE test was conducted using seeds without parchment immersed in a solution of 3% sodium hypochlorite for 3 hours. Color photographs (RGB) with a resolution of 5 MPx were taken of each seed. The seeds were visually evaluated, and the functions generated from the analyses of the stained and non-stained regions were quantified by the Matlab R2009b program. Classification models were developed based on the Fisher Linear Discriminant Function and the evaluation of the adequacy of the models confusion matrix between the visual references and the classification generated by the linear functions. The image analysis for the creation of Fisher's linear discriminant function in the development of classifiers for the coffee seeds submitted to the LERCAFE test is potentially efficient; however, it remains necessary to test other discriminant functions and quantification methodologies. Keywords: determinants functions, sodium hypochlorite, pixels. Objetivou-se com essa pesquisa quantificar as areas coradas de sementes de cafe submetidas ao teste LERCAFE por meio da analise de imagens. Foram utilizadas sementes das cultivares Catuai Vermelho IAC 99 e Paraiso. Foi realizada a caracterizacao da qualidade fisiologica dos lotes com os testes de germinacao, umidade e indice de velocidade de germinacao. O teste LERCAFE foi conduzido utilizando semente sem o pergaminho com solucao de hipoclorito de sodio 3% pelo periodo de 3 horas. Foram feitas fotografias coloridas (RGB) com resolucao de 5 MPx de cada semente. As sementes foram avaliadas visualmente e por funcoes geradas a partir da analise de regioes coradas e nao coradas quantificadas pelo programa Matlab R2009b. Foram desenvolvidos modelos de classificacao com base na Funcao Linear de Fisher e avaliacao da adequacao dos modelos pela Matriz de Confusao entre as referencias visuais e classificacao gerada pelas funcoes lineares. A analise de imagem para criacao da funcao discriminante linear de Fisher no desenvolvimento de classificadores para sementes de cafe submetidas ao teste LERCAFE e potencialmente eficiente sendo necessario testar outras funcoes discriminantes e metodologias para quantifica