SANTOS, J. M.; http://lattes.cnpq.br/8170853273213004; SANTOS, Joniedson Marcos dos.
Resumo:
Cowpea is a crop of great importance worldwide, which is why many improved cultivars are exploited. The plants of these cultivars have intrinsic characteristics that distinguish them. In this contexto, the objective was to evaluate artificial intelligence algorithms to fit cowpea cultivar phenotyping models by digital images at different phenological stages. For this purpose, digital images obtained at stages V1, V2, V3 and V4 of nine cultivars were processed using the vectors InceptionV3, SqueezeNet, VGG16 and VGG19. Subsequently, the k-nearest neighbors (KNN - number of nearest neighbors), decision tree (Tree), random forest (RF - Random Forest), gradient boost (GB - Gradient Boosting), vector support machine (SVM - Support Vector Machines) and artificial neural network (MLP - Multi-Layer Perceptron). The performance of the models was tested using the cross-validation method. The Artificial Neural Network machine learning algorithm has better performance for non-destructive phenotyping of cowpea cultivars improved by digital images at different phenological stages in the vegetative phase.