Spectral signature analysis is one of the most widely used techniques for diagnosing diseased plants. For this, it is necessary to consider different techniques for the feature extraction that allow the identification of different damage levels of a specific pathology, such as the case of fungal disease in cucurbits plants. In this study, reflectance measurements of healthy and diseased leaves are used to identify three main stages of powdery mildew levels: leaves in the germination stage of the fungus leaves with first symptoms and diseased leaves. Then, a proposal to use frequency analysis of the spectral signatures using the Wavelet transforms and the Fourier transforms to the feature extraction from the obtained coefficients and determines the damage levels using multi-classification in support vector machine blocks. Classification accuracy of 94.6% and 98.3%, respectively, was demonstrated. Therefore, this methodology is important for the diagnosis of damage levels on cucurbits leaves and other similar plants.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.