Early-Stage Identification of Powdery Mildew Levels for Cucurbit Plants in Open-Field Conditions Based on Texture Descriptors

Abstract

Constant monitoring is necessary for powdery mildew prevention in field crops because, as a fungal disease, it modifies the green pigments of the leaves and is responsible for production losses. Therefore, there is a need for solutions that assure early disease detection to realize proactive control and management of the disease. The methodology currently used for the identification of powdery mildew disease uses RGB leaf images to detect damage levels. In the early stage of the disease, no symptoms are visible, but this is a point at which the disease can be controlled before the symptoms appear. This study proposes the implementation of a support vector machine to identify powdery mildew on cucurbit plants using RGB images and color transformations. First, we use an image dataset that provides photos covering five growing seasons in different locations and under natural light conditions. Twenty-two texture descriptors using the gray-level co-occurrence matrix result are calculated as the main features. The proposed damage levels are ’healthy leaves’, ’leaves in the fungal germination phase’, ’leaves with first symptoms’, and ’diseased leaves’. The implementation reveals that the accuracy in the L * a * b color space is higher than that when using the combined components, with an accuracy value of 94% and kappa Cohen of 0.7638.

Optimal Image Characterization for In-Bed Posture Classification by Using SVM Algorithm

“…In addition, applications with images are used in agricultural areas. A methodology for identification of the disease powdery mildew using diseased leaf images was proposed by [13], in which the implementation of a Support Vector Machine was used to identify the powdery mildew in cucurbit plants using RGB images and color transformations. First, they used an image dataset from five growing seasons in different locations in natural conditions of light.…”