Algorithms for plant disease diagnostics by leaf image

Abstract

This article discusses the task of detecting diseases of cultivated plants. When determining the phytosanitary status of cultivated plants, images of their leaves are considered as initial data. To solve the problem under consideration, a model of diagnostic algorithms based on two-dimensional threshold functions is proposed. The main idea of the proposed algorithms is to form a set of preferred diagnostic features and make decisions aimed at making a diagnosis based on a comparison of these features. The classification stages of the diagnostic algorithm model are presented. An assessment of the applicability of the proposed model is demonstrated using the example of solving the problem of diagnosing wheat diseases by leaf images. Keywords: diagnostic algorithms, basic image slices, diagnostic features, preferred features, calculation of the overall score.