Disease and pest identification method and device

Abstract

A pest and disease identification method and device provided by the invention are applied to the data processing equipment, wherein the data processing equipment is pre-configured with a trained neural network model, and the neural network model is obtained by training leaf images and plant images of a plurality of diseased plants. The data processing equipment obtains a leaf image and a plant image of a to-be-identified plant, identifies the characteristics of the to-be-identified plant through the neural network model, and further obtains the type of the to-be-identified plant and the pest and disease damage type. Therefore, by combining the leaf image of the plant with the plant image of the plant, the identification rate of the plant species and the identification rate of the disease types of different plants are improved.

Description

technical field [0001] The present application relates to the field of image recognition, in particular, to a method and device for identifying pests and diseases. Background technique [0002] Plant diseases and insect pests refer to the infection of plants by other organisms, such as pathogen infection, fungal infection or pest infection; or the destruction of normal physiological functions caused by unsuitable environmental conditions, such as drought, freezing or air pollution. As a large agricultural country in my country, crop diseases and insect pests often cause great losses to the national economy. [0003] In the existing pest detection technology, most of the methods identify a single type of plant or pest. Since the identification method relies on manual extraction of features, it is usually difficult to reuse a more accurate identification method on one type of crops to another type. on the plants. Therefore, there are problems of poor versatility and unstable...

AI Technical Summary

Problems solved by technology

[0003] In the existing pest detection technology, most of the methods identify a single type of plant or pest. Since the identification method relies on manual extraction of features, it is usually difficult to reuse a more accurate identification method on one type of crops to another type. on the plant

Therefore, there are problems of poor versatility and unstable recognition rates among different plants

Images