Crop leaf disease identification method and device and storage medium

Abstract

The invention relates to a crop leaf disease identification method and device and a storage medium, and the method comprises the steps: segmenting a crop leaf image under a real background through employing a preset semantic segmentation model, and obtaining each leaf image; performing scab segmentation on each leaf image according to an image enhancement technology and a color space conversion technology to obtain each scab image; setting a disease type label for each disease spot image, and establishing a data set of each disease spot image; extracting disease spot feature vectors of disease spot images in the disease spot image data set; performing classification training on a classifier according to the disease spot feature vector and a disease type label corresponding to the disease spot image data set; realizing crop leaf disease identification according to the trained classifier. Crop leaves under a complex background are accurately segmented, classification training is performed on the classifier through the scab feature vectors and the disease type labels to realize disease identification, a manual identification mode is avoided, the labor rate is greatly reduced, and the identification accuracy is improved.

Description

technical field [0001] The invention relates to the field of agricultural disease identification, in particular to a method, device and storage medium for identifying crop leaf diseases. Background technique [0002] Various diseases may appear during the growth of crops, seriously affecting the yield and quality of crops, and posing a certain threat to food safety. In the case of large-scale planting, only relying on manual identification of diseases will be time-consuming and laborious, and the development of the disease cannot be detected and prevented in time. The technical methods currently used are all researched and tested on the characteristics of lesion spots on the individual leaves picked manually. For example, the individual leaves are spread in a single color and the background is not disturbed. However, in real scenarios such as crops In the actual planting environment, the original image of the leaf obtained during monitoring cannot be a single leaf, but gene...

AI Technical Summary

Problems solved by technology

[0002] Various diseases may appear during the growth of crops, seriously affecting the yield and quality of crops, and posing a certain threat to food safety

In the case of large-scale planting, only relying on manual identification of diseases will be time-consuming and laborious, and the development of the disease cannot be detected and prevented in time

The technical methods currently used are all researched and tested on the characteristics of lesion spots on individual leaves picked manually. For example, the individual leaves are spread in a single color and the background is not disturbed. However, in real scenarios such as crops In the actual planting environment, the original image of the leaf obtained during monitoring cannot be a single leaf, but generally has multiple leaves with different postures and contains other complex backgrounds, which makes it difficult to segment the leaf and its lesion images, and makes subsequent feature extraction methods invalid.

Images