A multi-type crop leaf disease identification method based on a dynamic neural network

Abstract

The invention provides a multi-type crop leaf disease identification method based on a dynamic neural network, and the method comprises the steps of randomly selecting part of crop leaf disease image data for pixel-level marking, and training a convolutional neural network for image segmentation; then, automatically segmenting the crop leaf disease image by using the trained convolutional neural network, and extracting effective information in the image; and finally, designing a dynamic neural network which comprises three parts of a dynamic convolution module, a shallow classifier and an early-going mechanism, and realizing leaf disease identification based on a dynamic network structure. According to the scheme, the method can realize automatic segmentation and extraction of effective information of the crop leaf disease image and recognition of various types of crop leaf diseases, the adopted dynamic neural network can dynamically adjust the network structure according to the complexity of the crop leaf diseases, and the use of computing resources is reduced under the condition that the requirement for high recognition accuracy rate is met.

Description

technical field [0001] The invention belongs to the field of plant disease detection, and in particular relates to a dynamic neural network-based identification method for various types of crop leaf diseases. Background technique [0002] Crop diseases have always been a problem for agricultural growers. The traditional method of judging the type of crop leaf disease is through naked eye observation. This method requires experts to go to the scene to observe and judge, which has certain limitations. Timely and effective analysis of the types of crop diseases will help to quickly carry out corresponding disease control measures, thereby reducing economic losses. [0003] At present, there are many methods for identifying crop leaf diseases based on deep learning. Most of them design feature extraction methods for different diseases of a specific crop, and then identify the specific crop disease. However, there are relatively few technologies for identifying diseases of vario...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem that the traditional fixed network structure cannot better identify various crop leaf diseases, the present invention proposes a method for identifying various crop leaf diseases based on a dynamic neural network, which can dynamically adjust the network structure of the model, and has strong robustness. Sticky, it has a good performance effect on the identification of various crop leaf diseases

Images