Disease and pest identification system and method based on machine vision and convolutional neural network

Abstract

The invention relates to a pest identification system and a method based on machine vision and a convolutional neural network, and belongs to the technical field of artificial intelligence. The systemmainly comprises an image acquisition module, a model training module, a model test module, a visual identification module, an information classification detection module and a training updating module. The method mainly comprises an image acquisition step, a model training step, a model test step, a visual identification step, an information classification detection step and a training updatingstep. According to the disease and pest identification system and the method based on machine vision and the convolutional neural network, a large amount of image data can be obtained at fixed pointsand fixed time; visual identification and convolutional neural network model testing are placed at an acquisition front end, invalid image bandwidth occupation is reduced, network resources are optimized, identification efficiency is improved, a feedback and updating mechanism enables the model to be continuously optimized in a gradient mode, a front end model is synchronized in real time, and disease and pest identification accuracy is effectively improved.

Description

technical field [0001] The invention relates to a system and method for identifying diseases and insect pests based on machine vision and convolutional neural network, and belongs to the technical field of artificial intelligence. Background technique [0002] In recent years, the global climate has changed, farming systems and production methods have changed, and agricultural diseases and insect pests have shown a trend of high incidence, frequent occurrence, and extensive disaster areas. The application of agricultural disease and insect pest identification technology is particularly important for agricultural crop disaster prevention and agricultural planting production. . Existing pest and disease identification systems rely on front-end acquisition equipment to transmit a large number of images and images to the data center, and then carry out relevant identification and training through artificial intelligence technology. This method results in a huge amount of collec...

AI Technical Summary

Problems solved by technology

This method results in a huge amount of collection and occupies a high network bandwidth. If the network is unstable, the transmission efficiency is low, and the artificial intelligence technology is behind, there is a certain delay in the recognition response. In addition, due to the large amount of data transmitted back Less efficient at identifying valid image data

At present, there is no system or method that can change this situation

Images