Image database establishing method suitable for training deep convolution neural network

Abstract

The invention discloses an image database establishing method suitable for training a deep convolution neural network, and the method comprises the following steps: collecting an original image in a pest RGB form, and recognizing and marking pest categories; performing color attenuation on the original image to obtain an RGB image and a corresponding HSV image; calculating respective color proportions according to the RGB image, calculating color similarity regions according to the HSV image, and calculating a significance image of the RGB image; thresholding the significance image to obtain a binary image, using a region appointed by the binary image as an initial region, and dividing a pest target in the initial region with a GrabCut algorithm; cutting the original image according to the divided region, zooming to a uniform size and storing and establishing a database. The problems of difficulty in sampling, fuzzy marking and non-uniform size when a crop pest database is established in the prior art are solved, and the problem of over-fitting caused by too less samples and single gestures in a training process of the deep convolution neural network is solved.

Description

technical field [0001] The invention relates to the technical field of precision agriculture, in particular to a method for constructing an image database suitable for training a deep convolutional neural network. Background technique [0002] Rice is one of the important food crops in my country. During the whole growth period of rice, there are many diseases, insects and other harmful organisms, especially rice pests, which cause staggering losses every year, directly endangering rice production. At present, my country's rice pest control has always adhered to the "Integrated Pest Management (IPM)" plant protection policy, based on monitoring and forecasting, comprehensively applying agricultural, biological, physical control and chemical control and other technical measures to effectively control pest damage. [0003] The investigation of the types and quantities of rice pests is a basic and important task in the pest forecasting work. If there is no correct survey data,...

AI Technical Summary

Problems solved by technology

At present, the number of samples of pest image classification models for a certain pest or all pests of a certain crop is too small, and the range of poses and angles covered is insufficient. Overfitting is very easy to occur when the model is established, resulting in the generalization ability of the model classification. insufficient

Images