Corn seed production cluster screening method and device based on double-channel convolutional neural network

Abstract

The invention provides a corn seed production cluster screening method and a device based on a double-channel convolutional neural network. The method comprises the following steps: inputting a corn seed production cluster image with a corn seed production cluster type label into a first branch model and a second branch model of a double-channel convolutional neural network in advance; and respectively extracting the characteristic quantities of the corn seed production cluster images and inputting the characteristic quantities into a fusion classification model for fusion and classification,thereby training the double-channel convolutional neural network, and then obtaining the corn seed production cluster types corresponding to the acquired corn seed production cluster images by using the trained double-channel convolutional neural network. According to the method, the advantages of the first branch model and the second branch model can be combined; the classification accuracy of the model is improved, the problems that it is difficult to manually extract deep features of corn ear images and it is difficult to obtain high classification accuracy are effectively solved, the cornseed production operation process is greatly simplified, the corn seed production efficiency is improved, the labor cost is saved, and the method has important reference significance for improving thecorn ear seed production efficiency.

Description

technical field [0001] The invention relates to the technical field of deep learning and image processing, in particular to a method and device for ear screening of corn seed production based on a two-way convolutional neural network. Background technique [0002] As one of the important food crops, maize's yield has a decisive impact on the development of agricultural economy, and the quality of maize seeds is the key factor for the maize yield. As one of the world's largest agricultural countries, increasing corn production is of great significance to my country's economic development. Therefore, planting high-quality corn seeds is an important means to greatly increase my country's corn production and promote agricultural economic development. [0003] The corn seed production process mainly includes bract removal, ear selection, drying, and threshing. In the ear selection process of corn seed production, corn ears with good phenotypic characteristics are selected for thr...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the current problem that manual selection of ear selection for seed production is slow, consumes a lot of manpower and material resources, and manual screening is easily affected by subjective and large errors, the embodiment of the present invention provides a corn seed production method based on a two-way convolutional neural network. Ear screening method and device

Images