Sunflower seed sorting method based on double-branch convolutional neural network

Abstract

The invention provides a sunflower seed sorting method based on a double-branch convolutional neural network, which comprises the following steps: firstly, labeling class labels on acquired original images of sunflower seeds, randomly dividing the original images into a training set and a test set, and then carrying out data amplification on the training set and the test set to form an amplification training set and an amplification test set; secondly, constructing a double-branch convolutional neural network of which the network structure is an input layer-feature extraction layer-output layer; inputting the amplification training set into a double-branch convolutional neural network for training to obtain a sunflower seed sorting model based on the double-branch convolutional neural network; and finally, verifying the sunflower seed sorting model by utilizing the amplification test set, and testing the recognition capability of the sunflower seed sorting model. According to the method, the utilization rate of the model for front-layer lower-level features is increased, the storage space of the network model on hardware equipment is reduced, and meanwhile the method has the advantages of being high in robustness and high in recognition precision.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for sorting sunflower seeds based on a double-branch convolutional neural network. Background technique [0002] Automatic sorting technology has very broad development and application prospects in industry, agriculture and commerce. Especially in the sorting task of agricultural seeds, due to the continuous stringent and refined requirements of the agricultural market for seed quality, improving the quality of crop seeds in the market has become an important task in agricultural production. [0003] During the harvesting and storage of sunflower seeds, a large number of abnormal seeds will be mixed in, resulting in insufficient competitiveness of seed products in the market. How to efficiently and accurately identify and sort abnormal seeds in sunflower seeds is still a relatively difficult problem in the agricultural field. There are many types of abnormal s...

AI Technical Summary

Problems solved by technology

[0004] In view of the deficiencies in the above-mentioned background technology, the present invention proposes a sunflower seed sorting method based on a double-branch convolutional neural network, which solves the technical problems that the existing convolutional neural network is relatively complex and has low real-time performance

Images