Grain insect identification method and identification system based on feature fusion of SSD algorithm

Abstract

The invention relates to a grain insect identification method and identification system based on SSD algorithm feature fusion. The identification method comprises the following steps: establishing a data set; establishing a neural network model and training the neural network model by adopting the data set to obtain a trained neural network model; and collecting a to-be-identified grain insect image, inputting the to-be-identified grain insect image into the trained neural network model, and detecting the type and position of the grain insect in the to-be-identified grain insect image. According to the technical scheme provided by the invention, the output feature maps of the convolution layers conv43 and conv53 in the neural network model are fused, the block 11 unfavorable for small target detection is deleted, and the priori box suitable for the grain insect is obtained by adopting the Kmeans clustering algorithm, so that the defect of the default priori box in the original SSD is improved, the identification and positioning of the grain insect are facilitated, the problem that in the prior art, grain insect recognition accuracy is poor can be solved.

Description

technical field [0001] The invention relates to the technical field of grain insect identification, in particular to a grain insect identification method and identification system based on feature fusion of SSD algorithm. Background technique [0002] During the whole process of production, processing and storage, grain, oil and food will be attacked by stored grain pests. Grain worms will not only eat food and cause loss of food quantity, but also the products of their life metabolism will heat up food, aggravate the activity of food microorganisms, make food rotten and deteriorate, and may induce the production of microbial toxins. In addition, due to the existence of the dead bodies and excreta of pests in the food, the food is also polluted, the hygienic quality of the food is reduced, and the health of users is endangered. [0003] At present, with the development of computer technology, the informatization requirements of the grain industry are getting higher and high...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a grain insect identification method and identification system based on feature fusion of SSD algorithm, to solve the problem of inaccurate identification of grain insects in the prior art

Images