Recognition of Common Insect in Field Based on Deep Learning

Abstract

Traditional insect taxonomy methods have high technical requirements, and the ability of artificial identification of insects is insufficient. In order to solve the problem, this paper proposes a method of common insects recognition in field based on transfer learning. A total of 9 kinds of insects, such as mythimna separata, rice borer, rice plant hopper, mole cricket, mantis, locust, grass fly, ladybug, and ditch beetle are collected for classification and identification, those include the main insect pests and some natural enemies of the main food crops in the field, such as wheat, rice, corn, etc. Then we use the digital image processing technology and the confrontation generation network to expend the insect dataset, and build a model based on transfer learning to transfer the knowledge learned by VGG16, VGG19, InceptionV3, and InceptionV4 on the ImageNet dataset to the insect classification and recognition. Experimental results show that the transfer learning training model has better classification performance and higher convergence speed, and data expansion can help extend sample and avoid overfitting. The highest recognition accuracy is up to 97.39% among models, which adopt the VGG19 convolutional neural network to pretrain the model for transfer learning. This method has the high recognition accuracy, less time consumption, simple and convenient, robustness in particular for the translation and rotation, which provides a reference for the identification and classification method of field insects.