Abstract: This paper presents an image recognition method for most types of rice pests. ResNet34 network is improved to realize the recognition ability of the network, so as to automatically recognize and classify the main pests based on the given image. In addition, the transfer learning method overcomes the shortcomings of insufficient training caused by insufficient data. Firstly, the ImageNet database is used for network parameter pre training to make the network have good feature extraction ability. According to the migration learning method, the IDADP database is used for parameter fine-tuning and training. In this paper, the performance of the proposed improved ResNet34 model is compared with other models. The results show that the improved ResNet34 model has the highest recognition accuracy, and the F₁-score is 0.98, which proves that the proposed model has a good recognition effect on rice pest images.