Abstract—Agricultural production has become a key factor for the well-being of citizens and stability of the world economy. However, pest diseases in the fields will reduce the production of crops and pose a threat to food security. In order to solve this problem, farmers have to use more advanced pest recognition systems to identify the types of pest diseases quickly rather than making judgement based on their own observation. This paper presents an artificial intelligence recognition model based on multi-scale convolutional neural network called LH-DenseNet. In this model, the advanced deep convolution network model DenseNet is used as the basic framework, and the large-scale public dataset ImageNet is used to train the convolution neural network's powerful feature extraction ability by applying various data enhancement strategies. Extracting and integrating the global and detailed features of images can improve the accuracy of pest classification. Thus, it can enhance the potential of deep learning in the field of agriculture, allowing more autonomic and systematic systems emerge.
Index Terms—Agricultural production, pest diseases, pest recognition, multi-scale convolutional neural network, LH-DenseNet.
Sihai Li is with High School Affiliated to Renmin University of China, Beijing, China (e-mail: lisihai1424@gmail.com).
Cite: Sihai Li, "Recognition of Crop Pest Diseases Based on Multi-scale Artificial Intelligence," International Journal of Future Computer and Communication vol. 11, no. 4, pp. 84-87, 2022.
Copyright © 2022 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
Copyright © 2008-2025. International Journal of Future Computer and Communication. All rights reserved.
E-mail: editor@ijfcc.org