A High-Precision Identification Method for Maize Leaf Diseases and Pests Based on LFMNet under Complex Backgrounds
Author:
Liu Jintao1, He Chaoying1, Jiang Yichu2, Wang Mingfang1, Ye Ziqing1, He Mingfang1
Affiliation:
1. College of Electronic Information & Physics, Central South University of Forestry and Technology, Changsha 410004, China 2. Hunan Polytechnic College of Environment and Biology, Hengyang 421005, China
Abstract
Maize, as one of the most important crops in the world, faces severe challenges from various diseases and pests. The timely and accurate identification of maize leaf diseases and pests is of great significance for ensuring agricultural production. Currently, the identification of maize leaf diseases and pests faces two key challenges: (1) In the actual process of identifying leaf diseases and pests, complex backgrounds can interfere with the identification effect. (2) The subtle features of diseases and pests are difficult to accurately extract. To address these challenges, this study proposes a maize leaf disease and pest identification model called LFMNet. Firstly, the localized multi-scale inverted residual convolutional block (LMSB) is proposed to perform preliminary down-sampling on the image, preserving important feature information for the subsequent extraction of fine disease and pest features in the model structure. Then, the feature localization bottleneck (FLB) is proposed to improve the model’s ability to focus on and locate disease and pest characteristics and to reduce interference from complex backgrounds. Subsequently, the multi-hop local-feature fusion architecture (MLFFA) is proposed, which effectively addresses the problem of extracting subtle features by enhancing the extraction and fusion of global and local disease and pest features in images. After training and testing on a dataset containing 19,451 images of maize leaf diseases and pests, the LFMNet model demonstrated excellent performance, with an average identification accuracy of 95.68%, a precision of 95.91%, a recall of 95.78%, and an F1 score of 95.83%. Compared to existing models, it exhibits significant advantages, offering robust technical support for the precise identification of maize diseases and pests.
Funder
Hunan Provincial Natural Science Foundation of China Scientific Research Project of Education Department of Hunan Province National Natural Science Foundation of China
Reference46 articles.
1. Xue, Y.F., Li, X.J., Yan, W., Miao, Q., Zhang, C.Y., Huang, M., Sun, J., Qi, S.B., Ding, Z.H., and Cui, Z.L. (2023). Biofortification of different maize cultivars with zinc, iron and selenium by foliar fertilizer applications. Front. Plant Sci., 14. 2. Dabija, A., Ciocan, M.E., Chetrariu, A., and Codină, G.G. (2021). Maize and Sorghum as Raw Materials for Brewing, a Review. Appl. Sci., 11. 3. Global maize production, utilization, and consumption;Ranum;Ann. N. Y. Acad. Sci.,2014 4. Maize: A paramount staple crop in the context of global nutrition;Nuss;Comp. Rev. Food Sci. F,2010 5. Multi-channel feature fusion networks with hard coordinate attention mechanism for maize disease identification under complex backgrounds;Fang;Comput. Electron. Agric.,2022
|
|