Multi-channel feature fusion networks with hard coordinate attention mechanism for maize disease identification under complex backgrounds

被引:43
作者
Fang, Shundong [1 ]
Wang, Yanfeng [2 ]
Zhou, Guoxiong [1 ]
Chen, Aibin [1 ]
Cai, Weiwei [1 ]
Wang, Qifan [1 ]
Hu, Yahui [3 ]
Li, Liujun [4 ]
机构
[1] Cent South Univ Forestry & Technol, Coll Comp & Informat Engn, Changsha 410004, Hunan, Peoples R China
[2] Natl Univ Def Technol, Changsha 410015, Hunan, Peoples R China
[3] Acad Agr Sci, Plant Protect Res Inst, Changsha 410125, Hunan, Peoples R China
[4] Univ Missouri Rolla, Dept Civil Architectural & Environm Engn, 11, Rolla, MO 65401 USA
基金
中国国家自然科学基金;
关键词
Maize leaf disease identification; Hard coordinated attention mechanism; Multi-scale convolution; Depthwise separable convolution;
D O I
10.1016/j.compag.2022.107486
中图分类号
S [农业科学];
学科分类号
09 ;
摘要
Maize leaf disease has a negative impact on food security. If maize leaf disease is not controlled in time, it can spread and affect corn quality and yield. Severe maize leaf disease may even result in no harvest at all. In the existing deep learning technology for maize leaf disease recognition, due to the complex growing environment of maize, it is easy to capture the complex background of maize in the image acquisition process, which brings difficulties to the recognition of maize leaf disease. Therefore, we propose a new network architecture, HCA-MFFNet, for maize leaf disease recognition in a complex background. In HCA-MFFNet, hard coordinated attention (HCA) assigned at different spatial scales was used to extract features from maize leaf disease images to reduce the influence of complex backgrounds. In order to retain the feature information of maize leaf disease in the sampling process to the maximum extent, a multi-feature fusion network that can extract the weight in-formation in two spatial directions was constructed. The traditional convolutional layer was replaced by depthwise separable convolutional layer, reducing the number of parameters in the network. In order to verify the feasibility and effectiveness of this model in complex environment, we compare it with existing methods. The average recognition accuracy of the model is 97.75%, and the F1 value is 97.03%. The proposed method is better than the existing methods.
引用
收藏
页数:13
相关论文
共 24 条
[1]  
Aravind KR, 2018, PROCEEDINGS OF THE 2ND INTERNATIONAL CONFERENCE ON INVENTIVE SYSTEMS AND CONTROL (ICISC 2018), P1191, DOI 10.1109/ICISC.2018.8398993
[2]   Attention embedded lightweight network for maize disease recognition [J].
Chen, Junde ;
Wang, Wenhua ;
Zhang, Defu ;
Zeb, Adnan ;
Nanehkaran, Yaser Ahangari .
PLANT PATHOLOGY, 2021, 70 (03) :630-642
[3]   Using deep transfer learning for image-based plant disease identification [J].
Chen, Junde ;
Chen, Jinxiu ;
Zhang, Defu ;
Sun, Yuandong ;
Nanehkaran, Y. A. .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2020, 173
[4]   Identi fi cation of tomato leaf diseases based on combination of ABCK-BWTR and B-ARNet [J].
Chen, Xiao ;
Zhou, Guoxiong ;
Chen, Aibin ;
Yi, Jizheng ;
Zhang, Wenzhuo ;
Hu, Yahui .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2020, 178
[5]   An optimized model based on convolutional neural networks and orthogonal learning particle swarm optimization algorithm for plant diseases diagnosis [J].
Darwish, Ashraf ;
Ezzat, Dalia ;
Hassanien, Aboul Ella .
SWARM AND EVOLUTIONARY COMPUTATION, 2020, 52
[6]   Identification of plant leaf diseases using a nine-layer deep convolutional neural network [J].
Geetharamani, G. ;
Pandian, Arun J. .
COMPUTERS & ELECTRICAL ENGINEERING, 2019, 76 :323-338
[7]  
Howard A., 2018, INVERTED RESIDUALS L
[8]   Densely Connected Convolutional Networks [J].
Huang, Gao ;
Liu, Zhuang ;
van der Maaten, Laurens ;
Weinberger, Kilian Q. .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :2261-2269
[9]   Attention embedded residual CNN for disease detection in tomato leaves [J].
Karthik, R. ;
Hariharan, M. ;
Anand, Sundar ;
Mathikshara, Priyanka ;
Johnson, Annie ;
Menaka, R. .
APPLIED SOFT COMPUTING, 2020, 86
[10]   A survey of the recent architectures of deep convolutional neural networks [J].
Khan, Asifullah ;
Sohail, Anabia ;
Zahoora, Umme ;
Qureshi, Aqsa Saeed .
ARTIFICIAL INTELLIGENCE REVIEW, 2020, 53 (08) :5455-5516