magazinelogo

Advances in Computer and Communication

ISSN Online: 2767-2875 CODEN: ACCDC3
Frequency: quarterly Email: acc@hillpublisher.com
Total View: 905112 Downloads: 179439 Citations: 149 (From Dimensions)

Volumes & Issues

Current Issue

All Volumes

ArticleOpen Access http://dx.doi.org/10.26855/acc.2023.06.020

Classification of Crop Disease Images Based on Convolutional Neural Network

Jian Guo

Hangzhou Dianzi University, Hangzhou, Zhejiang, China.

*Corresponding author: Jian Guo

Published: July 24,2023

Abstract

Agriculture is the cornerstone of human survival and affects everyone. Crop diseases are crucial factors that impact crop yields. However, manually diagnosing crop diseases requires specialized knowledge and is prone to high error rates, consuming significant time and societal resources. It also hinders the development of modernized agriculture. Therefore, this paper proposes a Mobile-SKF Net model for crop disease image classification based on MobileNet v2. The Mobile-SKF Net model is built upon the MobileNet v2 model, incorporating channel attention modules to enhance feature representation, followed by classification output. Data augmentation and transformations are applied to the dataset, which is then used for training the Mobile-SKF Net model. The model is validated through experiments. Experimental results demonstrate that the Mobile-SKF Net achieves a crop classification accuracy of 99.41% on the public dataset PlantVillage, exhibiting excellent performance evaluation metrics and accuracy. The Mobile-SKF Net serves as a basis for crop disease identification, providing valuable insights in this field.

Keywords

Convolutional Neural Network, Image Classification, Attention Mechanism

References

[1] Nettleton D F, Katsantonis D, Kalaitzidis A, et al. Predicting rice blast disease: machine learning versus process-based models [J]. BMC Bioinformatics, 2019, 20(1):1-16.

[2] Duarte-Carvajalino J M, Alzate D F, Ramirez A A, et al. Evaluating late blight severity in potato crops using unmanned aerial vehi‐ cles and machine learning algorithms [J]. Remote Sensing, 2018, 10 (10):1513.

[3] Fujita E, Kawasaki Y, Uga H, et al. Basic investigation on a robust and practical plant diagnostic system [C]// 2016 15th IEEE International Conference on Machine Learning and Applications, 2016:989-992. 

[4] Zhang M, Liu J, Cai G Y. Recognition method of citrus canker disease based on convolution neural network [J]. Journal of Computer Applications, 2018, 38(S1):48-52. 

[5] Sandler M, Howard A, Zhu M, et al. Mobilenetv2: Inverted residuals and linear bottlenecks [C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 4510-4520.

[6] Niu Z, Zhong G, Yu H. A review on the attention mechanism of deep learning [J]. Neurocomputing, 2021, 452: 48-62.

[7] Feurer M, Hutter F. Hyperparameter optimization [J]. Automated machine learning: Methods, systems, challenges, 2019: 3-33.

[8] Chen Y, Dai X, Liu M, et al. Dynamic relu [C]//Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XIX 16. Springer International Publishing, 2020: 351-367.

[9] Yu X, Wang S H. Abnormality diagnosis in mammograms by transfer learning based on ResNet18 [J]. Fundamenta Informaticae, 2019, 168(2-4): 219-230.

[10] Zhang X, Zhou X, Lin M, et al. Shufflenet: An extremely efficient convolutional neural network for mobile devices [C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 6848-6856.

[11] Koonce B, Koonce B. MobileNetV3 [J]. Convolutional Neural Networks with Swift for Tensorflow: Image Recognition and Dataset Categorization, 2021: 125-144.

How to cite this paper

Classification of Crop Disease Images Based on Convolutional Neural Network

How to cite this paper: Jian Guo. (2023) Classification of Crop Disease Images Based on Convolutional Neural Network. Advances in Computer and Communication4(3), 205-209.

DOI: http://dx.doi.org/10.26855/acc.2023.06.020