Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Dec 22:13:1088531.
doi: 10.3389/fpls.2022.1088531. eCollection 2022.

Research on cassava disease classification using the multi-scale fusion model based on EfficientNet and attention mechanism

Mingxin Liu  1 , Haofeng Liang  1 , Mingxin Hou  2
Affiliations

Research on cassava disease classification using the multi-scale fusion model based on EfficientNet and attention mechanism

Mingxin Liu et al. Front Plant Sci. .

Abstract

Cassava disease is one of the leading causes to the serious decline of cassava yield. Because it is difficult to identify the characteristics of cassava disease, if not professional cassava growers, it will be prone to misjudgment. In order to strengthen the judgment of cassava diseases, the identification characteristics of cassava diseases such as different color of cassava leaf disease spots, abnormal leaf shape and disease spot area were studied. In this paper, deep convolutional neural network was used to classify cassava leaf diseases, and image classification technology was used to recognize and classify cassava leaf diseases. A lightweight module Multi-scale fusion model (MSFM) based on attention mechanism was proposed to extract disease features of cassava leaves to enhance the classification of disease features. The resulting feature map contained key disease identification information. The study used 22,000 cassava disease leaf images as a data set, including four different cassava leaf disease categories and healthy cassava leaves. The experimental results show that the cassava leaf disease classification model based on multi-scale fusion Convolutional Neural Network (CNN) improves EfficientNet compared with the original model, with the average recognition rate increased by nearly 4% and the average recognition rate up to 88.1%. It provides theoretical support and practical tools for the recognition and early diagnosis of plant disease leaves.

Keywords: EfficientNet; attention mechanism; classification; deep learning; multi-scale feature fusion.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
Cassava disease classification model based on multi-scale fusion.
Figure 2
Figure 2
EfficientNet-B6 model structure.
Figure 3
Figure 3
CBAM structure diagram.
Figure 4
Figure 4
Channel Attention Mechanism structure diagram.
Figure 5
Figure 5
Spatial attention mechanism.
Figure 6
Figure 6
Multi-scale fusion module.
Figure 7
Figure 7
Images of cassava leaf diseases (A–D is the disease of four different cassava leaves and e is the healthy leaf).
Figure 8
Figure 8
Cassava Bacterial Blight. (A) original (B) Rotation by 180° (C)Brightness reduction (D) Horizontal flipping.
Figure 9
Figure 9
Cassava Brown Streak Disease. (A) original (B) Rotation by 180° (C) Brightness reduction (D) Horizontal flipping.
Figure 10
Figure 10
Cassava Green Mottle. (A) original (B) Rotation by 180° (C) Brightness reduction (D)Horizontal flipping.
Figure 11
Figure 11
Cassava Mosaic Disease. (A) original (B) Rotation by 180° (C) Brightness reduction (D) Horizontal flipping.
Figure 12
Figure 12
Healthy cassava leaf. (A) original (B) Rotation by 180° (C) Brightness reduction (D) Horizontal flipping.
Figure 13
Figure 13
Confusion matrix for the test set.
Figure 14
Figure 14
Visual comparison of EfficientNet-B6 and our model.
See this image and copyright information in PMC

References

    1. Aamir M., Li Z., Bazai S., Wagan R. A., Bhatti U. A., Nizamani M. M., et al. . (2021). Spatiotemporal change of air-quality patterns in hubei province–a pre-to post-COVID-19 analysis using path analysis and regression. Atmosphere 12 (10), 1338. doi: 10.3390/atmos12101338 - DOI
    1. Bazai S. U., Jang-Jaccard J., Wang R. (2017). “Anonymizing k-NN classification on MapReduce,” in International conference on mobile networks and management (Cham: Springer; ), 364–377.
    1. Bhatti U. A., Ming-Quan Z., Qing-Song H., Ali S., Hussain A., Yuhuan Y., et al. . (2021. a). Advanced color edge detection using Clifford algebra in satellite images. IEEE Photonics J. 13 (2), 1–20. doi: 10.1109/JPHOT.2021.3059703 - DOI
    1. Bhatti U. A., Yu Z., Chanussot J., Zeeshan Z., Yuan L., Luo W., et al. . (2021. b). Local similarity-based spatial–spectral fusion hyperspectral image classification with deep CNN and gabor filtering. IEEE Trans. Geosci. Remote Sens. 60, 1–15. doi: 10.1109/TGRS.2021.3090410 - DOI
    1. Bhatti U. A., Nizamani M. M., Mengxing H. (2022. a). Climate change threatens pakistan’s snow leopards. Science 377 (6606), 585–586. doi: 10.1126/science.add9065 - DOI - PubMed

LinkOut - more resources