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 May 26:13:875693.
doi: 10.3389/fpls.2022.875693. eCollection 2022.

Automatic Plant Disease Detection Based on Tranvolution Detection Network With GAN Modules Using Leaf Images

Yan Zhang  1 , Shiyun Wa  1 , Longxiang Zhang  2 , Chunli Lv  1
Affiliations

Automatic Plant Disease Detection Based on Tranvolution Detection Network With GAN Modules Using Leaf Images

Yan Zhang et al. Front Plant Sci. .

Abstract

The detection of plant disease is of vital importance in practical agricultural production. It scrutinizes the plant's growth and health condition and guarantees the regular operation and harvest of the agricultural planting to proceed successfully. In recent decades, the maturation of computer vision technology has provided more possibilities for implementing plant disease detection. Nonetheless, detecting plant diseases is typically hindered by factors such as variations in the illuminance and weather when capturing images and the number of leaves or organs containing diseases in one image. Meanwhile, traditional deep learning-based algorithms attain multiple deficiencies in the area of this research: (1) Training models necessitate a significant investment in hardware and a large amount of data. (2) Due to their slow inference speed, models are tough to acclimate to practical production. (3) Models are unable to generalize well enough. Provided these impediments, this study suggested a Tranvolution detection network with GAN modules for plant disease detection. Foremost, a generative model was added ahead of the backbone, and GAN models were added to the attention extraction module to construct GAN modules. Afterward, the Transformer was modified and incorporated with the CNN, and then we suggested the Tranvolution architecture. Eventually, we validated the performance of different generative models' combinations. Experimental outcomes demonstrated that the proposed method satisfyingly achieved 51.7% (Precision), 48.1% (Recall), and 50.3% (mAP), respectively. Furthermore, the SAGAN model was the best in the attention extraction module, while WGAN performed best in image augmentation. Additionally, we deployed the proposed model on Hbird E203 and devised an intelligent agricultural robot to put the model into practical agricultural use.

Keywords: Generative Adversarial Networks; deep learning; detection network; leaf images; plant disease detection; transformer.

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
Dataset visualization. (A,D,I) Images on solid color backgrounds. (B,C,G) Images via color channel variation. (E,F) Images from practical production scenes. (H) Electronic document image.
Figure 2
Figure 2
Processing of removal of interferential leaf details.
Figure 3
Figure 3
Demonstration of five date augmentation methods. (A) Mixup; (B) Mosaic; (C) CutMix; (D) CutOut.
Figure 4
Figure 4
Structure of the Tranvolution detection network with GAN modules.
Figure 5
Figure 5
Flow chart of SAGAN.
Figure 6
Figure 6
The ground truth in the dataset.
Figure 7
Figure 7
The detection results of YOLO v3 in the dataset.
Figure 8
Figure 8
The detection results of SSD in the dataset.
Figure 9
Figure 9
The detection results of EfficientDet L2 in the dataset.
Figure 10
Figure 10
The detection results of our model in the dataset.
Figure 11
Figure 11
Illustration of noise mask generated by different GAN models. (A) Feature maps generated by WGAN. (B) Feature maps generated by SAGAN.
Figure 12
Figure 12
Intelligent agricultural robot, with infrared distance measurement and multiple cameras deployed on the bottom.
See this image and copyright information in PMC

References

    1. Agarwal M., Singh A., Arjaria S., Sinha A., Gupta S. (2020). Toled: tomato leaf disease detection using convolution neural network. Proc. Comput. Sci. 167, 293–301. 10.1016/j.procs.2020.03.225 - DOI
    1. Anderson R., Bayer P. E., Edwards D. (2020). Climate change and the need for agricultural adaptation. Curr. Opin. Plant Biol. 56, 197–202. 10.1016/j.pbi.2019.12.006 - DOI - PubMed
    1. Bochkovskiy A., Wang C.-Y., Liao H.-Y. M. (2020). YOLOv4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934. 10.48550/arXiv.2004.10934 - DOI - PubMed
    1. Chen S., Haralick R. M. (1995). Recursive erosion, dilation, opening, and closing transforms, in IEEE Transactions on Image Processing (Seoul: IEEE; ), 335–345. 10.1109/83.366481 - DOI - PubMed
    1. DeVries T., Taylor G. W. (2017). Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552. 10.48550/arXiv.1708.04552 - DOI

LinkOut - more resources