research-article

Automatic localization of image semantic patches for crop disease recognition

Authors:

Linsheng Huang,

Wenjiang Huang,

Dong LiangAuthors Info & Claims

Volume 165, Issue C

https://doi.org/10.1016/j.asoc.2024.112076

Published: 01 November 2024 Publication History

Abstract

Crop disease recognition plays a crucial role in agricultural production. However, disease images are large in scale and have a lot of redundant information, which reduces the effectiveness of deep neural networks in extracting diseases. To address the above issues and considering that not all image regions are relevant to disease recognition, this study proposes an efficient crop disease recognition method with dynamic reduction of image redundancy. The method is a two-stage process. In the first stage, we employ the lightweight CA-AnchorNet, which incorporates coordinate attention, to swiftly generate a feature map of the affected crop areas. Subsequently, class activation maps (CAMs) are utilized to identify the disease feature regions, highlighting areas that exhibit class discriminability. These regions are then mapped to a higher resolution from the original lower-resolution image, and the target patch is extracted. In the second stage, these local semantic patches, characterized by reduced spatial redundancy, are fed into the lightweight PatchNet for accurate recognition. PatchNet incorporates the Inception-C module and the ACON-C activation function. These features enhance the model's ability to express multi-scale and non-linear characteristics of crop disease features. This method does not require manually annotated region boxes and achieves an identification accuracy of 99.86 % on a 12-class crop disease dataset with complex environments. The parameter count is only 0.98 M. This method has the characteristics of accurate localization and low parameter count, and can be used for effective and high-precision recognition of crop diseases in complex environments.

Highlights

•

Coordinate attention mechanism was used to design a lightweight CA-AnchorNet.

•

A lightweight CA-AnchorNet and PatchNet constitute a two-stage framework.

•

A patch localization algorithm was designed through a class activation map.

•

A multi-scale lightweight PatchNet network is proposed.

References

[1]

Y. Alqahtani, M. Nawaz, T. Nazir, A. Javed, F. Jeribi, A. Tahir, An improved deep learning approach for localization and recognition of plant leaf diseases, Expert Syst. Appl. 230 (2023).

[2]

N.C. Eli-Chukwu, Applications of artificial intelligence in agriculture: a review, Eng. Technol. Appl. Sci. 9 (4) (2019) 4377–4383.

[3]

B. De Ville, Decision trees, Wires Comput. Stat. 5 (6) (2013) 448–455.

[4]

C. Mfuka, X. Zhang, E. Byamukama, Mapping and quantifying white mold in soybean across south dakota using landsat images, J. Geogr. Inform. Syst. 11 (3) (2019) 331–346.

[5]

J. Zhao, S. Du, L. Huang, Monitoring wheat powdery mildew (Blumeria graminis f. sp. tritici) using multisource and multitemporal satellite images and support vector machine classifier, Smart Agric. 4 (1) (2022) 17–28.

[6]

E.M.F. El Houby, A survey on applying machine learning techniques for management of diseases, J. Appl. Biomed. 16 (3) (2018) 165–174.

[7]

L. Birgé, P. Massart, Gaussian model selection, J. Eur. Math. Soc. 3 (3) (2001) 203–268.

[8]

D.R. Anamisa, A. Rachmad, M. Yusuf, A. Jauhari, R.D.T. Erdiansa, M.Y. Hariyawan, Classification of diseases for rice plant based on naive bayes classifier with a combination of promethee, Commun. Math. Biol. Neurosci. 2021 (2021) 95.

[9]

L.C. Ngugi, M. Abelwahab, M. Abo-zahhad, Recent advances in image processing techniques for automated leaf pest and disease recognition – a review, Inform. Process. Agr. 8 (1) (2021) 27–51.

[10]

F. Saeed, M.A. Khan, M. Sharif, M. Mittal, L.M. Goyal, S. Roy, Deep neural network features fusion and selection based on PLS regression with an application for crops diseases classification, Appl. Soft Comput. 103 (2021).

Digital Library

[11]

W. Lin, J. Chu, L. Leng, J. Miao, L. Wang, Feature disentanglement in one-stage object detection, Pattern Recognit. 145 (2024).

[12]

Y. Zhang, J. Chu, L. Leng, J. Miao, Mask-refined R-CNN: A network for refining object details in instance segmentation, Sens. -BASEL 20 (4) (2020) 1010.

[13]

C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, Z. Wojna, Rethinking the inception architecture for computer vision, Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recog. (CVPR) (2016) 2818–2826.

[14]

K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recog. (CVPR) (2016) 770–778.

[15]

G. Huang, Z. Liu, L. Van Der Maaten, K.Q. Weinberger, Densely connected convolutional networks, Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recog. (CVPR) (2017) 4700–4708.

[16]

A.G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, H. Adam, Mobilenets: Efficient convolutional neural networks for mobile vision applications, arXiv Preprint (2017) arXiv:1704.04861.

[17]

K. Han, Y. Wang, Q. Tian, J. Guo, C. Xu, C. Xu, GhostNet: More features from cheap operations, Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recog. (CVPR) (2020) 1580–1589.

[18]

Y. Wang, K. Lv, R. Huang, S. Song, L. Yang, G. Huang, Glance and focus: a dynamic approach to reducing spatial redundancy in image classification, Adv. Neural Inf. Process. Syst. 33 (2020) 2432–2444.

[19]

C. Yang, Z. An, Y. Xu, Localizing semantic patches for accelerating image classification, Proc. IEEE Int. Conf. Multimed. Expo. (ICME) (2022) 1–6.

[20]

Y. Chen, Y. Huang, Z. Zhang, Z. Wang, B. Liu, C. Liu, C. Huang, S. Dong, X. Pu, F. Wan, X. Qiao, W. Qian, Plant image recognition with deep learning: A review, Comput. Electron. Agr. 212 (2023).

[21]

G. Yang, Y. He, Y. Yang, B. Xu, Fine-grained image classification for crop disease based on attention mechanism, Front. Plant Sci. 11 (2020).

[22]

S. Albahli, M. Masood, Efficient attention-based CNN network (EANet) for multi-class maize crop disease classification, Front. Plant Sci. 13 (2022).

[23]

J. Lin, Y. Chen, R. Pan, T. Cao, J. Cai, D. Yu, X. Chi, T. Cernava, X. Zhang, X. Chen, CAMFFNet: a novel convolutional neural network model for tobacco disease image recognition, Comput. Electron. Agr. 202 (2022).

[24]

R. Wang, L. Wu, Drought-tolerant crop disease identification based on attention mechanism, IEEE Inf. Technol. Netw. Electro Autom. Control Conf. (ITNEC) 6 (2023) 1139–1143.

[25]

W. Min, Z. Wang, J. Yang, C. Liu, S. Jiang, Vision-based fruit recognition via multi-scale attention CNN, Comput. Electron. Agr. 210 (2023).

[26]

S.H. Lee, H. Goëau, P. Bonnet, A. Joly, Attention-based recurrent neural network for plant disease classification, Front. Plant Sci. 11 (2020).

[27]

V. Mnih, N. Heess, A. Graves, K. Kavukcuoglu, Recurrent models of visual attention, Int. Conf. Neural Inf. Process. Syst. 2 (2014) 2204–2212.

[28]

H.J. Yu, C.H. Son, Leaf spot attention network for apple leaf disease identification, CVF Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW) (2020) 229–237.

[29]

J. Pan, T. Wang, Q. Wu, RiceNet: a two stage machine learning method for rice disease identification, Biosyst. Eng. 225 (2023) 25–40.

[30]

Q. Hou, D. Zhou, J. Feng, Coordinate attention for efficient mobile network design, Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recog. (CVPR) (2021) 13713–13722.

[31]

M. Tan, Q.V. Le, EfficientNet: Rethinking model scaling for convolutional neural networks, Proc. Int. Conf. Mach. Learn. (ICML) (2019) 6105–6114.

[32]

M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, L.C. Chen, Mobilenetv2: Inverted residuals and linear bottlenecks, Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recog. (CVPR) (2018) 4510–4520.

[33]

N. Ma, X. Zhang, M. Liu, J. Sun, Activate or not: Learning customized activation, Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recog. (CVPR) (2021) 8032–8042.

[34]

C. Szegedy, S. Ioffe, V. Vanhoucke, A.A. Alemi, Inception-v4, inception-ResNet and the impact of residual connections on learning, Proc. AAAI Conf. Artif. Intell. (AAAI) (2017) 12–18.

[35]

B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, A. Torralba, Learning deep features for discriminative localization, Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recog. (CVPR) (2016) 2921–2929.

[36]

L. Bottou, Stochastic gradient descent tricks, Stochastic gradient descent tricks, Neural Networks: Tricks of the Trade, Second Edition, Springer Berlin Heidelberg, Berlin, Heidelberg, 2012, pp. 421–436.

[37]

S. Ioffe, C. Szegedy, Batch normalization: accelerating deep network training by reducing internal covariate shift, Proc. Int. Conf. Mach. Learn. (ICML) (2015) 448–456.

[38]

G. Chen, T. Gu, J. Lu, J.A. Bao, J. Zhou, Person re-identification via attention pyramid, IEEE Trans. Image Process. 30 (2021) 7663–7676.

[39]

W. Rong, Z. Yang, L. Leng, Channel group-wise drop network with global and fine-grained-aware representation learning for palm recognition, IEEE Int. Jt. Conf. Biom. (IJCB) (2022) 1–9.

[40]

Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, B. Guo, Swin transformer: Hierarchical vision transformer using shifted windows, Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recog. (CVPR) (2021) 10012–10022.

[41]

W. Wang, E. Xie, X. Li, D.-P. Fan, K. Song, D. Liang, T. Lu, P. Luo, L. Shao, Pyramid vision transformer: a versatile backbone for dense prediction without convolutions, Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recog. (CVPR) (2021) 568–578.

[42]

Z. Xia, X. Pan, S. Song, L.E. Li, G. Huang, Vision transformer with deformable attention, Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recog. (CVPR) (2022) 4794–4803.

[43]

J. Hu, L. Shen, G. Sun, Squeeze-and-excitation networks, Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recog. (CVPR) (2018) 7132–7141.

[44]

S. Woo, J. Park, J.Y. Lee, I.S. Kweon, CBAM: Convolutional block attention module, Proc. Eur. Conf. Comput. Vis. (ECCV) (2018) 3–19.

[45]

P. Ramachandran, B. Zoph, Q.V. Le, Searching for activation functions, arXiv Preprint (2017) arXiv: 1710.05941.

[46]

A. Howard, M. Sandler, B. Chen, W. Wang, L.C. Chen, M. Tan, G. Chu, V. Vasudevan, Y. Zhu, R. Pang, Q. Le, H. Adam, Searching for mobileNetV3, Proc. IEEE Int. Conf. Comput. Vis. (ICCV) (2019) 1314–1324.

[47]

G. Huang, D. Chen, T. Li, F. Wu, L. van der Maaten, K.Q. Weinberger, Multi-scale dense networks for resource efficient image classification, arXiv Preprint (2017) arXiv:1703.09844.

[48]

H. Li, H. Zhang, X. Qi, Y. Ruigang, G. Huang, Improved techniques for training adaptive deep networks, Proc. IEEE Int. Conf. Comput. Vis. (ICCV) (2019) 1891–1900.

[49]

L. Yang, Y. Han, X. Chen, S. Song, J. Dai, G. Huang, Resolution adaptive networks for efficient inference, Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recog. (CVPR) (2020) 2369–2378.

Index Terms

Automatic localization of image semantic patches for crop disease recognition
1. Applied computing
  1. Computers in other domains
    1. Agriculture
  2. Life and medical sciences
    1. Health care information systems
    2. Health informatics
2. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision problems
        Object detection
  2. Machine learning
    1. Machine learning approaches
      1. Neural networks

Index terms have been assigned to the content through auto-classification.

Recommendations

Multi-View Fusion Network for Crop Disease Recognition
ICACS '21: Proceedings of the 5th International Conference on Algorithms, Computing and Systems

During the growth of crops, crop yields will be affected by various diseases. Automatic and accurate recognition of crop diseases and determination of disease severity are the key to crop disease prevention and control. In practice, due to noise ...
Automatic facial expression recognition using features of salient facial patches
Extraction of discriminative features from salient facial patches plays a vital role in effective facial expression recognition. The accurate detection of facial landmarks improves the localization of the salient patches on face images. This paper ...
A generalizable and interpretable model for early warning of pest-induced crop diseases using environmental data
Highlights
- ML model predicts rice pests and resulting diseases using environmental factors.
- Model achieved high overall F1 score and mean AUC value, demonstrating generalizability.
- Explainable AI revealed importance of environmental factors.
Abstract
Pest infestations and resulting crop diseases threaten global food security. Traditional pest and disease monitoring methods are time-consuming and prone to delays, thus necessitating the development of effective prediction strategies that ...

Comments

Information & Contributors

Information

Published In

cover image Applied Soft Computing

Applied Soft Computing Volume 165, Issue C

Nov 2024

1386 pages

Issue’s Table of Contents

Elsevier B.V.

Publisher

Elsevier Science Publishers B. V.

Netherlands

Publication History

Published: 01 November 2024

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

0
Total Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 20 Feb 2025

Other Metrics

View Author Metrics

Citations

View Options

View options

Figures

Tables

Media

View Issue’s Table of Contents