More Web Proxy on the site http://driver.im/

research-article

Using EfficientNet and transfer learning for image-based diagnosis of nutrient deficiencies

Authors:

Borja Espejo-Garcia,

Ioannis Malounas,

Aikaterini Kasimati,

Spyros FountasAuthors Info & Claims

Volume 196, Issue C

https://doi.org/10.1016/j.compag.2022.106868

Published: 01 May 2022 Publication History

Highlights

•

We performed nutrient deficiency identification by using deep learning techniques.

•

We evaluated different recent architectures and transfer learning strategies.

•

We used two different datasets for checking the generalization ability.

•

We used the Grad-CAM++ technique for validating the learning output.

•

We have made publicly available a new dataset containing nutrient deficiencies in orange trees.

Abstract

Early diagnosis of nutrient deficiencies can play a major role in avoiding significant agricultural losses and increasing the final yield while preserving the environment through efficient fertilizer usage. In this work, we study how well nutrient deficiency symptoms can be recognized in RGB images by using deep neural networks and transfer learning. Two different datasets, presenting real-world conditions, were used for this purpose. The first one was the Deep Nutrient Deficiency for Sugar Beet (DND-SB) dataset, which contains 5648 images of sugar beets presenting nitrogen (N), phosphorous (P), and potassium (K) deficiencies, the omission of liming (Ca) and full fertilization. The second one, collected on the field for this research and currently publicly available, was a dataset combining different orange tree images with iron (Fe), potasssium (K), magnesium (Mg), and manganese (Mn) deficiencies. Image classification via fine-tuning with EfficientNetB4, whose original weights came from a noisy student training on ImageNet, obtained the best performances on both datasets with 98.65% and 98.52% Top-1 accuracies. Additionally, the Grad-CAM++ analysis showed that the models were performing an accurate analysis of the most relevant part inside the images. Finally, the use of agricultural transfer learning did not report improvement in the performances.

References

[1]

Afonso, M.V., Blok, P.M., Polder, G., Wolf, J.M., van der Wolf, Kamp, J., 2019. Blackleg detection in potato plants using convolutional neural networks, 6th IFAC Conference on Sensing, Control and Automation Technologies for Agriculture, AgriControl.

[2]

M. Arsenovic, M. Karanovic, S. Sladojevic, A. Anderla, D. Stefanović, Solving current limitations of deep learning based approaches for plant disease detection, Symmetry 11 (2019) 939.

[3]

J.G.A. Barbedo, Factors influencing the use of deep learning for plant disease recognition, Biosyst. Eng. 172 (2018) 84–91.

[4]

Bashir, M., Ali, S., Ghauri, M., Adris, A., Harun, R., 2013. Impact of excessive nitrogen fertilizers on the environment and associated mitigation strategies.

[5]

Barker, A., Pilbeam, D., 2015. Handbook of plant nutrition.

[6]

Canziani, A., Paszke, A., Culurciello, E., 2016. An analysis of deep neural network models for practical applications. arXiv:1605.07678.

[7]

C. Cevallos, H. Ponce, E. Moya-Albor, J. Brieva, Vision-based analysis on leaves of tomato crops for classifying nutrient deficiency using convolutional neural networks, 2020 International Joint Conference on Neural Networks (IJCNN) (2020) 1–7.

[8]

Chattopadhay, A.; Sarkar, A.; Howlader, P.; Balasubramanian, V.N., 2018. Grad-cam++: generalized gradient-based visual explanations for deep convolutional networks. In Proceedings of the IEEE Winter Conference on Applications of Computer Vision, Lake Tahoe, NV, USA, 12–15 March 2018; pp. 839–847.

[9]

Chandra, A.L., Desai, S.V., Guo, W., Balasubramanian, V.N., 2020. Computer vision with deep learning for plant phenotyping in agriculture: a survey. ArXiv, abs/2006.11391.

[10]

Chollet, F., others, 2015. Keras. https://keras.io.

[11]

B. Espejo-Garcia, N. Mylonas, L. Athanasakos, S. Fountas, I. Vasilakoglou, Towards weeds identification assistance through transfer learning, Comput. Electron. Agric. 171 (2020) 105306,.

Digital Library

[12]

B. Espejo-Garcia, N. Mylonas, L. Athanasakos, S. Fountas, Improving weeds identification with a repository of agricultural pre-trained deep neural networks, Comput. Electron. Agric. 175 (2020) 105593,.

[13]

K.P. Ferentinos, Deep learning models for plant disease detection and diagnosis, Comput. Electron. Agric. 145 (2018) 311–318.

Digital Library

[14]

Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F., Brendel, W. (2019). ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. ArXiv, abs/1811.12231.

[15]

X. Glorot, Y. Bengio, Understanding the difficulty of training deep feedforward neural networks, AISTATS (2010).

[16]

K.A. Han, U. Watchareeruetai, Classification of nutrient deficiency in black gram using deep convolutional neural networks, in: 2019 16th International Joint Conference on Computer Science and Software Engineering (JCSSE), 2019, pp. 277–282.

[17]

K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016) 770–778.

[18]

A.G. Howard, M. Sandler, G. Chu, L. Chen, B. Chen, M. Tan, W. Wang, Y. Zhu, R. Pang, V. Vasudevan, Q.V. Le, H. Adam, Searching for MobileNetV3, 2019 IEEE/CVF International Conference on Computer Vision (ICCV) (2019) 1314–1324.

[19]

G. Huang, Z. Liu, K.Q. Weinberger, Densely connected convolutional networks, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017) 2261–2269.

[20]

Kühl, N., Goutier, M., Baier, L., Wolff, C., Martin, D., 2020. Human vs. supervised machine learning: who learns patterns faster? ArXiv, abs/2012.03661.

[21]

Lecun, Y., Bottou, L., Bengio, Y., Haffner, P., 1998. Gradient-based learning applied to document recognition. In: Proc. of the IEEE.

[22]

Marcus, G., 2018. Deep learning: a critical appraisal. ArXiv, abs/1801.00631.

[23]

Marschner, H., Marschner, P., 2011. Marschner's mineral nutrition of higher plants.

[24]

Mishkin, D., Matas, Jiri., 2016. All you need is a good init. In: Proceedings of the International Conference on Learning Representations (ICLR) 2016.

[25]

S.P. Mohanty, D.P. Hughes, M. Salathé, Using deep learning for image-based plant disease detection, Front. Plant Sci. (2016) 7.

[26]

A. Olsen, D.A. Konovalov, B. Philippa, P. Ridd, J.C. Wood, J. Johns, W. Banks, B. Girgenti, O. Kenny, J. Whinney, B. Calvert, M.R. Azghadi, R.D. White, DeepWeeds: a multiclass weed species image dataset for deep learning, Sci. Rep. 9 (1) (2019),.

[27]

Perez, L., Wang, J., 2017. The effectiveness of data augmentation in image classification using deep learning. ArXiv, abs/1712.04621.

[28]

Pereira, C.S., Morais, R., Reis, M.C., 2019. Deep learning techniques for grape plant species identification in natural images. Sensors (Basel, Switzerland), 19.

[29]

C. Potena, D. Nardi, A. Pretto, Fast and accurate crop and weed identification with summarized train sets for precision agriculture, Adv. Intell. Syst. Comput. 531 (2016) 105–121.

[30]

Reyes, A.K., Caicedo, J.C., Camargo, J.E., 2015. Fine-tuning deep convolutional networks for plant recognition. In: CLEF.

[31]

P.K. Sethy, N.K. Barpanda, A.K. Rath, S.K. Behera, Nitrogen deficiency prediction of rice crop based on convolutional neural network, J. Ambient Intell. Hum. Comput. 11 (11) (2020) 5703–5711.

[32]

C. Shorten, T. Khoshgoftaar, A survey on image data augmentation for deep learning, J. Big Data 6 (2019) 1–48.

[33]

Sladojevic, S., Arsenovic, M., Anderla, A., Culibrk, D., Stefanović, D., 2016. Deep neural networks based recognition of plant diseases by leaf image classification. Comput. Intell. Neurosci.

[34]

H.K. Suh, J. IJsselmuiden, J.W. Hofstee, E.J. van Henten, Transfer learning for the classification of sugar beet and volunteer potato under field conditions, Biosyst. Eng. 174 (2018) 50–65.

[35]

Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A., 2016. Inception-v4, Inception-ResNet and the impact of residual connections on learning. In: Thirty-First AAAI Conference on Artificial Intelligence. pp. 4278–4284.

[36]

Szegedy, C., Vanhoucke, V., Loffe, S., Shlens, J., Wojna, Z., 2015. Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; 2015-Decem:2818–2826:arXiv:1512.00567v3.

[37]

Tan, M., Le, Q.V., 2019. EfficientNet: rethinking model scaling for convolutional neural networks. ArXiv, abs/1905.11946.

[38]

M. Tan, Q.V. Le, EfficientNetV2: smaller models and faster training, ICML (2021).

[39]

T.-T. Tran, J.-W. Choi, T.-T. Le, J.-W. Kim, A comparative study of deep CNN in forecasting and classifying the macronutrient deficiencies on development of tomato plant, Appl. Sci. 9 (8) (2019) 1601,.

[40]

Tzilivakis, J., Green, A., Warner, D.J., Lewis, K.A., 2020. Identification of approaches and measures in action programmes under Directive 91/676/EEC. Final report: Report prepared for Directorate-General Environment, European Commission, for project ENV.D.1/SER/2018/0017 by the Agriculture and Environment Research Unit (AERU), University of Hertfordshire, United Kingdom.

[41]

R. Vatansever, I.I. Ozyigit, E. Filiz, Essential and beneficial trace elements in plants, and their transport in roots: a review, Appl. Biochem. Biotechnol. 181 (2016) 464–482.

[42]

U. Watchareeruetai, P. Noinongyao, C. Wattanapaiboonsuk, P. Khantiviriya, S. Duangsrisai, Identification of plant nutrient deficiencies using convolutional neural networks, 2018 International Electrical Engineering Congress (iEECON) (2018) 1–4.

[43]

Q. Xie, E. Hovy, M. Luong, Q.V. Le, Self-training with noisy student improves ImageNet classification, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020) 10684–10695.

[44]

Z. Xu, X.i. Guo, A. Zhu, X. He, X. Zhao, Y.i. Han, R. Subedi, Using deep convolutional neural networks for image-based diagnosis of nutrient deficiencies in rice, Comput. Intell. Neurosci. 2020 (2020) 1–12.

[45]

Yi, J., Krusenbaum, L., Unger, P., Hüging, H., Seidel, S., Schaaf, G., Gall, J., 2020. Deep learning for non-invasive diagnosis of nutrient deficiencies in sugar beet using RGB images. Sensors (Basel, Switzerland), 20.

Cited By

Yigit EAksoy ADuysak HIşiker H(2024)Detection of moisture of flowing grain with a novel deep learning structure using 2D spectrogram dataComputers and Electronics in Agriculture10.1016/j.compag.2024.109180224:COnline publication date: 1-Sep-2024
https://dl.acm.org/doi/10.1016/j.compag.2024.109180
Qin SDing YZhou TZhai MZhang ZFan MLv XZhang ZZhang L(2024)“Image-Spectral” fusion monitoring of small cotton samples nitrogen content based on improved deep forestComputers and Electronics in Agriculture10.1016/j.compag.2024.109002221:COnline publication date: 18-Jul-2024
https://dl.acm.org/doi/10.1016/j.compag.2024.109002
Liu QWang CJiang JWu JWang XCao QTian YZhu YCao WLiu X(2024)Multi-source data fusion improved the potential of proximal fluorescence sensors in predicting nitrogen nutrition status across winter wheat growth stagesComputers and Electronics in Agriculture10.1016/j.compag.2024.108786219:COnline publication date: 1-Apr-2024
https://dl.acm.org/doi/10.1016/j.compag.2024.108786
Show More Cited By

Index Terms

Using EfficientNet and transfer learning for image-based diagnosis of nutrient deficiencies
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
  2. Machine learning
    1. Learning paradigms
      1. Supervised learning
    2. Machine learning approaches
      1. Neural networks

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

Recommendations

Delineation of management zones with soil apparent electrical conductivity to improve nutrient management

The apparent electrical conductivity (ECa) was measured in excessively drained to imperfect soils.The ECa was a potential estimator of soil properties and nutrients.The ECa measurements successfully delimited two homogeneous soil zones.The ECa maps have ...
Soil nutrient prediction for paddy cultivation via soil fertility and pH trained hybrid architecture: Recommendations based on nutrient deficiency

Soil testing can assist in determining how much fertilizer is necessary, as it depends on the fertility and crop of the soil. Through soil fertility and pH-trained hybrid architecture, a new soil nutrient prediction model for paddy agriculture is ...
Towards weeds identification assistance through transfer learning
Highlights
- Weed identification using deep learning techniques.
- Different pre-processing ...
Abstract
Reducing the use of pesticides through selective spraying is an important component towards a more sustainable computer-assisted agriculture. Weed identification at early growth stage contributes to reduced herbicide rates. However, ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Computers and Electronics in Agriculture

Computers and Electronics in Agriculture Volume 196, Issue C

May 2022

700 pages

ISSN:0168-1699

Issue’s Table of Contents

Elsevier B.V.

Publisher

Elsevier Science Publishers B. V.

Netherlands

Publication History

Published: 01 May 2022

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

6
Total Citations
View Citations
0
Total Downloads

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

Reflects downloads up to 23 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Yigit EAksoy ADuysak HIşiker H(2024)Detection of moisture of flowing grain with a novel deep learning structure using 2D spectrogram dataComputers and Electronics in Agriculture10.1016/j.compag.2024.109180224:COnline publication date: 1-Sep-2024
https://dl.acm.org/doi/10.1016/j.compag.2024.109180
Qin SDing YZhou TZhai MZhang ZFan MLv XZhang ZZhang L(2024)“Image-Spectral” fusion monitoring of small cotton samples nitrogen content based on improved deep forestComputers and Electronics in Agriculture10.1016/j.compag.2024.109002221:COnline publication date: 18-Jul-2024
https://dl.acm.org/doi/10.1016/j.compag.2024.109002
Liu QWang CJiang JWu JWang XCao QTian YZhu YCao WLiu X(2024)Multi-source data fusion improved the potential of proximal fluorescence sensors in predicting nitrogen nutrition status across winter wheat growth stagesComputers and Electronics in Agriculture10.1016/j.compag.2024.108786219:COnline publication date: 1-Apr-2024
https://dl.acm.org/doi/10.1016/j.compag.2024.108786
Goyal PSharda RSaini MSiag M(2024)A deep learning approach for early detection of drought stress in maize using proximal scale digital imagesNeural Computing and Applications10.1007/s00521-023-09219-z36:4(1899-1913)Online publication date: 1-Feb-2024
https://dl.acm.org/doi/10.1007/s00521-023-09219-z
Nguyen ANguyen KTran HQuach L(2023)Using Optimization Algorithms to Improve The Classification Of Diseases On Rice Leaf Of EfficientNet-B4 ModelProceedings of the 2023 8th International Conference on Intelligent Information Technology10.1145/3591569.3591606(209-215)Online publication date: 24-Feb-2023
https://dl.acm.org/doi/10.1145/3591569.3591606
Yin LZhao M(2023)Inception-embedded attention memory fully-connected network for short-term wind power predictionApplied Soft Computing10.1016/j.asoc.2023.110279141:COnline publication date: 1-Jul-2023
https://dl.acm.org/doi/10.1016/j.asoc.2023.110279

View Options

View options

Media

Figures

Other

Tables

View Issue’s Table of Contents