Mehdhar S. A. M. Al-gaashani

Tomato leaf disease classification by exploiting transfer learning and feature concatenation

• Authors Details :  
• Mehdhar S. A. M. Al-gaashani

Journal title : IET Image Processing

Publisher : Institution of Engineering and Technology (IET)

Online ISSN : 1751-9667

Page Number : 913-925

Journal volume : 16

Journal issue : 3

283 Views Original Article

Tomato is one of the most important vegetables worldwide. It is considered a mainstayof many countries’ economies. However, tomato crops are vulnerable to many diseasesthat lead to reducing or destroying production, and for this reason, early and accuratediagnosis of tomato diseases is very urgent. For this reason, many deep learning modelshave been developed to automate tomato leaf disease classification. Deep learning isfar superior to traditional machine learning with loads of data, but traditional machinelearning may outperform deep learning for limited training data. The authors proposea tomato leaf disease classification method by exploiting transfer learning and featuresconcatenation. The authors extract features using pre-trained kernels (weights) fromMobileNetV2 and NASNetMobile; then, they concatenate and reduce the dimensionalityof these features using kernel principal component analysis. Following that, they feedthese features into a conventional learning algorithm. The experimental results confirmthe effectiveness of concatenated features for boosting the performance of classifiers.The authors have evaluated the three most popular traditional machine learning classifiers,random forest, support vector machine, and multinomial logistic regression; amongthem, multinomial logistic regression achieved the best performance with an averageaccuracy of 97%.

Article DOI & Crossmark Data

DOI : https://doi.org/10.1049/ipr2.12397

Article Subject Details

• Artificial Intelligence
• Computer Science
• Computer Science Applications

Article Keywords Details

• DL
• ML
• Tomato leaf disease
• Transfer learning

Article File

Full Text PDF

Article References

• (1). Home Food and Agriculture Organization of the United Nations.http://www.fao.org/faostat/en/#home(2019). Accessed 1 February 2021
• (2). 10.1007/s13593-018-0507-5
• (3). 10.1007/s12571-012-0200-5
• (4). 10.3390/computers8040077
• (5). 10.1016/j.micpro.2020.103615
• (6). 10.1016/j.compag.2010.06.009
• (7). 10.1016/j.compag.2017.04.013
• (8). 10.3390/plants9101302
• (9). Hong H. Lin J. Huang F.:Tomato Disease Detection and Classification by Deep Learning. In:Proc. ? 2020 Int. Conf. Big Data Artif. Intell. Internet Things Eng. ICBAIE 2020 pp.25–29(2020)
• (10). Hlaing C.S. Zaw S.M.M.:Tomato Plant Diseases Classification Using Statistical Texture Feature and Color Feature. In:2018 IEEE/ACIS 17th International Conference on Computer and Information Science (ICIS) pp.439–444(2018)
• (11). 10.1007/s11277-020-07590-x
• (12). 10.1049/iet-cvi.2015.0414
• (13). 10.1049/iet-ipr.2017.0822
• (14). Batool A. Hyder S.B. Rahim A. Waheed N. Asghar M.A.:Fawad: Classification and identification of tomato leaf disease using deep neural network. In:2020 Int. Conf. Eng. Emerg. Technol. ICEET 2020(2020)
• (15). 10.1016/j.procs.2020.03.225
• (16). 10.1049/iet-cvi.2019.0136
• (17). 10.1016/j.suscom.2020.100407
• (18). 10.1016/j.compeleceng.2019.04.011
• (19). Nithish E.K. Kaushik M. Prakash P. Ajay R. Veni S.:Tomato leaf disease detection using convolutional neural network with data augmentation. In:Proc. 5th Int. Conf. Commun. Electron. Syst. ICCES 2020 pp.1125–1132(2020)
• (20). 10.3389/fpls.2016.01419
• (21). 10.1017/9781139061773
• (22). 10.1016/j.compag.2020.105466
• (23). 10.1016/j.compag.2019.01.041
• (24). 10.1007/s11263-015-0816-y
• (25). Sandler M. Howard A. Zhu M. Zhmoginov A. Chen L.C.:MobileNetV2: Inverted Residuals and Linear Bottlenecks. In:Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. pp.4510–4520(2018)
• (26). Howard A.G. Zhu M. Chen B. et al.:MobileNets: Efficient convolutional neural networks for mobile vision applications.arXiv (2017)
• (27). Bishop C.M.:Pattern Recoginiton and Machine Learning. (2006)
• (28). Wang Q.:Kernel Principal Component Analysis and its Applications in Face Recognition and Active Shape Models(2012)
• (29). 10.1155/2019/9152506
• (30). 10.1007/BF00994018
• (31). keras?team/keras: Deep Learning for humans.https://github.com/fchollet/keras(2015). Accessed March 2021

---

More Article by Mehdhar S. A. M. Al-Gaashani