PRE-TRAINED NETWORK BASED DEEP NETWORK MODEL FOR CLASSIFICATION OF LEAF DISEASES

Year 2021, , 442 - 456, 31.12.2021

Halit Çetiner

https://doi.org/10.54365/adyumbd.988049

Cited By: 4

Abstract

Early diagnosis of plant-damaging diseases is very important to reduce the consumption of chemical pesticides, to save money and to prevent pollution to the environment. In case of any disease in apple tree leaves, farmers have to get support from expert agricultural personnel in order to detect the signs of disease at an early stage. This situation creates a great cost to the farmers. In order to solve the aforementioned problem, a deep learning model based on the Convolutional Neural Network (CNN) method has been developed to classify scab, rust and multiple disease groups in which both can be used together. The proposed approach consists of a combination of CNN layers using popular transfer learning techniques DenseNet201, MobileNetV2, ResNet50V2, ResNet101V2, ResNet152V2 algorithms as input layer. The developed method has been tested on a data set with high difficulty level, which includes different levels of illumination, noise, and heterogeneous illumination. With the CNN-based method recommended in the test processes, the classification accuracy rate was 97%.

Keywords

CNN, apple leaf disease, classification, transfer learning

YAPRAK HASTALIKLARININ SINIFLANDIRILABİLMESİ İÇİN ÖNCEDEN EĞİTİLMİŞ AĞ TABANLI DERİN AĞ MODELİ

Abstract

Bitkiye zarar veren hastalıkların erken teşhisi, kimyasal tarım ilaçlarının tüketimini azaltmak, mali olarak tasarruf etmek ve çevreye verilen kirliliği engelleyebilmek için oldukça önemlidir. Elma ağaç yapraklarında oluşan herhangi bir hastalık durumunda, hastalık belirtilerini erken aşamada tespit edebilmek için çiftçiler uzman tarım personelinden destek almak zorunda kalmaktadır. Bu durum çiftçilere büyük bir maliyet oluşturmaktadır. Bahsedilen problemi çözebilmek adına scab, rust ve her ikisinin bir arada kullanılabileceği çoklu hastalık gruplarını sınıflandırabilmek için Konvolüsyonel Sinir Ağı (CNN) yöntemi tabanlı derin öğrenme modeli geliştirilmiştir. Önerilen yaklaşım popüler transfer öğrenim teknikleri olen DenseNet201, MobileNetV2, ResNet50V2, ResNet101V2, ResNet152V2 algoritmalarını giriş katmanı olarak kullanan CNN katmanlarının birleşiminden oluşmaktadır. Geliştirilen yöntem farklı seviyelerde aydınlatma, gürültü, arka planı homojen olmama durumlarını içeren zorluk seviyesi yüksek bir veri seti üzerinde test edilmiştir. Test işlemlerinde önerilen CNN tabanlı yöntemle sınıflandırma doğruluk oranı olarak %97 değerine ulaşılmıştır.

Keywords

CNN, elma yaprak hastalığı, sınıflandırma, transfer öğrenme

References

• [1] G. Sottocornola, F. Stella, and M. Zanker, Counterfactual Contextual Multi-Armed Bandit: a Real-World Application to Diagnose Apple Diseases. 2021.
• [2] B. Duralija et al., “The Perspective of Croatian Old Apple Cultivars in Extensive Farming for the Production of Functional Foods,” Foods , vol. 10, no. 4. 2021, doi: 10.3390/foods10040708.
• [3] M. Bin Tahir et al., “Recognition of Apple Leaf Diseases using Deep Learning and Variances-Controlled Features Reduction,” Microprocess. Microsyst., p. 104027, 2021, doi: https://doi.org/10.1016/j.micpro.2021.104027.
• [4] R. Thapa, K. Zhang, N. Snavely, S. Belongie, and A. Khan, “The Plant Pathology Challenge 2020 data set to classify foliar disease of apples,” Appl. Plant Sci., vol. 8, no. 9, p. e11390, Sep. 2020, doi: https://doi.org/10.1002/aps3.11390.
• [5] V. Singh and A. K. Misra, “Detection of plant leaf diseases using image segmentation and soft computing techniques,” Inf. Process. Agric., vol. 4, no. 1, pp. 41–49, 2017, doi: https://doi.org/10.1016/j.inpa.2016.10.005.
• [6] G. Wang, Y. Sun, and J. Wang, “Automatic Image-Based Plant Disease Severity Estimation Using Deep Learning,” Comput. Intell. Neurosci., vol. 2017, p. 2917536, 2017, doi: 10.1155/2017/2917536.
• [7] K. Kayaalp and S. Metlek, “Classification of Robust and Rotten Apples by Deep Learning Algorithm,” Sak. Univ. J. Comput. Inf. Sci., vol. 3, no. 2, pp. 111–119, Aug. 2020, doi: 10.35377/saucis.03.02.717452.
• [8] M. Turkoglu, D. Hanbay, and A. Sengur, “Multi-model LSTM-based convolutional neural networks for detection of apple diseases and pests,” J. Ambient Intell. Humaniz. Comput., 2019, doi: 10.1007/s12652-019-01591-w.
• [9] G. Shrivastava, “Review on Emerging Trends in Detection of Plant Diseases using Image Processing with Machine Learning,” Int. J. Comput. Appl., vol. 174, Jan. 2021, doi: 10.5120/ijca2021920990.
• [10] N. Gobalakrishnan, K. Pradeep, C. J. Raman, L. J. Ali, and M. P. Gopinath, “A Systematic Review on Image Processing and Machine Learning Techniques for Detecting Plant Diseases,” in 2020 International Conference on Communication and Signal Processing (ICCSP), 2020, pp. 465–468, doi: 10.1109/ICCSP48568.2020.9182046.
• [11] A. Gargade and S. A. Khandekar, “A Review: Custard Apple Leaf Parameter Analysis and Leaf Disease Detection using Digital Image Processing,” in 2019 3rd International Conference on Computing Methodologies and Communication (ICCMC), 2019, pp. 267–271, doi: 10.1109/ICCMC.2019.8819867.
• [12] B. Liu, Y. Zhang, D. He, and Y. Li, “Identification of Apple Leaf Diseases Based on Deep Convolutional Neural Networks,” Symmetry (Basel)., vol. 10, no. 1, p. 11, 2018, doi: http://dx.doi.org/10.3390/sym10010011.
• [13] O. Russakovsky et al., “ImageNet Large Scale Visual Recognition Challenge,” Int. J. Comput. Vis., vol. 115, no. 3, pp. 211–252, 2015, doi: 10.1007/s11263-015-0816-y.
• [14] E. C. Too, L. Yujian, S. Njuki, and L. Yingchun, “A comparative study of fine-tuning deep learning models for plant disease identification,” Comput. Electron. Agric., vol. 161, pp. 272–279, 2019, doi: https://doi.org/10.1016/j.compag.2018.03.032.
• [15] S. H. Lee, H. Goëau, P. Bonnet, and A. Joly, “New perspectives on plant disease characterization based on deep learning,” Comput. Electron. Agric., vol. 170, p. 105220, 2020, doi: https://doi.org/10.1016/j.compag.2020.105220.
• [16] L. S. P. Annabel, T. Annapoorani, and P. Deepalakshmi, “Machine Learning for Plant Leaf Disease Detection and Classification – A Review,” in 2019 International Conference on Communication and Signal Processing (ICCSP), 2019, pp. 538–542, doi: 10.1109/ICCSP.2019.8698004.
• [17] R. Sujatha, J. M. Chatterjee, N. Z. Jhanjhi, and S. N. Brohi, “Performance of deep learning vs machine learning in plant leaf disease detection,” Microprocess. Microsyst., vol. 80, p. 103615, 2021, doi: https://doi.org/10.1016/j.micpro.2020.103615.
• [18] Y. Shi, X. F. Wang, S. W. Zhang, and C. L. Zhang, “PNN based crop disease recognition with leaf image features and meteorological data,” Int. J. Agric. Biol. Eng., vol. 8, pp. 60–68, Aug. 2015, doi: 10.3965/j.ijabe.20150804.1719.
• [19] K. Aurangzeb, F. Akmal, M. A. Khan, M. Sharif, and M. Y. Javed, “Advanced Machine Learning Algorithm Based System for Crops Leaf Diseases Recognition,” in 2020 6th Conference on Data Science and Machine Learning Applications (CDMA), 2020, pp. 146–151, doi: 10.1109/CDMA47397.2020.00031.
• [20] M. A. Khan, T. Akram, M. Sharif, and T. Saba, “Fruits diseases classification: exploiting a hierarchical framework for deep features fusion and selection,” Multimed. Tools Appl., vol. 79, no. 35, pp. 25763–25783, 2020, doi: 10.1007/s11042-020-09244-3.
• [21] X. Yang and T. Guo, “Machine learning in plant disease research,” Eur. J. Biomed. Res., vol. 3, p. 6, Mar. 2017, doi: 10.18088/ejbmr.3.1.2017.pp6-9.
• [22] S. Metlek and E. E. Kılınç, “Determination of Heart Disease By Machine Learning Methods,” in 5th International Gap Mathematics-Engineering-Science and Health Sciences Congress, 2020, pp. 48–74, doi: ISBN: 978-625-7687-23-2.
• [23] D. F. Mengi and S. Metlek, “Türkiye’nin Akdeniz Bölgesine ait rüzgâr ekserjisinin çok katmanli yapay sinir aği ile modellenmesi,” Int. J. Eng. Innov. Res., vol. 2, no. 2, pp. 102–120, 2020.
• [24] S. Metlek and K. Kayaalp, “Detection of bee diseases with a hybrid deep learning method,” J. Fac. Eng. Archit. Gazi Univ., vol. 36, no. 3, pp. 1716–1731, Mar. 2021, doi: 10.17341/gazimmfd.749443.
• [25] S. P. Mohanty, D. P. Hughes, and M. Salathé, “Using Deep Learning for Image-Based Plant Disease Detection,” Front. Plant Sci., vol. 7, p. 1419, 2016, doi: 10.3389/fpls.2016.01419.
• [26] K. Prashar, R. Talwar, and C. Kant, Robust Automatic Cotton Crop Disease Recognition (ACDR) Method using the Hybrid Feature Descriptor with SVM. 2017.
• [27] D. Tiwari, M. Ashish, N. Gangwar, A. Sharma, S. Patel, and S. Bhardwaj, Potato Leaf Diseases Detection Using Deep Learning. 2020.
• [28] S. R. Dubey and A. S. Jalal, “Apple disease classification using color, texture and shape features from images,” Signal, Image Video Process., vol. 10, no. 5, pp. 819–826, 2016, doi: 10.1007/s11760-015-0821-1.
• [29] Q. Liang, S. Xiang, Y. Hu, G. Coppola, D. Zhang, and W. Sun, “PD2SE-Net: Computer-assisted plant disease diagnosis and severity estimation network,” Comput. Electron. Agric., vol. 157, pp. 518–529, Feb. 2019, doi: 10.1016/j.compag.2019.01.034.
• [30] S. Zhang, W. Huang, and C. Zhang, “Three-channel convolutional neural networks for vegetable leaf disease recognition,” Cogn. Syst. Res., vol. 53, pp. 31–41, 2019, doi: https://doi.org/10.1016/j.cogsys.2018.04.006.
• [31] K. Kayaalp and S. Metlek, “Classification of Robust and Rotten Apples by Deep Learning Algorithm,” Sak. Univ. J. Comput. Inf. Sci., vol. 3, pp. 111–119, Aug. 2020, doi: 10.35377/saucis.03.02.717452.
• [32] K. P. Ferentinos, “Deep learning models for plant disease detection and diagnosis,” Comput. Electron. Agric., vol. 145, pp. 311–318, 2018, doi: https://doi.org/10.1016/j.compag.2018.01.009.
• [33] G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 4700–4708.
• [34] X. Yu, N. Zeng, S. Liu, and Y.-D. Zhang, “Utilization of DenseNet201 for diagnosis of breast abnormality,” Mach. Vis. Appl., vol. 30, no. 7, pp. 1135–1144, 2019, doi: 10.1007/s00138-019-01042-8.
• [35] K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2016, pp. 770–778, doi: 10.1109/CVPR.2016.90.
• [36] T. Liu, M. Chen, M. Zhou, S. S. Du, E. Zhou, and T. Zhao, “Towards understanding the importance of shortcut connections in residual networks,” arXiv Prepr. arXiv1909.04653, 2019.
• [37] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “Mobilenetv2: Inverted residuals and linear bottlenecks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 4510–4520.
• [38] P. Bansal, R. Kumar, and S. Kumar, “Disease Detection in Apple Leaves Using Deep Convolutional Neural Network,” Agriculture , vol. 11, no. 7. 2021, doi: 10.3390/agriculture11070617.
• [39] S. Divakar, A. Bhattacharjee, and R. Priyadarshini, “Smote-DL: A Deep Learning Based Plant Disease Detection Method,” in 2021 6th International Conference for Convergence in Technology (I2CT), 2021, pp. 1–6, doi: 10.1109/I2CT51068.2021.9417920.