Deep Feature Extraction and Machine Learning Method for Leaf Disease Detection in Plants

Yıl 2022, Cilt: 34 Sayı: 1, 123 - 132, 20.03.2022

Orhan Yaman , Türker Tuncer

https://doi.org/10.35234/fumbd.982348

Cited By: 3

Öz

The development of deep learning methods has positively affected smart agriculture practices. Deep learning and machine learning are used in many areas such as detecting diseases in tree and plant leaves, predicting fruit and vegetable yields. In this study, leaf disease was detected by using deep learning and feature selection methods. For the proposed method, a total of 726 images of walnut leaves were collected. These images consist of two classes, healthy and diseased. Deep learning models were used to extract features from these images. 17 deep learning models were tested and the best two models were selected. These two models are designated as DarkNet53 and ResNet101. The features from these two models are combined. Thus, hybrid feature extraction was created. ReliefF algorithm is used for feature selection. Thus, the most weighty features were selected. Support Vector Machine (SVM) algorithm is used for the classification of selected features. With the proposed method, 99.58% accuracy was calculated.

Anahtar Kelimeler

Leaf disease detection, deep feature extraction, ReliefF, DenseNet53, ResNet101.

Bitkilerdeki Yaprak Hastalığı Tespiti için Derin Özellik Çıkarma ve Makine Öğrenmesi Yöntemi

Öz

Derin öğrenme yöntemlerinin gelişmesi akıllı tarım uygulamalarını olumlu yönde etkilemiştir. Ağaç ve bitki yapraklarındaki hastalıkların tespit edilmesi, meyve ve sebze rekoltelerinin tahmin edilmesi gibi birçok alanda derin öğrenme ve makine öğrenmesi kullanılmaktadır. Bu çalışmada derin öğrenme ve özellik seçme yöntemi kullanılarak yaprak hastalığı tespit edilmiştir. Önerilen yöntem için ceviz yapraklarından oluşan 726 görüntü toplanmıştır. Bu görüntüler sağlıklı ve hastalıklı olmak üzere iki sınıftan oluşmaktadır. Bu görüntülerden özellik çıkarımı yapmak için derin öğrenme modelleri kullanılmıştır. 17 adet derin öğrenme modeli test edilmiş ve en iyi iki model seçilmiştir. Bu iki model DarkNet53 ve ResNet101 olarak belirlenmiştir. Bu iki modelden elde edilen özellikler birleştirilmiştir. Böylece hibrit bir özellik çıkarımı oluşturulmuştur. Özellik seçimi için ReliefF algoritması kullanılmıştır. Böylece en ağırlıklı özellikler seçilmiştir. Seçilen özelliklerin sınıflandırılması için Destek Vektör Makinesi (DVM) algoritması kullanılmıştır. Önerilen yöntem ile %99.58 doğruluk hesaplanmıştır.

Anahtar Kelimeler

Yaprak hastalığı tespiti, derin özellik çıkarımı, ReliefF, DenseNet53, ResNet101.

Kaynakça

• Singh, V., and Misra, A.K. (2017) Detection of plant leaf diseases using image segmentation and soft computing techniques. Inf. Process. Agric., 4 (1), 41–49.
• Singh, D., Jain, N., Jain, P., Kayal, P., Kumawat, S., and Batra, N. (2020) PlantDoc: A dataset for visual plant disease detection. ACM Int. Conf. Proceeding Ser., 249–253.
• Rao, A., and Kulkarni, S.B. (2020) A Hybrid Approach for Plant Leaf Disease Detection and Classification Using Digital Image Processing Methods. Int. J. Electr. Eng. Educ., 1–19.
• Radovanovic, D., and Dukanovic, S. (2020) Image-Based Plant Disease Detection: A Comparison of Deep Learning and Classical Machine Learning Algorithms. 2020 24th Int. Conf. Inf. Technol. IT 2020, (February), 1–4.
• Dhakal, A., and Shakya, S. (2018) Image-Based Plant Disease Detection with Deep Learning. Int. J. Comput. Trends Technol., 61 (1), 26–29.
• Hammad Saleem, M., Khanchi, S., Potgieter, J., and Mahmood Arif, K. (2020) Image-based plant disease identification by deep learning meta-architectures. Plants, 9 (11), 1–23.
• Ganatra, N., and Patel, A. (2020) A multiclass plant leaf disease detection using image processing and machine learning techniques. Int. J. Emerg. Technol., 11 (2), 1082–1086.
• Ahmad, I., Hamid, M., Yousaf, S., Shah, S.T., and Ahmad, M.O. (2020) Optimizing pretrained convolutional neural networks for tomato leaf disease detection. Complexity, 2020.
• Sibiya, M., and Sumbwanyambe, M. (2019) A Computational Procedure for the Recognition and Classification of Maize Leaf Diseases Out of Healthy Leaves Using Convolutional Neural Networks. AgriEngineering, 1 (1), 119–131.
• Wang, G., Sun, Y., and Wang, J. (2017) Automatic Image-Based Plant Disease Severity Estimation Using Deep Learning. Comput. Intell. Neurosci., 2017.
• Türkoğlu, M., and Hanbay, D. (2019) Plant disease and pest detection using deep learning-based features. Turkish J. Electr. Eng. Comput. Sci., 27 (3), 1636–1651.
• Meena Prakash, R., Saraswathy, G.P., Ramalakshmi, G., Mangaleswari, K.H., and Kaviya, T. (2018) Detection of leaf diseases and classification using digital image processing. Proc. 2017 Int. Conf. Innov. Information, Embed. Commun. Syst. ICIIECS 2017, 2018-Janua, 1–4.
• Durmus, H., Gunes, E.O., and Kirci, M. (2017) Disease detection on the leaves of the tomato plants by using deep learning. 2017 6th Int. Conf. Agro-Geoinformatics, Agro-Geoinformatics 2017, 0–4.
• Mohanty, S.P., Hughes, D.P., and Salathé, M. (2016) Using deep learning for image-based plant disease detection. Front. Plant Sci., 7 (September), 1–10.
• Mohameth, F., Bingcai, C., and Sada, K.A. (2020) Plant Disease Detection with Deep Learning and Feature Extraction Using Plant Village. J. Comput. Commun., 08 (06), 10–22.
• B. Rajesh, M. Vishnu Sai Vardhan, L.S. (2020) Leaf Disease Detection and Classification by Decision Tree. Mach. Learn. Found., (ICOEI), 705–708.
• Das, D., Singh, M., Mohanty, S.S., and Chakravarty, S. (2020) Leaf Disease Detection using Support Vector Machine. Proc. 2020 IEEE Int. Conf. Commun. Signal Process. ICCSP 2020, 1036–1040.
• Kshyanaprava Panda Panigrahi, Himansu Das, A.K.S., and Moharana, S.C. (2020) Maize Leaf Disease Detection and Classification Using Machine Learning Algorithms. Prog. Comput. Anal. Networking, Springer, Singapore, 659–669.
• Tiwari, D., Ashish, M., Gangwar, N., Sharma, A., Patel, S., and Bhardwaj, S. (2020) Potato Leaf Diseases Detection Using Deep Learning. Proc. Int. Conf. Intell. Comput. Control Syst. ICICCS 2020, (Iciccs), 461–466.
• Jiang, P., Chen, Y., Liu, B., He, D., and Liang, C. (2019) Real-Time Detection of Apple Leaf Diseases Using Deep Learning Approach Based on Improved Convolutional Neural Networks. IEEE Access, 7, 59069–59080.
• Divakar, S., Bhattacharjee, A., and Priyadarshini, R. (2021) Smote-DL: A Deep Learning Based Plant Disease Detection Method. 2021 6th Int. Conf. Converg. Technol. I2CT 2021, 4–9.
• Dhaware, C.G., and Wanjale, K.H. (2017) A modern approach for plant leaf disease classification which depends on leaf image processing. 2017 Int. Conf. Comput. Commun. Informatics, ICCCI 2017, 31–34.
• Kumar, S., Prasad, K., Srilekha, A., Suman, T., Rao, B.P., and Vamshi Krishna, J.N. (2020) Leaf disease detection and classification based on machine learning. Proc. Int. Conf. Smart Technol. Comput. Electr. Electron. ICSTCEE 2020, 361–365.
• Dharanika, T., Ruban Karthik, S., Sabhariesh Vel, S., Vyaas, S., and Yogeshwaran, S. (2021) Automatic Leaf Disease Identification and Fertilizer Agrobot. 2021 7th Int. Conf. Adv. Comput. Commun. Syst. ICACCS 2021, 1341–1344.
• Mattihalli, C., Gedefaye, E., Endalamaw, F., and Necho, A. (2018) Plant leaf diseases detection and auto-medicine. Internet of Things, 1–2, 67–73.
• Nalawade, R., Nagap, A., Jindam, L., and Ugale, M. (2020) Agriculture Field Monitoring and Plant Leaf Disease Detection. 2020 3rd Int. Conf. Commun. Syst. Comput. IT Appl. CSCITA 2020 - Proc., 226–231.
• Chouhan, S.S., Singh, U.P., and Jain, S. (2021) Automated Plant Leaf Disease Detection and Classification Using Fuzzy Based Function Network. Wirel. Pers. Commun., (0123456789).
• Ertam, F. (2019) An efficient hybrid deep learning approach for internet security. Phys. A Stat. Mech. its Appl., 535, 122492.
• Yaman, O., Tuncer, T., and Tasar, B. (2021) DES-Pat: A novel DES pattern-based propeller recognition method using underwater acoustical sounds. Appl. Acoust., 175, 107859.
• Baygin, M., Yaman, O., Tuncer, T., Dogan, S., Datta, P., and Acharya, R. (2021) Biomedical Signal Processing and Control Automated accurate schizophrenia detection system using Collatz pattern technique with EEG signals. Biomed. Signal Process. Control, 70 (June), 102936.
• Tuncer, T., Dogan, S., and Ozyurt, F. (2020) An automated Residual Exemplar Local Binary Pattern and iterative ReliefF based COVID-19 detection method using chest X-ray image. Chemom. Intell. Lab. Syst., (January).
• Kira, K., and Rendell, L.A. (1992) Feature selection problem: traditional methods and a new algorithm. Proc. Tenth Natl. Conf. Artif. Intell., 129–134.
• Kononenko, I. (1994) Estimating attributes: Analysis and extensions of RELIEF. Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), 784 LNCS, 171–182.