ÖNERİLEN KONVOLÜSYON SİNİR AĞI YAKLAŞIMI KULLANARAK ELMA YAPRAĞI HASTALIKLARININ SINIFLANDIRILMASI

Abstract

Tarım arazilerindeki elma ağaçlarını sürekli olarak kontrol etmek zordur. Ağaç yapraklarında oluşan bir hastalık durumunda diğer yapraklara hastalığın bulaş riski yüksektir. Erken dönemde hastalığın otomatik tespitini gerçekleştirerek bitkinin daha fazla bozulmasını önlemek gereklidir. Eğer hastalık tespitinde geç kalınırsa planlanan üretim gerçekleştirilememektedir. Bir çiftçi ya da tarım uzmanı tarafından hastalıkların tespit edilmesi durumunda geç kalınmaktadır. Buna ek olarak tarım arazileri büyüdükçe ihtiyaç duyulan uzman sayısı da ona göre artış göstermektedir. Bu sebeplerden dolayı elma ağaçlarına ait yaprak görüntülerini kullanarak ağaç yaprakları elma kabuğu, yaprak pası, sağlıklı elma ve birden fazla hastalık durumları olmak üzere 4 farklı sınıfa gruplandırılmıştır. Öne sürülen yöntemde görüntülerde gürültülerin temizlenmesi, ilgili alanın tespiti ve YUV renk uzayı üzerinde histogram eşitleme gerçekleştirilmiştir. Kullanılan veri setinde sınıf dağılımlarının dengesiz olmasından dolayı SMOTE yöntemi ile azınlık olarak kalan sınıflar için veri büyütmesi uygulanmıştır. Sonrasında DenseNet121, DenseNet201, InceptionResNetV2, InceptionV3, ResNet50V2 önceden eğitilmiş ağ modelleri kullanılarak öznitelikler çıkartılmıştır. Çıkartılan öznitelikler geliştirilen CNN tabanlı bir yöntemle 99% doğruluk oranında sınıflandırılma gerçekleştirilmiştir.

Keywords

• Konvolüsyonel Sinir Ağı
• Görüntü İşleme
• Elma Yaprağı
• SMOTE
• Önceden Eğitilmiş Ağ

CLASSIFICATION OF APPLE LEAF DISEASES USING THE PROPOSED CONVOLUTION NEURAL NETWORK APPROACH

Abstract

It is difficult to constantly control apple trees in farmland. In case of a disease on tree leaves, the risk of disease transmission to other leaves is high. It is necessary to prevent further deterioration of the plant by performing automatic detection of the disease in the early period. If the disease detection is delayed, the planned production cannot be realized. It is too late if diseases are detected by a farmer or agronomist. In addition, as the agricultural lands grow, the number of experts needed increases accordingly. For these reasons, leaf images of apple trees are grouped into 4 different classes: apple peel, leaf rust, healthy apple and multiple disease states. In the proposed method, noise removal in the images, detection of the relevant area and histogram equalization on the YUV color space are performed. Due to the unbalanced class distribution in the data set used, data augmentation was applied for the minority classes with the SMOTE method. Afterwards, features are extracted using pre-trained network models DenseNet121, DenseNet201, InceptionResNetV2, InceptionV3, ResNet50V2. Extracted features were classified with a CNN-based method developed with an accuracy of 99%.

Keywords

• Convolutional Neural Network
• Image Processing
• Apple leaf
• SMOTE
• Pre Trained Network.

References

1. Annabel, L. S. P., Annapoorani, T., & Deepalakshmi, P. (2019). Machine Learning for Plant Leaf Disease Detection and Classification – A Review. 2019 International Conference on Communication and Signal Processing (ICCSP), 538–542. https://doi.org/10.1109/ICCSP.2019.8698004
2. Aurangzeb, K., Akmal, F., Khan, M. A., Sharif, M., & Javed, M. Y. (2020). Advanced Machine Learning Algorithm Based System for Crops Leaf Diseases Recognition. 2020 6th Conference on Data Science and Machine Learning Applications (CDMA), 146–151. https://doi.org/10.1109/CDMA47397.2020.00031
3. Bansal, P., Kumar, R., & Kumar, S. (2021). Disease Detection in Apple Leaves Using Deep Convolutional Neural Network. In Agriculture (Vol. 11, Issue 7). https://doi.org/10.3390/agriculture11070617
4. Deng, X., Xu, D., Zeng, M., & Qi, Y. (2019). Does Internet use help reduce rural cropland abandonment? Evidence from China. Land Use Policy, 89, 104243. https://doi.org/10.1016/j.landusepol.2019.104243
5. Divakar, S., Bhattacharjee, A., & Priyadarshini, R. (2021). Smote-DL: A Deep Learning Based Plant Disease Detection Method. 2021 6th International Conference for Convergence in Technology (I2CT), 1–6. https://doi.org/10.1109/I2CT51068.2021.9417920
6. Dubey, S. R., & Jalal, A. S. (2016). Apple disease classification using color, texture and shape features from images. Signal, Image and Video Processing, 10(5), 819–826. https://doi.org/10.1007/s11760-015-0821-1
7. Duralija, B., Putnik, P., Brdar, D., Bebek Markovinović, A., Zavadlav, S., Pateiro, M., Domínguez, R., Lorenzo, J. M., & Bursać Kovačević, D. (2021). The Perspective of Croatian Old Apple Cultivars in Extensive Farming for the Production of Functional Foods. In Foods (Vol. 10, Issue 4). https://doi.org/10.3390/foods10040708
8. Ferentinos, K. P. (2018). Deep learning models for plant disease detection and diagnosis. Computers and Electronics in Agriculture, 145, 311–318. https://doi.org/10.1016/j.compag.2018.01.009

9. Gargade, A., & Khandekar, S. A. (2019). A Review: Custard Apple Leaf Parameter Analysis and Leaf Disease Detection using Digital Image Processing. 2019 3rd International Conference on Computing Methodologies and Communication (ICCMC), 267–271. https://doi.org/10.1109/ICCMC.2019.8819867
10. Gobalakrishnan, N., Pradeep, K., Raman, C. J., Ali, L. J., & Gopinath, M. P. (2020). A Systematic Review on Image Processing and Machine Learning Techniques for Detecting Plant Diseases. 2020 International Conference on Communication and Signal Processing (ICCSP), 465–468. https://doi.org/10.1109/ICCSP48568.2020.9182046
11. Gollapudi, S. (2019). Learn Computer Vision Using OpenCV. https://doi.org/10.1007/978-1-4842-4261-2
12. Han, H., Xiong, J., & Zhao, K. (2021). Digital inclusion in social media marketing adoption: the role of product suitability in the agriculture sector. Information Systems and E-Business Management. https://doi.org/10.1007/s10257-021-00522-7
13. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770–778.
14. Hoang, N.-D., & Nguyễn Quốc, L. (2018). Metaheuristic Optimized Edge Detection for Recognition of Concrete Wall Cracks: A Comparative Study on the Performances of Roberts, Prewitt, Canny, and Sobel Algorithms. Advances in Civil Engineering, 2018, 1–16. https://doi.org/10.1155/2018/7163580
15. Hou, J., Huo, X., & Yin, R. (2019). Does computer usage change farmers’ production and consumption? Evidence from China. China Agricultural Economic Review, 11(2), 387–410. https://doi.org/10.1108/CAER-09-2016-0149
16. Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 4700–4708.
17. Iqbal, Z., Khan, M. A., Sharif, M., Shah, J. H., ur Rehman, M. H., & Javed, K. (2018). An automated detection and classification of citrus plant diseases using image processing techniques: A review. Computers and Electronics in Agriculture, 153, 12–32. https://doi.org/10.1016/j.compag.2018.07.032
18. Ishaq, A., Sadiq, S., Umer, M., Ullah, S., Mirjalili, S., Rupapara, V., & Nappi, M. (2021). Improving the Prediction of Heart Failure Patients’ Survival Using SMOTE and Effective Data Mining Techniques. IEEE Access, 9, 39707–39716. https://doi.org/10.1109/ACCESS.2021.3064084
19. Khan, M. A., Akram, T., Sharif, M., & Saba, T. (2020). Fruits diseases classification: exploiting a hierarchical framework for deep features fusion and selection. Multimedia Tools and Applications, 79(35), 25763–25783. https://doi.org/10.1007/s11042-020-09244-3
20. Liang, Q., Xiang, S., Hu, Y., Coppola, G., Zhang, D., & Sun, W. (2019). PD2SE-Net: Computer-assisted plant disease diagnosis and severity estimation network. Computers and Electronics in Agriculture, 157, 518–529. https://doi.org/10.1016/j.compag.2019.01.034
21. Mohanty, S. P., Hughes, D. P., & Salathé, M. (2016). Using Deep Learning for Image-Based Plant Disease Detection. Frontiers in Plant Science, 7, 1419. https://doi.org/10.3389/fpls.2016.01419
22. Ni, A., Huang, L., & Xiong, F. (2021). A new perspective of innovation-driven agricultural sustainable development: a case of China. IOP Conference Series: Earth and Environmental Science, 667, 12096. https://doi.org/10.1088/1755-1315/667/1/012096
23. Prashar, K., Talwar, R., & Kant, C. (2017). Robust Automatic Cotton Crop Disease Recognition (ACDR) Method using the Hybrid Feature Descriptor with SVM.
24. Shi, Y., Wang, X. F., Zhang, S. W., & Zhang, C. L. (2015). PNN based crop disease recognition with leaf image features and meteorological data. International Journal of Agricultural and Biological Engineering, 8, 60–68. https://doi.org/10.3965/j.ijabe.20150804.1719
25. Shrivastava, G. (2021). Review on Emerging Trends in Detection of Plant Diseases using Image Processing with Machine Learning. International Journal of Computer Applications, 174. https://doi.org/10.5120/ijca2021920990
26. Singh, V., & Misra, A. K. (2017). Detection of plant leaf diseases using image segmentation and soft computing techniques. Information Processing in Agriculture, 4(1), 41–49. https://doi.org/10.1016/j.inpa.2016.10.005
27. Sottocornola, G., Stella, F., & Zanker, M. (2021). Counterfactual Contextual Multi-Armed Bandit: a Real-World Application to Diagnose Apple Diseases.
28. Sujatha, R., Chatterjee, J. M., Jhanjhi, N. Z., & Brohi, S. N. (2021). Performance of deep learning vs machine learning in plant leaf disease detection. Microprocessors and Microsystems, 80, 103615. https://doi.org/10.1016/j.micpro.2020.103615
29. Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. A. (2017). Inception-v4, inception-resnet and the impact of residual connections on learning. Thirty-First AAAI Conference on Artificial Intelligence.
30. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. B. (2016). Rethinking the Inception Architecture for Computer Vision. https://doi.org/10.1109/CVPR.2016.308
31. Tahir, M. Bin, Khan, M. A., Javed, K., Kadry, S., Zhang, Y.-D., Akram, T., & Nazir, M. (2021). Recognition of Apple Leaf Diseases using Deep Learning and Variances-Controlled Features Reduction. Microprocessors and Microsystems, 104027. https://doi.org/10.1016/j.micpro.2021.104027
32. Thapa, R., Zhang, K., Snavely, N., Belongie, S., & Khan, A. (2020). The Plant Pathology Challenge 2020 data set to classify foliar disease of apples. Applications in Plant Sciences, 8(9), e11390. https://doi.org/10.1002/aps3.11390
33. Tiwari, D., Ashish, M., Gangwar, N., Sharma, A., Patel, S., & Bhardwaj, S. (2020). Potato Leaf Diseases Detection Using Deep Learning. https://doi.org/10.1109/ICICCS48265.2020.9121067
34. Turkoglu, M., Hanbay, D., & Sengur, A. (2019). Multi-model LSTM-based convolutional neural networks for detection of apple diseases and pests. Journal of Ambient Intelligence and Humanized Computing. https://doi.org/10.1007/s12652-019-01591-w
35. Wang, G., Sun, Y., & Wang, J. (2017). Automatic Image-Based Plant Disease Severity Estimation Using Deep Learning. Computational Intelligence and Neuroscience, 2017, 2917536. https://doi.org/10.1155/2017/2917536
36. Zhang, S., Huang, W., & Zhang, C. (2019). Three-channel convolutional neural networks for vegetable leaf disease recognition. Cognitive Systems Research, 53, 31–41. https://doi.org/10.1016/j.cogsys.2018.04.006
37. Zhu, X., Hu, R., Zhang, C., & Shi, G. (2021). Does Internet use improve technical efficiency? Evidence from apple production in China. Technological Forecasting and Social Change, 166, 120662. https://doi.org/10.1016/j.techfore.2021.120662