The Efficiency of Transfer Learning and Data Augmentation in Lemon Leaf Image Classification

Öz

Leaf diseases in trees and plants are important factors that directly affect the yield of agricultural products. This problem may cause a decrease in the production capacity and profitability of farmers. For this reason, computer-aided detection and classification systems are needed to accurately detect plant diseases. In recent years, learning algorithms and image-processing techniques have been used effectively in the agricultural sector. In this study, the efficiency of transfer learning and data augmentation methods on a dataset consisting of lemon leaf images is examined and the classification of diseased and healthy lemon leaf images is performed. In our study, VGG16, ResNet50, and DenseNet201 transfer learning methods were applied both with and without data increment, and the effect of data augmentation on performance was evaluated. Among the deep transfer learning methods used, DenseNet201 gave the highest accuracy rate with 98.29%. This study shows that transfer learning methods can effectively distinguish between diseased and healthy lemon leaves. It has also been observed that data augmentation does not always provide performance improvement. In future studies, it is predicted that it will be appropriate to evaluate the effect of data augmentation more effectively by applying deep transfer learning methods to plants with different class numbers.

Anahtar Kelimeler

• Data Augmentation
• Image Processing
• Lemon Leaf Diseases
• Transfer Learning

Limon Yaprağı Görüntü Sınıflandırmasında Transfer Öğrenme ve Veri Artırımın Etkinliği

Öz

Ağaç ve bitkilerde yaprak hastalıkları, tarımsal ürünlerin verimini doğrudan etkileyen önemli faktörlerdir. Bu sorun, çiftçilerin üretim kapasitelerinin ve karlılık düzeylerinin düşmesine neden olabilmektedir. Bu nedenle bitki hastalıklarını doğru bir şekilde tespit edebilmek için bilgisayar destekli tespit ve sınıflandırma sistemlerine ihtiyaç duyulmaktadır. Son yıllarda öğrenme algoritmaları ve görüntü işleme teknikleri tarım sektöründe etkin bir şekilde kullanılmaktadır. Bu çalışmada, limon yaprağı görüntülerinden oluşan bir veri kümesi üzerinde transfer öğrenme ve veri artırma yöntemlerinin etkinliği incelenerek hastalıklı ve sağlıklı limon yaprağı görüntüleri sınıflandırılması işlemi yapılmaktadır. Çalışmamızda VGG16, ResNet50 ve DenseNet201 transfer öğrenme yöntemleri hem veri artırımlı hem de artırımsız olarak uygulanmış ve veri artırmanın performansa etkisi değerlendirilmiştir. Kullanılan derin transfer öğrenme yöntemleri arasında en yüksek doğruluk oranını %98,29 ile DenseNet201 vermiştir. Gerçekleştirilen bu çalışma, transfer öğrenme yöntemlerinin hastalıklı ve sağlıklı limon yapraklarını etkili bir şekilde ayırt edebildiğini göstermektedir. Veri artırmanın her zaman performans iyileşmesi sağlamadığı da gözlemlenmiştir. Gelecekteki çalışmalarda derin transfer öğrenme yöntemleri farklı sınıf sayılarına sahip bitkilerde uygulanarak veri artırmanın etkisinin daha etkili bir şekilde değerlendirilmesinin uygun olacağı öngörülmektedir.

Anahtar Kelimeler

• Veri Artırımı
• Görüntü İşleme
• Limon Yaprağı Hastalıkları
• Transfer Öğrenme

Kaynakça

1. Ahmad, I., Hamid, M., Yousaf, S., Shah, S. T., Ahmad, M. O. (2020). Optimizing pretrained convolutional neural networks for tomato leaf disease detection, Complexity, vol. 2020, 1-6.
2. FAO. "A Third More Mouths to Feed, FAO, Roma, Italy." http://www.fao.org/news/story/en/item/35571/icode/, Access Date: 02.06.2023.
3. Sujatha, R., Chatterjee, J. M., Jhanjhi, N., Brohi, S. N. (2021). Performance of deep learning vs machine learning in plant leaf disease detection, Microprocessors and Microsystems, vol. 80, p. 103615.
4. Liliane, T. N. & Charles, M. S. (2020). Factors affecting yield of crops, Agronomy-climate change & food security, p. 9, 2020.
5. Subramanian, B., Jayashree, S., Kiruthika, S., Miruthula, S. (2019), Lemon leaf disease detection and classification using SVM and CNN, International Journal of Recent Technology and Engineering, vol. 8, no. 4, pp. 11485-11488.
6. Banni, R. & Sksvmacet, L. (2018), Citrus leaf disease detection using image processing approaches, International Journal of Pure and Applied Mathematics, vol. 120, no. 6, pp. 727-735.
7. Sardogan, M., Tuncer, A., Ozen, Y. (2018) Plant leaf disease detection and classification based on CNN with LVQ algorithm, in 2018 3rd international conference on computer science and engineering (UBMK), 2018: IEEE, pp. 382-385.
8. Rastogi, A., Arora, R., Sharma, S. Leaf disease detection and grading using computer vision technology & fuzzy logic, in 2015 2nd international conference on signal processing and integrated networks (SPIN), 2015: IEEE, pp. 500-505.

9. Padol, P. B. & Yadav, A. A., SVM classifier based grape leaf disease detection, in 2016 Conference on advances in signal processing (CASP), 2016: IEEE, pp. 175-179.
10. Ahmed, K., Shahidi, T. R., Alam, S. M. I., Momen, S. Rice leaf disease detection using machine learning techniques, in 2019 International Conference on Sustainable Technologies for Industry 4.0 (STI), 2019: IEEE, pp. 1-5.
11. Agarwal, M., Singh, A., Arjaria, S., Sinha, A., Gupta, S. (2020) ToLeD: Tomato leaf disease detection using convolution neural network, Procedia Computer Science, vol. 167, pp. 293-301.
12. Irmak, G., Saygili, A. (2020). Tomato leaf disease detection and classification using convolutional neural networks," in 2020 Innovations in Intelligent Systems and Applications Conference (ASYU), 2020: IEEE, pp. 1-5.
13. Kurmi, Y., Saxena, P., Kirar, B. S., Gangwar, S., Chaurasia, V., Goel, A. (2022), Deep CNN model for crops’ diseases detection using leaf images, Multidimensional Systems and Signal Processing, vol. 33, no. 3, pp. 981-1000.
14. Chen, W., Chen, J., Zeb, A., Yang, S., Zhang, D. (2022). Mobile convolution neural network for the recognition of potato leaf disease images, Multimedia Tools and Applications, vol. 81, no. 15, pp. 20797-20816.
15. Elfatimi, E., Eryigit, R., Elfatimi, L. (2022). Beans leaf diseases classification using MobileNet models, IEEE Access, vol. 10, pp. 9471-9482, 2022.
16. Anonymous. Healthy vs. Diseased Leaf Image Dataset (Public Domain). https://www.kaggle.com/datasets/amandam1/healthy-vs-diseased-leaf-image-dataset, Access Date: 05.05.2023.
17. Simonyan, K. &. Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition, arXiv preprint arXiv:1409.1556.
18. He, K., Zhang, X., Ren, S., Sun, J. (2016). Deep residual learning for image recognition, in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770-778.
19. Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K. Q. (2017). Densely connected convolutional networks," in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4700-4708.
20. Sahinbas, K. &. Catak, F. O. (2021). Transfer learning-based convolutional neural network for COVID-19 detection with X-ray images," in Data science for COVID-19: Elsevier, pp. 451-466.
21. S. Mukherjee. "ResNet50." https://towardsdatascience.com/the-annotated-resnet-50-a6c536034758, Access Date: 05.06.2023.
22. Sharma, N., Saba, L., Khanna, N. N., Kalra, M. K., Fouda, M. M., Suri, J. S. (2022). Segmentation-Based Classification Deep Learning Model Embedded with Explainable AI for COVID-19 Detection in Chest X-ray Scans, Diagnostics, vol. 12, no. 9, p. 2132, 2022.