AppleCNN: Elma yaprak hastalıklarının sınıflandırılabilmesi için CNN tabanlı yeni bir derin öğrenme modeli

Yıl 2025, Cilt: 15 Sayı: 1, 51 - 63, 15.03.2025

İbrahim Çetiner

Öz

Gün geçtikçe dünya nüfusu artmakta ve insanların gıda için kullandıkları alanlar azalmaktadır. Mevcut tarım arazilerindeki meyve ağaçları çok sayıda patojen ve böcek nedeniyle sürekli tehdit altındadır. Bundan dolayı sürekli takip edilmesi, maksimum seviyede verim alınabilmesi için önem arz etmektedir. Hem tüketici talebi hem de küresel ticaret açısından elma oldukça önemli bir meyvedir. Bununla birlikte, elmanın gelişimi, kalitesi ve verimi birtakım hastalıklardan etkilenebilir. Başarılı hastalık yönetiminin ve elmalarda başka salgınların önlenmesinin anahtarı, hastalığın erken ve kesin olarak tanımlanmasıdır. Elma yapraklarındaki hastalık erken teşhis edilemez ise aşırı kimyasal kullanımı veya yetersiz kullanımına sebep olabilir. Bu gibi sebepler üretim maliyetlerinin armasına ve çevre, sağlık durumunu olumsuz etki edebilir. Elma yaprak hastalıkları; elma kabuğu, sedir elma pası, sağlıklı elma ve karmaşık hastalık belirtileri (yaprakta birden fazla hastalık) olmak üzere 4 farklı sınıfa gruplandırılmıştır. Önerilen CNN modeli önceden eğitilmiş VGG19, DenseNet169, MobileNetV2, Xception ve NASNetLarge mimarileri giriş katmanı olarak kullanılarak yeni bir CNN model öne sürülmüştür. Bu öne sürülen CNN modeli bilgisayar görünün ön işleme teknikleri ile derin öğrenme tabanlı 23 katmandan oluşmaktadır. Önerilen CNN modeli ile elma meyvesi hastalık sınıfı %98 başarı oranı elde edilmiştir.

Anahtar Kelimeler

Elma yaprak hastalığı, CNN, Bilgisayar görü, Derin öğrenme mimarisi, DenseNet169, NASNetLarge

AppleCNN: A new CNN-based deep learning model for classification of apple leaf diseases

Öz

Day by day, the world's population is increasing and the land people use for food is decreasing. Fruit trees in existing agricultural lands are under constant threat from numerous pathogens and insects. Therefore, continuous monitoring is important to ensure maximum yield. Apple is a very important fruit both in terms of consumer demand and global trade. However, apple growth, quality and yield can be affected by a number of diseases. The key to successful disease management and prevention of further outbreaks in apples is early and accurate identification of the disease. If apple foliar disease is not identified early, it can lead to overuse or underuse of chemicals. This can lead to increased production costs and adverse effects on the environment and health. Apple leaf diseases are grouped into 4 different classes: apple scab, cedar apple rust, healthy apple and complex disease symptoms (more than one disease on the leaf). A new CNN model is proposed by using pre-trained VGG19, DenseNet169, MobileNetV2, Xception and NASNetLarge architectures as input layer. This proposed CNN model consists of 23 layers based on computer vision preprocessing techniques and deep learning. With the proposed CNN model, 98% success rate is achieved for apple fruit disease class.

Anahtar Kelimeler

Apple leaf disease, CNN, Computer vision, Deep learning architecture, DenseNet169, NASNetLarge

Kaynakça

• Abbas, A., Jain, S., Gour, M., & Vankudothu, S. (2021). Tomato plant disease detection using transfer learning with C-GAN synthetic images. Computers and Electronics in Agriculture, 187, 106279.
• Aslam, M., Sana, M. U., Kiren, T., & Irshad, M. J. (2024). Classification of Apple Plant Leaf Diseases Using Deep Convolutional Neural Network. The Asian Bulletin of Big Data Management, 4(02).
• Bansal, P., Kumar, R., & Kumar, S. (2021). Disease Detection in Apple Leaves Using Deep Convolutional Neural Network. In Agriculture, 11(617), 1-23.
• Chaturvedi, S. S., Tembhurne, J. V, & Diwan, T. (2020). A multi-class skin Cancer classification using deep convolutional neural networks. Multimedia Tools and Applications, 79(39), 28477–28498.
• Çetiner, H. (2021). Classification of Apple Leaf Diseases Using The Proposed Convolution Neural Network Approach. Journal of Engineering Sciences and Design, 9(4), 1130–1140.
• Çetiner, H. (2022). Citrus disease detection and classification using based on convolution deep neural network. Microprocessors and Microsystems, 95(104687), 1–10.
• Dalvi, P. P., Edla, D. R., & Purushothama, B. R. (2023). Diagnosis of Coronavirus Disease From Chest X-Ray Images Using DenseNet-169 Architecture. SN Computer Science, 4(3), 214.
• Delalieux, S., van Aardt, J., Keulemans, W., Schrevens, E., & Coppin, P. (2007). Detection of biotic stress (Venturia inaequalis) in apple trees using hyperspectral data: Non-parametric statistical approaches and physiological implications. European Journal of Agronomy, 27(1), 130–143.
• Dittmer, S., King, E. J., & Maass, P. (2020). Singular Values for ReLU Layers. IEEE Transactions on Neural Networks and Learning Systems, 31(9), 3594–3605.
• Eelbode, T., Sinonquel, P., Maes, F., & Bisschops, R. (2021). Pitfalls in training and validation of deep learning systems. Best Practice & Research Clinical Gastroenterology, 52–53, 101712.
• Fan, X., Luo, P., Mu, Y., Zhou, R., Tjahjadi, T., & Ren, Y. (2022). Leaf image based plant disease identification using transfer learning and feature fusion. Computers and Electronics in Agriculture, 196, 106892.
• Foody, G. M. (2023). Challenges in the real world use of classification accuracy metrics: From recall and precision to the Matthews correlation coefficient. PLOS ONE, 18(10), 1-27.
• Gholamalinezhad, H., & Khosravi, H. (2020). Pooling Methods in Deep Neural Networks, a Review.
• Giddings, Nahum James, & A. B. (1915). Apple Rust, West Virginia Agricultural and Forestry Experiment Station Bulletins. 154 .
• LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444.
• Liu, B., Zhang, Y., He, D., & Li, Y. (2018). Identification of Apple Leaf Diseases Based on Deep Convolutional Neural Networks. Symmetry, 10(1), 11.
• Ma, Y., Chen, S., Ermon, S., & Lobell, D. B. (2024). Transfer learning in environmental remote sensing. Remote Sensing of Environment, 301, 113924. https://doi.org/10.1016/j.rse.2023.113924
• Miao, J., & Zhu, W. (2022). Precision–recall curve (PRC) classification trees. Evolutionary Intelligence, 15(3), 1545–1569.
• Mutembesa, D., Mwebaze, E., Nsumba, S., Omongo, C., & Mutaasa, H. (2019). Mobile community sensing with smallholder farmers in a developing nation; A scaled pilot for crop health monitoring. arXiv preprint arXiv:1908.07047.
• Norelli, J.L., E. Borejsza-Wysocka, J.-P. R. and H. S. A. (2000). Transgenic ‘Royal Gala’ Apple Expressing Attacin E Has Increased Field Resistance To Erwinia Amylovora (Fire Blight). Proc. EUCARPIA Symp. on Fruit Breed. and Genetics Eds M. Geibel, M. Fischer & C. Fischer Acta Hort., 538.
• Oerke, E.-C., Fröhling, P., & Steiner, U. (2011). Thermographic assessment of scab disease on apple leaves. Precision Agriculture, 12(5), 699–715.
• Pak, M., & Kim, S. (2017). A review of deep learning in image recognition. 2017 4th International Conference on Computer Applications and Information Processing Technology (CAIPT) (pp. 1-3), Bali.
• Peil, A., Bus, V. G. M., Geider, K., Richter, K., Flachowsky, H., & Hanke, M.-V. (2009). Improvement of fire blight resistance in apple and pear. International Journal of Plant Breeding, 3(1), 1–27.
• Pradhan, P., Kumar, B., & Mohan, S. (2022). Comparison of various deep convolutional neural network models to discriminate apple leaf diseases using transfer learning. Journal of Plant Diseases and Protection, 129(6), 1461–1473.
• Sapna, S., Sandhya, S., Acharya, V., & Ravi, V. (2024). Apple foliar leaf disease detection through improved capsule neural network architecture. Multimedia Tools and Applications, 83(16), 48585–48605.
• Sengar, N., Dutta, M. K., & Travieso, C. M. (2018). Computer vision based technique for identification and quantification of powdery mildew disease in cherry leaves. Computing, 100(11), 1189–1201.
• Senthil, P., Jerin, B. S., & Jeciyazhini, J. (2024). Medicinal Plant Classification Using VGG-19. 2024 Second International Conference on Advances in Information Technology (ICAIT), 1, 1–5.
• Sharif, M., Khan, M. A., Iqbal, Z., Azam, M. F., Lali, M. I. U., & Javed, M. Y. (2018). Detection and classification of citrus diseases in agriculture based on optimized weighted segmentation and feature selection. Computers and Electronics in Agriculture, 150, 220–234.
• Singh, P., Raj, P., & Namboodiri, V. P. (2020). EDS pooling layer. Image and Vision Computing, 98, 103923.
• Sunil, C. K., Jaidhar, C. D., & Patil, N. (2023). Systematic study on deep learning-based plant disease detection or classification. Artificial Intelligence Review, 56(12), 14955–15052.
• 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–e11390.
• Tu, S., Xue, Y., Zheng, C., Qi, Y., Wan, H., & Mao, L. (2018). Detection of passion fruits and maturity classification using Red-Green-Blue Depth images. Biosystems Engineering, 175, 156–167.
• Udayananda, G. K. V. L., Shyalika, C., & Kumara, P. P. N. V. (2022). Rice plant disease diagnosing using machine learning techniques: a comprehensive review. SN Applied Sciences, 4(11), 311.
• Wang, Y., Feng, K., Sun, L., Xie, Y., & Song, X. (2024). Satellite-based soybean yield prediction in Argentina: A comparison between panel regression and deep learning methods. Computers and Electronics in Agriculture, 221, 108978.
• Yu, H., Cheng, X., Chen, C., Heidari, A. A., Liu, J., Cai, Z., & Chen, H. (2022). Apple leaf disease recognition method with improved residual network. Multimedia Tools and Applications, 81(6), 7759–7782.
• Zhai, H. (2016). Research on image recognition based on deep learning technology. 2016 4th International Conference on Advanced Materials and Information Technology Processing (AMITP 2016) (pp. 266–270), Guilin.
• Zhang, Z., Liu, H., Chen, D., Zhang, J., Li, H., Shen, M., Pu, Y., Zhang, Z., Zhao, J., & Hu, J. (2022). SMOTE-based method for balanced spectral nondestructive detection of moldy apple core. Food Control, 141, 109100.
• Zhong, Y., & Zhao, M. (2020). Research on deep learning in apple leaf disease recognition. Computers and Electronics in Agriculture, 168, 105146.
• 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.