Domates Yapraklarında Hastalık Tespiti İçin Transfer Öğrenme Metotlarının Kullanılması

Year 2023, Volume: 5 Issue: 2, 215 - 222, 27.10.2023

Serhat Kılıçarslan Ishak Pacal

https://doi.org/10.46387/bjesr.1273729

Cited By: 1

Abstract

Günümüzde, tarımsal faaliyetlerin verimli hale getirilmesi için her gün birçok araştırma yapılmaktadır. Dünya genelinde kişi başı domates tüketimi, yılda yaklaşık olarak 20 kg ile ilk sıralarda yer almaktadır. Bu nedenle domates üretiminde oluşabilecek hastalıkların tespiti üreticiler için büyük önem arz etmektedir. Hastalıkların çoğu domates yaprağı temelli olduğu için, domates yaprağının sağlıklı olması, elde edilecek ürünlerinde verimliliğinin artması ve sonuç olarak yüksek bir hasat getirir. Bu yüzden domates yaprağında oluşabilecek hastalıkların erken ve hızlı şekilde tespit edilmesi, domates üretiminde büyük bir önem arz etmektedir. Bu çalışmada, domates yaprağında meydana gelen hastalıkları tespit edebilmek için DenseNet, ResNet50 ve MobileNet mimarileri kullanılmıştır. Deneysel sonuçların karşılaştırılması için hata, doğruluk, kesinlik, f1-skor ve duyarlılık metrikleri dikkate alınarak değerlendirme yapılmıştır. Deneysel sonuçlarda en iyi performans DenseNet modeli ile sağlanmış ve sırasıyla 0.0269 hata, 0.9900 doğruluk, 0.9880 kesinlik, 0.9892 f1-skor ve 0.9906 duyarlılık sonuçları elde edilmiştir. Deneysel sonuçlara göre derin öğrenme modelleri domates yaprağı hastalıklarının sınıflandırılmasında yüksek bir başarım ve güvenilirlik sunduğu görülmüştür.

Keywords

Domates yaprağı hastalığı tespiti, Bitki hastalık tespiti, Yaprak Sınıflandırma, Transfer öğrenme, ResNet, DenseNet, MobileNet

References

• S. Zhao, Y. Peng, J. Liu, ve S. Wu “Tomato leaf disease diagnosis based on improved convolution neural network by attention module”, Agriculture, vol. 11, no 7, pp. 651, 2021.
• S. Mansoor vd., “Evidence for the association of a bipartite geminivirus with tomato leaf curl disease in Pakistan”, Plant Dis., vol. 81, no. 8, pp. 958-958, 1997.
• A. Raza vd., “First report of tomato chlorosis virus infecting tomato in Pakistan”, Plant Dis, vol. 104, no. 2036, pp. 10-1094, 2020.
• S. Adhikari, D. Unit, B. Shrestha, ve B. Baiju, “Tomato Plant Diseases Detection System”, 1st KEC Conference Proceedings, pp. 81-86, 2018.
• A. Fuentes, S. Yoon, S.C. Kim, ve D.S. Park “A robust deep-learning-based detector for real-time tomato plant diseases and pests recognition”, Sensors, vol. 17, no. 9, pp. 2022, 2017.
• B.A. Ashqar ve S.S. Abu-Naser “Image-based tomato leaves diseases detection using deep learning”, 2018.
• S. Zhao, Y. Peng, J. Liu, ve S. Wu “Tomato leaf disease diagnosis based on improved convolution neural network by attention module”, Agriculture, vol. 11, no. 7, p. 651, 2021.
• R. Karthik, M. Hariharan, S. Anand, P. Mathikshara, A. Johnson, ve R. Menaka “Attention embedded residual CNN for disease detection in tomato leaves”, Appl. Soft Comput., vol. 86, p. 105933, 2020.
• M. Agarwal, A. Singh, S. Arjaria, A. Sinha, ve S. Gupta “ToLeD: Tomato leaf disease detection using convolution neural network”, Procedia Comput. Sci., vol. 167, pp. 293-301, 2020.
• H. Durmuş, E.O. Güneş, ve M. Kırcı “Disease detection on the leaves of the tomato plants by using deep learning”, 6th International conference on agro-geoinformatics, IEEE, pp. 1-5, 2017.
• A. Elhassouny ve F. Smarandache “Smart mobile application to recognize tomato leaf diseases using Convolutional Neural Networks”, International Conference of Computer Science and Renewable Energies (ICCSRE), IEEE, pp. 1-4, 2019.
• L.R. Burra, J. Bonam, P. Tumuluru, ve B. Narendra Kumar Rao “Fine-tuning for Transfer Learning of ResNet152 for Disease Identification in Tomato Leaves”, In Intelligent Computing and Applications, Springer Nature, pp. 295-302, 2022.
• E. Cengil ve A. Çınar “Hybrid convolutional neural network based classification of bacterial, viral, and fungal diseases on tomato leaf images”, Concurr. Comput. Pract. Exp., vol. 34, no. 4, p. e6617, 2022.
• S. Widiyanto, D.T. Wardani, ve S.W. Pranata “Image-Based tomato maturity classification and detection using Faster R-CNN method”, 5th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), IEEE, pp. 130-134, 2021.
• X. Zhou, P. Wang, G. Dai, J. Yan, ve Z. Yang “Tomato Fruit Maturity Detection Method Based on YOLOV4 and Statistical Color Model”, 11th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER), IEEE, pp. 904-908, 2021.
• C. S. Hlaing ve S. M. M. Zaw “Tomato plant diseases classification using statistical texture feature and color feature”, IEEE/ACIS 17th International Conference on Computer and Information Science (ICIS), IEEE, pp. 439-444, 2018.
• J. Lu, G. Shao, Y. Gao, K. Zhang, Q. Wei, ve J. Cheng “Effects of water deficit combined with soil texture, soil bulk density and tomato variety on tomato fruit quality: A meta-analysis”, Agric. Water Manag., vol. 243, pp. 106427, 2021.
• S. Kaur, S. Pandey, ve S. Goel “Plants disease identification and classification through leaf images: A survey”, Arch. Comput. Methods Eng., vol. 26, pp. 507-530, 2019.
• P. Tm, A. Pranathi, K. SaiAshritha, N.B. Chittaragi, ve S.G. Koolagudi “Tomato leaf disease detection using convolutional neural networks”, Eleventh international conference on contemporary computing (IC3), IEEE, pp. 1-5, 2018.
• T.T. Mim, M.H. Sheikh, R.A. Shampa, M.S. Reza, ve M.S. Islam “Leaves diseases detection of tomato using image processing”, 8th international conference system modeling and advancement in research trends (SMART), IEEE, pp. 244-249, 2019.
• S. Kushwaha ve S. Zade “Identification of Tomato Leaf Disease Prediction Using CNN”, Int. J., vol. 7, no. 8, pp. 36-41, 2022.
• A.K. Alkaff ve B. Prasetiyo “Hyperparameter Optimization on CNN Using Hyperband on Tomato Leaf Disease Classification”, IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom), IEEE, pp. 479-483, 2022.
• H.I. Peyal, S.M. Shahriar, A. Sultana, I. Jahan, ve M. H. Mondol “Detection of tomato leaf diseases using transfer learning architectures: A comparative analysis”, International Conference on Automation, Control and Mechatronics for Industry 4.0 (ACMI), IEEE, pp. 1-6, 2021.
• D. Singh, N. Jain, P. Jain, P. Kayal, S. Kumawat, ve N. Batra “PlantDoc: a dataset for visual plant disease detection”, Proceedings of the 7th ACM IKDD CoDS and 25th COMAD, pp. 249-253, 2020.
• S.P. Mohanty, D. P. Hughes, ve M. Salathé “Using deep learning for image-based plant disease detection”, Front. Plant Sci., vol. 7, pp. 1419, 2016.
• I. Pacal, D. Karaboga, A. Basturk, B. Akay, ve U. Nalbantoglu “A comprehensive review of deep learning in colon cancer”, Comput. Biol. Med., vol. 126, p. 104003, 2020.
• A. Karaman vd. “Hyper-parameter optimization of deep learning architectures using artificial bee colony (ABC) algorithm for high performance real-time automatic colorectal cancer (CRC) polyp detection”, Appl. Intell., pp. 1-18, 2022.
• M.A. Bülbül, E. Harirchian, M.F. Işık, S.E. Aghakouchaki Hosseini, ve E. Işık “A Hybrid ANN-GA Model for an Automated Rapid Vulnerability Assessment of Existing RC Buildings”, Appl. Sci., vol. 12, no. 10, 2022,
• M.A. Bülbül, C. Öztürk, ve M.F. Işık “Optimization of Climatic Conditions Affecting Determination of the Amount of Water Needed by Plants in Relation to Their Life Cycle with Particle Swarm Optimization, and Determining the Optimum Irrigation Schedule”, Comput. J., vol. 65, no. 10, 2022.
• M.A. Bülbül “Kuru Fasulye Tohumlarının Çok Sınıflı Sınıflandırılması İçin Hibrit Bir Yaklaşım”, J. Inst. Sci. Technol., vol. 13, no. 1, 2023.
• K. Adem “Impact of activation functions and number of layers on detection of exudates using circular Hough transform and convolutional neural networks”, Expert Syst. Appl., vol. 203, p. 117583, 2022.
• K. Adem ve S. Kiliçarslan, “COVID-19 Diagnosis Prediction in Emergency Care Patients using Convolutional Neural Network”, Afyon Kocatepe Üniversitesi Fen Ve Mühendis. Bilim. Derg., vol. 21, no. 2, 2021.
• S. Kılıçarsalan, A. Kemal, ve M. Çelik “An overview of the activation functions used in deep learning algorithms”, J. New Results Sci., vol. 10, no. 3, pp. 75-88, 2021.
• M. Hekim, O. Cömert, ve K. Adem “A hybrid model based on the convolutional neural network model and artificial bee colony or particle swarm optimization-based iterative thresholding for the detection of bruised apples”, Turk. J. Electr. Eng. Comput. Sci., vol. 28, no. 1, pp. 61-79, 2020.
• E. Dönmez “Enhancing classification capacity of CNN models with deep feature selection and fusion: A case study on maize seed classification”, Data Knowl. Eng., vol. 141, p. 102075, 2022.
• S. Kiliçarslan, C. Közkurt, S. Baş, ve A. Elen “Detection and classification of pneumonia using novel Superior Exponential (SupEx) activation function in convolutional neural networks”, Expert Syst. Appl., vol. 217, p. 119503, 2023.
• K. Adem, S. Kiliçarslan, ve O. Cömert “Classification and diagnosis of cervical cancer with stacked autoencoder and softmax classification”, Expert Syst. Appl., vol. 115, pp. 557-564, 2019.
• S. Kiliçarslan ve M. Celik “RSigELU: A nonlinear activation function for deep neural networks”, Expert Syst. Appl., vol. 174, p. 114805, 2021.
• I. Pacal ve D. Karaboga “A robust real-time deep learning based automatic polyp detection system.”, Comput. Biol. Med., vol. 134, pp. 104519-104519, 2021.