Görüntü Tabanlı Derin Öğrenme Yöntemleri Kullanılarak Ayçiçeği Yaprak Hastalıklarının Erken Tespiti

Abstract

Ayçiçeği, ekonomik değeri yüksek ve süs amaçlı da kullanılan bir bitki türüdür. Ancak ayçiçeği yapraklarında görülen çeşitli hastalıklar üretimi aksatabilmekte ve üreticilerin bu hastalıkları geleneksel yaklaşımlarla tespit etmesi zor olmaktadır. Bu nedenle yapraklarda görülen hastalıkları otomatik olarak tespit edebilen görüntü tabanlı yapay zeka yaklaşımlarına ihtiyaç duyulmuştur. Bu çalışmada, hem görüntü tabanlı hem de yapay zeka destekli olarak ayçiçeği yapraklarında görülen hastalıkları tespit edebilen bir sistem geliştirilmiştir. Çalışma dört aşamadan oluşmaktadır. İlk aşamada herkese açık bir veri seti kullanılmış ve tarafımızca ek veriler toplanmıştır. İkinci aşamada görüntü işleme yapılmıştır. Üçüncü aşamada CNN (Evrişimli Sinir Ağı), ViT (Görüntü Dönüştürücü) ve CNN-ViT modelleri tasarlanmıştır. Son aşamada bu modellerin performansları değerlendirilmiş ve başarıları doğruluk, duyarlılık, kesinlik, F1 skoru, Cohen Kappa ve Hamming kayıp metrikleriyle belirlenmiştir. Deneysel sonuçlar, çalışmada kullanılan hibrit yaklaşımın geleneksel derin öğrenme modellerine göre daha etkili olduğunu ortaya koymuştur.

Keywords

• Sınıflandırma
• Görüntü işleme
• Ayçiçeği hastalığı
• Derin öğrenme
• Görüntü tanılama sistemleri

Early Detection of Sunflower Leaf Diseases Using Image-Based Deep Learning Methods

Abstract

Sunflower is a crop type that has high economic value and is also used for ornamental purposes. However, various diseases seen on sunflower leaves can disrupt production and it is difficult for growers to identify these diseases with traditional approaches. Therefore, the need for image-based artificial intelligence approaches that can automatically identify diseases seen on leaves has arisen. In this study, a system that can detect diseases seen on sunflower leaves, both image-based and artificial intelligence-supported, has been developed. The study consists of four stages. In the first stage, a publicly available dataset was used, and additional data was collected by us. In the second stage, image processing was performed. In the third stage, CNN (Convolutional Neural Network), ViT (Vision Transformer) and CNN-ViT models were designed. In the last stage, the performances of these models were evaluated, and their success was determined by accuracy, recall, precision, F1-score, Cohen Kappa and Hamming loss metrics. Experimental results revealed that the hybrid approach used in the study was more effective than traditional deep learning models.

Keywords

• Classification
• Image processing
• Sunflower disease
• Deep learning
• Image diagnosis systems

References

1. Abbas JKK, Ruhaima AA, Naser OA, Hayder DM (2024) F-Test and One-Way ANOVA for Medical Images Diagnosis. Al-Nisour Journal for Medical Sciences 6(2): 29-38.
2. Alijani S, Fayyad J, Najjaran H (2024) Vision Transformers in Domain Adaptation and Domain Generalization: A Study of Robustness. Neural Computing and Applications36: 17979-18007.
3. Andasuryani I, Rasinta I. (2021). Classification of Tomato (Lycoersicon Esculentum Miil) Ripeness Levels Based on HSV Color Using Digital Image Processing. IOP Conference Series: Earth and Environmental Science, 116, 012062.
4. Azad R, Kazerouni A, Heidari M, Aghdam EK, Molaei A, Jia Y, Jose A, Roy R, Merhof D (2024) Advances in Medical Image Analysis with Vision Transformers: A Comprehensive Review. Medical Image Analysis 91: 1-66.
5. Çakar H, Sengur A (2021) Machine Learning Based Emotion Classification in the COVID-19 Real World Worry Dataset. Journal of Computer Science 6(1): 24-31.
6. Centorame L, Gasperinin T, Ilari A, Gatto AD, Pedretti EF (2024) An Overview of Machine Learning Applications on Plant Phenotyping, with a Focus on Sunflower. Agronomy 14(4): 1-23.
7. David LL, Pohl MD, Alvarado JL, Bye R (2008) Sunflower (Helianthus Annuus L.) As A Pre-Columbian Domesticate in Mexico. Anthropology 105(17): 6232-6237.
8. 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.

9. Ghosh P, Mondal AK, Chatterjee S, Masud M, Meshref H, Bariagi AK (2023) Recognition of sunflower diseases using hybrid deep learning and its explainability with AI. Mathematics 11(10): 1-24.
10. Inyang EJ, Moffat IU, Clement EP (2024) Friedman Test Technique for Optimizing a Seasonal Box-Jenkins ARIMA Model Building. Journal of Probability and Statistical Science 22(1): 1-15.
11. Islam M, Adil AA, Talukder A, Ahamed KU, Uddin A, Hasan K, Sharmin S, Rahman M, Debnath SK (2023) DeepCrop: Deep Learning-Based Crop Disease Prediction with Web Application. Journal of Agriculture and Food Research 14: 1-11.
12. Kaur R, Jain A, Kumar S (2022) Optimization Classification of Sunflower Recognition Through Machine Learning. Materials Today Proceedings 51(1): 207-211.
13. Koo C, Malapi-Wight M, Kim HS, Çiftçi OS, Vaughn-Diaz VL, Ma B, Kim S, Abdel-Raziq H, Ong K, Jo YK, Gross DC, Shim WB, Han A (2013) Development of a Real-Time Microchip PCR System for Portable Plant Disease Diagnosis. Plos One 8(12): e82704.
14. Li W, Zheng T, Yang Z, Li M, Sun C, Yang X (2021) Classification and Detection of Insects from Field Images Using Deep Learning for Smart Pest Management: A Systematic Review. Ecological Informatics 66: 1-18.
15. Malik A, Vaidya G, Jagota V, Eswaran S, Sirohi A, Batra I, Rakhra M, Asenso E (2022) Design and Evaluation of a Hybrid Technique for Detecting Sunflower Leaf Disease Using Deep Learning Approach. Journal of Food Quality 2022: 1-12.
16. Moupojou E, Tagne A, Retraint F, Tadonkemwa A, Wilfried D, Tapamo H (2023) FieldPlant: A Dataset of Field Plant Images for Plant Disease Detection and Classification with Deep Learning. IEEE Access 11: 35398-35410.
17. Ozer E (2024) Brain Tumor Detection using Deep CNNs and Ensemble Algorithms over MRI Images. Journal of Computer Science 9(2): 142-150.
18. Rajora R, Banerjee D, Chauhan R, Singh M. (2024). Advanced Sunflower Leaf Disease Detection using CNN-SVM Hybrid Models. 4th Asian Conference on Innovation in Technology, pp: 1-7.
19. Rani L, Veeramanickam MRM, Pandey B. (2024). Innovative Fusion for Sunflower Leaf Disease Identification: CNN and Random Forest Strategies. IEEE AITU: Digital Generation, pp: 65-70.
20. Sara U, Rajbongshi A, Shakil R, Akter B, Sazzad S, Uddin MS (2022) An Extensive Sunflower Dataset Representation for Successful Identification and Classification of Sunflower Diseases. Data in Brief 42: 1-8.
21. Sarhan M, Layeghy S, Moustafa N, Gallagher M, Portmann M (2024) Feature Extraction for Machine Learning-Based Intrusion Detection in IoT Networks. Digital Communications and Networks 10(1): 205-216.
22. Sasaki Y, Okamoto T, Imou K, Torii T (1998) Automatic Diagnosis of Plant Disease. IFAC Proceedings Volumes, 31(5): 145-150.
23. Sathi TA, Hasan A, Alam MJ. (2023). SunNet: A Deep Learning Approach to Detect Sunflower Disease. 7th International Conference on Trends in Electronics and Informatics, pp: 1210-1216.
24. Şener A, Ergen B (2024) Advanced CNN Approach for Segmentation of Diseased Areas in Plant Images. Journal of Crop Health 76: 1569-1583.
25. Singh V (2019) Sunflower Leaf Diseases Detection using Image Segmentation Based on Particle Swarm Optimization. Artificial Intelligence in Agriculture 3: 62-68.
26. Sirohi A, Malik A. (2021). A Hybrid Model for the Classification of Sunflower Diseases using Deep Learning. 2nd International Conference on Intelligent Engineering and Management, pp. 58-62.
27. Thirunavukarasu R, Kotei E (2024) A Comprehensive Review on Transformer Network for Natural and Medical Image Analysis. Computer Science Review 53: 1-19.
28. Toğaçar M (2022) Using DarkNet Models and Metaheuristic Optimization Methods Together to Detect Weeds Growing Along with Seedlings. Ecological Informatics 68:101519.
29. Vorobyov SP, Vorobyova VV. (2021) The Ecological and Economic Effectiveness of Sunflower Oilseed Production in Russia. IOP Conference Series: Earth and Environmental Science, 670, 012057.
30. Wang L, Wang J, Liu Z, Zhu J, Qin F (2022) Evaluation of a Deep-Learning Model for Multispectral Remote Sensing of Land Use and Crop Classification. The Crop Journal 15(5): 1435-1451.
31. Wu L, Zeng W, Lei G, Ma T, Wu J, Huang J, Gaiser T, Srivastava AK (2022) Simulating Root Length Density Dynamics of Sunflower in Saline Solis Based on Machine Learning. Computers and Electronics in Agriculture 197: 1-11.
32. Yuan J, Wan X (2022) The Associative Effects of Sunflower Straw, Sunflower Plate, Sunflower Seed Shells Associated with Concentrate and Alfalfa Evaluated by Using An In Vitro Gas Production Technique. Czech Journal of Animal Science 67(7): 253-265.
33. Zhou J, Li J, Wang C, Wu H, Zhao C, Teng G (2021) Crop Disease Identification and Interpretation Based on Multimodal Deep Learning. Computer and Electronics in Agriculture 189: 1-9.