Guava Fruit Disease Classification Using Deep Learning and Machine Learning Models

Year 2025, Volume: 56 Issue: 3, 217 - 226, 26.09.2025

Oya Kılcı , Murat Koklu

https://doi.org/10.17097/agricultureatauni.1665941

Abstract

This study presents a classification approach for guava fruit diseases using both deep learning and machine learning models. InceptionV3 was employed to extract image features, which were subsequently classified using models such as artificial neural networks support vector machines, k nearest neighbors, random forest, and decision tree. The performance of the models was evaluated in terms of accuracy, F1 score, precision, and recall. Experimental results demonstrate that SVM and ANN achieved the highest performance, with SVM reaching 0.9974 across all metrics and ANN achieving 0.9958. The kNN model also performed well with an accuracy of 0.9924, while random forest and decision tree obtained lower accuracies of 0.9612 and 0.9209, respectively. Confusion matrix analysis further confirmed the superiority of SVM and ANN, with minimal misclassifications across anthracnose, fruit fly, and healthy guava categories. These findings highlight the effectiveness of deep learning-based feature extraction combined with SVM and ANN classifiers for reliable and accurate detection of guava fruit diseases.

Keywords

Agricultural technology , Deep learning , Guava disease classification , Machine learning

Derin Öğrenme ve Makine Öğrenmesi Modelleri Kullanarak Guava Meyvesi Hastalıklarının Sınıflandırılması

Abstract

Bu çalışma, guava meyvesi hastalıklarının sınıflandırılmasına yönelik olarak derin öğrenme ve makine öğrenmesi modellerini bir arada kullanan bir yaklaşım sunmaktadır. Görüntü özelliklerinin çıkarılması için InceptionV3 kullanılmış, elde edilen bu özellikler yapay sinir ağları, destek vektör makineleri, en yakın k-komşu, rastgele orman ve karar ağacı gibi modeller aracılığıyla sınıflandırılmıştır. Modellerin performansı doğruluk, F1 skoru, kesinlik ve duyarlılık ölçütleri açısından değerlendirilmiştir. Deneysel sonuçlar, en yüksek başarımın SVM ve ANN modelleri tarafından elde edildiğini göstermektedir. Buna göre SVM tüm metriklerde 0,9974, ANN ise 0,9958 değerine ulaşmıştır. kNN modeli de 0,9924 doğruluk ile yüksek bir performans sergilerken, rastgele orman ve karar ağacı modelleri sırasıyla 0,9612 ve 0,9209 doğruluk oranlarına ulaşmıştır. Karışıklık matrisi analizi de SVM ve ANN’in üstünlüğünü doğrulamış, antraknoz, meyve sineği ve sağlıklı guava kategorilerinde minimal yanlış sınıflandırmalar gözlemlenmiştir. Bu bulgular, derin öğrenme tabanlı özellik çıkarımının SVM ve ANN sınıflandırıcıları ile birleştirilmesinin, guava meyvesi hastalıklarının güvenilir ve yüksek doğrulukla tespiti için etkin bir yöntem olduğunu ortaya koymaktadır.

Keywords

Tarım teknolojisi , Derin öğrenme , Guava hastalığı sınıflandırması , Makine öğrenmesi

References

• Ahmed, K. R., Salam, T., Nandi, S., Hasan, N., Al Rashid, O. F., Miraz, S., Reza, M. S., & Rahman, F. (2024). An Identification of Guava Fruit Disease Using ML. In Proceedings of the 2024 3rd International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE), pp. 1-6. IEEE.
• Al Haque, A. F., Hafiz, R., Hakim, M. A., & Islam, G. R. (2019). A computer vision system for guava disease detection and recommend curative solution using deep learning approach. In Proceedings of the 2019 22nd International Conference on Computer and Information Technology (ICCIT), pp. 1-6. IEEE.
• Almutiry, O., Ayaz, M., Sadad, T., Lali, I. U., Mahmood, A., Hassan, N. U., & Dhahri, H. (2021). A novel framework for multi-classification of guava disease. Computers, Materials & Continua, 69(2), 1915-1926. https://doi.org/10.32604/cmc.2021.017702
• Asim, M., Ullah, S., Razzaq, A., & Qadri, S. (2023). Varietal discrimination of guava (Psidium guajava) leaves using multi features analysis. International Journal of Food Properties, 26(1), 179-196. https://doi.org/10.1080/10 942912.2022.2158863
• Browne, M. W. (2000). Cross-validation methods. Journal of mathematical psychology, 44(1), 108-132. https://doi.org/10.1006/jmps.1999.1279
• Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1251-1258. IEEE.
• Chouhan, D., Kumari, M., Kumar, C., & Kukreja, V. (2024). From detection to action: Managing guava diseases using CNN and random forest models. In Proceedings of the 2024 International Conference on Automation and Computation (AUTOCOM), pp. 67-70. IEEE.
• Cinar, I., & Koklu, M. (2021). Determination of effective and specific physical features of rice varieties by computer vision in exterior quality inspection. Selcuk Journal of Agriculture and Food Sciences, 35(3), 229-243. https://doi.org/10.15316/SJAFS.2021.252
• Cinar, I., Taspinar, Y. S., Saritas, M. M., & Koklu, M. (2020). Feature extraction and recognition on traffic sign images. Selçuk-Teknik Dergisi, 19(4), 282-292.
• Doutoum, A. E., Recep Tugrul, Bulent. (2023). Classification of Guava Leaf Disease using Deep Learning. World Scientific and Engineering Academy and Society (WSEAS), 20(38). https://doi.org/10.37394/23209.2023.20.38
• Faisal, M., Leu, J. S., Avian, C., Prakosa, S. W., & Köppen, M. (2024). DFNet: Dense fusion convolution neural network for plant leaf disease classification. Agronomy Journal, 116(3), 826-838. https://doi.org/10.1002/agj2.21341
• Farisqi, B. A., & Prahara, A. (2022). Guava fruit detection and classification using mask region-based convolutional neural network. Buletin Ilmiah Sarjana Teknik Elektro, 4(3), 186-193. https://doi.org/10.12928/biste.v4i3.7412
• Foo, C. F., Tay, K. G., Al-Qershi, O., Huong, A., Chew, C. C., & Alzaeemi, S. A. (2024). Android-Based App Guava Leaf Diseases Identification using Convolution Neural Network. Journal of Advanced Research in Applied Sciences and Engineering Technology, 73-88. https://doi.org/0.37934/araset.57.1.7388
• Gencturk, B., Arsoy, S., Taspinar, Y. S., Cinar, I., Kursun, R., Yasin, E. T., & Koklu, M. (2024). Detection of hazelnut varieties and development of mobile application with CNN data fusion feature reduction-based models. European Food Research and Technology, 250(1), 97-110. https://doi.org/10.1007/s00217-023-04369-9
• Hashan, A. M., Rahman, S. M. T., Avinash, K., Ul Islam, R. M. R., & Dey, S. (2024). Guava fruit disease identification based on improved convolutional neural network. International Journal of Electrical & Computer Engineering (2088-8708), 14(2). https://doi.org/10.115 91/ijece.v14i2.pp1544-1551
• Irhebhude, M. E., Kolawole, A. O., & Chinyio, C. (2024). Classification of plants by their fruits and leaves using convolutional neural networks. Science in Information Technology Letters, 5(1), 1-15. https://doi.org/10.31 763/sitech.v5i1.1364
• Isik, H., Tasdemir, S., Taspinar, Y. S., Kursun, R., Cinar, I., Yasar, A., Yasin, E. T., & Koklu, M. (2024). Maize seeds forecasting with hybrid directional and bi‐directional long short‐term memory models. Food Science & Nutrition, 12(2), 786-803. https://doi.org/10.1002/fsn 3.3783
• Isik, M., Ozulku, B., Kursun, R., Taspinar, Y. S., Cinar, I., Yasin, E. T., & Koklu, M. (2024). Automated classification of hand-woven and machine-woven carpets based on morphological features using machine learning algorithms. The Journal of The Textile Institute, 115(12), 2650-2659. https://doi.org/10.1080/00405000.2024.2 309694
• Jain, R., Singla, P., Sharma, R., Kukreja, V., & Singh, R. (2023). Detection of guava fruit disease through a unified deep learning approach for multi-classification. In Proceedings of the 2023 IEEE International Conference on Contemporary Computing and Communications (InC4), pp. 1-5. IEEE
• Kaur, A., Kukreja, V., Upadhyay, D., Aeri, M., & Sharma, R. (2024). Multi-class guava disease classification using an efficient and fine-tuned DenseNet model. In Proceedings of the 2024 IEEE 9th International Conference for Convergence in Technology (I2CT), pp. 1-5. IEEE.
• Kilci, O., Eryesil, Y., & Koklu, M. (2025). Classification of Biscuit Quality with Deep Learning Algorithms. Journal of Food Science, 90(7), e70379. https://doi.org/10.1111/1750-3841.70379
• Kilci, O., & Koklu, M. (2024). Classification of guava diseases using features extracted from SqueezeNet with AdaBoost and gradient boosting. In Proceedings of the 4th International Conference on Frontiers in Academic Research, pp. 578-586.
• Kilci, O., & Koklu, M. (2025a). Automated Classification of Biscuit Quality Using YOLOv8 Models in Food Industry. Food Analytical Methods, 1-15. https://doi.org/10.100 7/s12161-025-02755-5
• Kilci, O., & Koklu, M. (2025b). Machine learning-based detection of solar panel surface defects using deep features from InceptionV3. 4th International Conference on Trends in Advanced Research Konya, Türkiye
• Kilci, O., Yildiz, M. B., & Tukel, H. Y. (2024). Deep learning and machine learning approaches for coffee leaf disease diagnosis. In H. Kahramanlı Örnek (Ed.), Agri-Intelligence (pp. 273–297). Çizgi Kitabevi. ISBN 978-625-396-413-9
• Kızgın, M. S., Çambay, Z., Sepet, H., Özçelik, S. T. A., vd. (2023). Onobrychis bitkisine ait meyve tiplerinin makine öğrenmesi yaklaşımıyla sınıflandırılması. Fırat Üniversitesi Fen Bilimleri Dergisi, 35(2), 87-96.
• Koklu, M., & Ozkan, I. A. (2020). Multiclass classification of dry beans using computer vision and machine learning techniques. Computers and Electronics in Agriculture, 174, 105507. https://doi.org/10.1016/j.compag.2020.1 05507
• Kursun, R., Cinar, I., Taspinar, Y. S., & Koklu, M. (2022). Flower recognition system with optimized features for deep features. In Proceedings of the 2022 11th Mediterranean Conference on Embedded Computing (MECO), pp. 1-4. IEEE
• Larsson, G., Maire, M., & Shakhnarovich, G. (2016). Fractalnet: Ultra-deep neural networks without residuals. arXiv preprint arXiv:1605.07648. https://doi.org/10.48550/arxiv.1605.07648
• Low, E. S., Ong, P., Sim, J. Q., Sia, C. K., & Ismon, M. (2024). Integrating deep learning with non‐destructive thermal imaging for precision guava ripeness determination. Journal of the Science of Food and Agriculture. https://doi.org/10.1002/jsfa.13614
• Mienye, I. D., & Jere, N. (2024). A survey of decision trees: Concepts, algorithms, and applications. IEEE access. https://doi.org/10.1109/ACCESS.2024.3416838
• Mir, T. A., Banerjee, D., Kumar, M., Rawat, R., & Chanti, Y. (2024). Hybridized model for improved papaya leaf disease classification: CNN and random forest integration. In Proceedings of the 2024 5th International Conference for Emerging Technology (INCET), pp. 1-6. IEEE
• Mirjat, R. M., Mahar, S. A., Siddiqui, M. I. M., Mahar, J. A. M., & Magsi, A. M. (2024). A Framework for Guava Wilt Disease Segmentation Using K-Means Clustering and Neural Network Techniques. VAWKUM Transactions on Computer Sciences, 12(1), 76-93. https://doi.org/10.21 015/vtcs.v12i1.1802
• Mostafa, A. M., Kumar, S. A., Meraj, T., Rauf, H. T., Alnuaim, A. A., & Alkhayyal, M. A. (2021). Guava disease detection using deep convolutional neural networks: A case study of guava plants. Applied Sciences, 12(1), 239. https://doi.org/10.3390/app12010239
• Paul, A., Mukherjee, D. P., Das, P., Gangopadhyay, A., Chintha, A. R., & Kundu, S. (2018). Improved random forest for classification. IEEE Transactions on Image Processing, 27(8), 4012-4024. https://doi.org/10.1109/TIP.2018.2 834830
• Perumal, P., Sellamuthu, K., Vanitha, K., & Manavalasundaram, V. (2021). Guava leaf disease classification using support vector machine. Turkish Journal of Computer and Mathematics Education, 12(7), 1177-1183. https://www.proquest.com/scholarly-journals/guava-leaf-disease-classification-using-support/docview/2623612894/se-2?accountid=16935
• Putra, I. C., & Prabowo, W. A. E. (2024). Implementation of convolutional neural network based on InceptionV3 to classify guava quality. In Proceedings of the 2024 International Seminar on Application for Technology of Information and Communication (iSemantic), pp. 112-117. IEEE
• Rana, S., Aeri, M., Kukreja, V., & Sharma, R. (2024). Integrating EfficientNet and fine-tuned DenseNet models for advanced detection and classification of guava diseases. In Proceedings of the 2024 International Conference on Emerging Technologies in Computer Science for Interdisciplinary Applications (ICETCS), pp. 1-5. IEEE
• Sabanci, K., Koklu, M., & Unlersen, M. F. (2015). Classification of Siirt and long type pistachios (Pistacia vera L.) by artificial neural networks. International Journal of Intelligent Systems and Applications in Engineering, 3(2), 86-89. https://doi.org/10.18201/ijisae.74573
• Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. (2017). Inception-v4, Inception-ResNet and the impact of residual connections on learning. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 31, No. 1, pp. 4278–4284). AAAI Press. https://doi.org/10.1609/aa ai.v31i1.11231
• Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the Inception architecture for computer vision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818-2826. IEEE
• Taspinar, Y. S., Cinar, I., Kursun, R., & Koklu, M. (2024). Monkeypox skin lesion detection with deep learning models and development of its mobile application. International Journal of Research in Engineering and Science, 12(1), 273-285.
• Taspinar, Y. S., Saritas, M. M., Cinar, I., & Koklu, M. (2020). Gender determination using voice data. International Journal of Applied Mathematics Electronics and Computers, 8(4), 232-235. https://doi.org/10.18100/ij amec.809476
• Toptas, B., & Guven, S. A. (2024). Guava fruit classification system design with convolutional neural networks. Gumuşhane University Journal of Science and Technology, 14(4), 1247-1258. https://doi.org/10.1 7714/gumusfenbil.1498303 Tutuncu, K., Cinar, I., Kursun, R., & Koklu, M. (2022). Edible and poisonous mushrooms classification by machine learning algorithms. 2022 11th Mediterranean Conference on Embedded Computing (MECO),
• Yasar, A., & Golcuk, A. (2025). Deep learning and evolutionary intelligence with fusion-based feature extraction for classification of wheat varieties. European Food Research and Technology, 1-14. https://doi.org/10.1 007/s00217-025-04720-2