Guava fruit classification system design with convolutional neural networks

Year 2024, Volume: 14 Issue: 4, 1247 - 1258, 15.12.2024

Buket Toptaş , Sara Altun Güven

https://doi.org/10.17714/gumusfenbil.1498303

Abstract

For the rapid and precise advancement of agriculture, artificial intelligence applications are of significant importance. Processes such as disease detection in the agricultural field, identification of soil types, and classification of plants and fruits are currently performed manually. Artificial intelligence enables the automation of these processes, leading to cost reduction and the minimization of human errors. In this study, a system for classifying the species of Guava fruit has been proposed. The proposed system is designed using four pre-trained convolutional neural networks. The convolutional neural networks used are GoogLeNet, Vgg19, ResNet50, and DenseNet201 architectures. The Guava fruit dataset was classified by both k-fold-stratified and an 80:20 split. All experimental studies were evaluated using six different performance metrics. The best result was achieved with the DenseNet201 architecture in the proposed method. The performance results for the DenseNet201 architecture in terms of accuracy, sensitivity, specificity, F1-score, MCC, and kappa are as follows: accuracy - 0.9658, sensitivity - 0.9677, specificity - 0.9954, F1-score - 0.9681, MCC - 0.9640, and Kappa - 0.8268.

Keywords

Convolutional neural network, Classification, Guava classification

Evrişimsel sinir ağları ile guava meyvesi sınıflandırma sistemi tasarımı

Abstract

Tarımın hızlı ve hassas bir şekilde ilerlemesi için yapay zeka uygulamaları büyük önem taşımaktadır. Tarım alanında hastalık tespiti, toprak türlerinin belirlenmesi ve bitki ile meyvelerin sınıflandırılması gibi süreçler şu anda manuel olarak gerçekleştirilmektedir. Yapay zeka, bu süreçlerin otomasyonunu sağlayarak maliyetleri düşürmekte ve insan hatalarını en aza indirmektedir. Bu çalışmada, Guava meyvesinin türlerini sınıflandıran bir sistem önerilmiştir. Önerilen sistem, dört ön eğitimli evrişimli sinir ağı kullanılarak tasarlanmıştır. Kullanılan evrişimli sinir ağları GoogLeNet, Vgg19, ResNet50 ve DenseNet201 mimarileridir. Guava meyvesi veri seti, hem k-katmanlı stratifiye hem de 80:20 bölme ile sınıflandırılmıştır. Tüm deneysel çalışmalar altı farklı performans metriği kullanılarak değerlendirilmiştir. Önerilen yöntemle en iyi sonuç DenseNet201 mimarisi ile elde edilmiştir. DenseNet201 mimarisinin performans sonuçları şu şekildedir: doğruluk - 0.9658, hassasiyet - 0.9677, özgüllük - 0.9954, F1-puanı - 0.9681, MCC - 0.9640 ve Kappa - 0.8268.

Keywords

Evrişimsel sinir ağlar, Sınıflandırma, Guava sınıflandırma

References

• Adige, S., Kurban, R., Durmuş, A., & Karaköse, E. (2023). Classification of apple images using support vector machines and deep residual networks. Neural Computing and Applications, 35(16), 12073-12087.
• Alsirhani, A., Siddiqi, M. H., Mostafa, A. M., Ezz, M., & Mahmoud, A. A. (2023). A novel classification model of date fruit dataset using deep transfer learning. Electronics, 12(3), 665.
• Assari, Z., Mahloojifar, A., & Ahmadinejad, N. (2022). A bimodal BI-RADS-guided GoogLeNet-based CAD system for solid breast masses discrimination using transfer learning. Computers in Biology and Medicine, 142, 105160.
• Chen, J., Chen, J., Zhang, D., Sun, Y., & Nanehkaran, Y. A. (2020). Using deep transfer learning for image-based plant disease identification. Computers and Electronics in Agriculture, 173, 105393.
• Chen, S. H., Wu, Y. L., Pan, C. Y., Lian, L. Y., & Su, Q. C. (2023). Breast ultrasound image classification and physiological assessment based on GoogLeNet. Journal of Radiation Research and Applied Sciences, 16(3), 100628.
• Dogan, M., Taspinar, Y. S., Cinar, I., Kursun, R., Ozkan, I. A., & Koklu, M. (2023). Dry bean cultivars classification using deep cnn features and salp swarm algorithm based extreme learning machine. Computers and Electronics in Agriculture, 204, 107575.
• 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, 770-778.
• 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, 4700-4708.
• Huang, Z., Wang, R., Cao, Y., Zheng, S., Teng, Y., Wang, F., ... & Du, J. (2022). Deep learning-based soybean seed classification. Computers and Electronics in Agriculture, 202, 107393.
• Islam, M. M., Barua, P., Rahman, M., Ahammed, T., Akter, L., & Uddin, J. (2023). Transfer learning architectures with fine-tuning for brain tumor classification using magnetic resonance imaging. Healthcare Analytics, 100270.
• Jamieson, S., Wallace, C. E., Das, N., Bhattacharyya, P., & Bishayee, A. (2022). Guava (Psidium guajava L.): a glorious plant with cancer preventive and therapeutic potential. Critical reviews in food science and nutrition, 63(2), 192-223.)
• Kapila, G., Vandana, B., Khaitan, A., Francis Avinash, A., and Ajay Kumar, C. H., (2021). Apple fruit classification and damage detection using pre-trained deep neural network as feature extractor. In Innovations in Electronics and Communication Engineering: Proceedings of the 9th ICIECE, 235-243. Springer Singapore.
• Khan, M. A., Alqahtani, A., Khan, A., Alsubai, S., Binbusayyis, A., Ch, M. M. I., ... & Cha, J. (2022). Cucumber leaf diseases recognition using multi-level deep entropy-ELM feature selection. Applied Sciences, 12(2), 593.
• Koklu, M., Unlersen, M. F., Ozkan, I. A., Aslan, M. F., & Sabanci, K. (2022). A CNN-SVM study based on selected deep features for grapevine leaves classification. Measurement, 188, 110425.
• Luque, A., Carrasco, A., Martín, A., & de Las Heras, A. (2019). The impact of class imbalance in classification performance metrics based on the binary confusion matrix. Pattern Recognition, 91, 216-231.
• Loddo, A., Loddo, M., & Di Ruberto, C. (2021). A novel deep learning-based approach for seed image classification and retrieval. Computers and Electronics in Agriculture, 187, 106269.
• Maitlo, A. K., Aziz, A., Raza, H., & Abbas, N. (2023). A novel dataset of guava fruit for grading and classification. Data in Brief, 49.
• Raiaan, M. A. K., Sakib, S., Fahad, N. M., Al Mamun, A., Rahman, M. A., Shatabda, S., & Mukta, M. S. H. (2024). A systematic review of hyperparameter optimization techniques in convolutional neural networks. Decision Analytics Journal, 100470.
• Pinto, C., Furukawa, J., Fukai, H., & Tamura, S. (2017). Classification of green coffee bean images based on defect types using convolutional neural network (CNN). In 2017 International Conference on Advanced Informatics, Concepts, Theory, and Applications (ICAICTA) 1-5.
• Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
• Singh, D., Taspinar, Y. S., Kursun, R., Cinar, I., Koklu, M., Ozkan, I. A., & Lee, H. N. (2022). Classification and analysis of pistachio species with pre-trained deep learning models. Electronics, 11(7), 981.
• Şahin, N., Alpaslan, N., İlçin, M., & Hanbay, D. (2023). Evrişimsel sinir ağı mimarileri ve öğrenim aktarma ile bitki zararlısı çekirge türlerinin sınıflandırılması. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 35(1), 321-331.
• Toğaçar, M., Ergen, B., & Cömert, Z. (2020). Classification of white blood cells using deep features obtained from convolutional neural network models based on the combination of feature selection methods. Applied Soft Computing, 97, 106810.
• Türkoğlu, M., Hanbay, K., Sivrikaya, I. S., & Hanbay, D. (2020). Classification of apricot diseases by using deep convolution neural network. BEU Journal of Science, 9, 334-345.