Derin Öğrenme Kullanarak Türüne Bağlı Domates Sınıflandırma Sistemi

Abstract

Domates, dünya genelinde yetiştirilen ve ülkelerin yemek kültürlerinde önemli bir yer tutan sebzedir. Bu sebzenin yetiştirildiği mevsim dışında ve farklı lezzetler elde etme gereksinimlerini karşılamak için toplandıktan sonra ayrıştırılması gerekir. Bu çalışma, yapay zeka ve görüntü işleme tekniklerini kullanarak salçalık ve soslarda tercih edilen Rio cinsi domateslerin Fujimaru cinsi domateslerden otomatik olarak ayrılması üzerine odaklanmaktadır. İki farklı domates türünü ayırmak için konvolüsyon sinir ağı (CNN), R-CNN ve Fast-CNN modelleri kullanılmış ve performansları karşılaştırılmıştır. Deneysel sonuçlara göre, Rio cinsi domateslerin sınıflandırılmasında, CNN modelin %94.1 doğruluk, %93.5 hassasiyet, %94.7 geri çağırma ve %.94.1 F1 skoru; Fujimaru cinsi domateslerin sınıflandırılmasında, %92.4 doğruluk, %91.8 hassasiyet, %93 geri çağırma ve %.92.4 F1 skoru ile daha başarılı sonuçlar elde ettiği görülmüştür. Projede kullanılan donanım ve yazılım bileşenleri düşük maliyetli, esnek ve modülerdir. Deneysel sonuçlar, önerilen modelin ve sistemin yüksek doğruluk, hassasiyet ve verimlilik oranlarına sahip olduğunu göstermektedir.

Keywords

• Derin öğrenme
• Evrişimli sinir ağı
• Domates ayırma

Tomato Sorting System Based on Type Using Deep Learning

Abstract

The tomato is a vegetable that is cultivated globally and plays a significant role in the culinary traditions of numerous countries. This vegetable needs to be separated after collection to meet the requirements of obtaining different flavors outside the growing season. This study focuses on the automatic separation of Rio tomatoes, which are preferred for tomato paste and sauces, from Fujimaru tomatoes using artificial intelligence and image processing techniques. Convolutional neural network (CNN), R-CNN, and Fast-CNN models were used to classify two different tomato types, and their performances were compared. According to the experimental results, it was observed that the CNN model achieved 94.1% accuracy, 93.5% precision, 94.7% recall, and 94.1% F1 score in the classification of Rio type tomatoes, and 92.4% accuracy, 91.8% precision, 93% recall, and 92.4% F1 score in the classification of Fujimaru type tomatoes. The hardware and software components used in the project are low cost, flexible, and modular. Experimental results show that the proposed model and system have high accuracy, precision, and efficiency rates.

Keywords

• Deep Learning
• Convolution Neural Network (CNN)
• Tomatto sorting

References

1. [1] S. Eğilmez, “Ürün raporu Domates 2022” (2025, 15 January). Tarımsal Ekonomi ve Politika Geliştirme Enstitüsü, Erişim: https://arastirma.tarimorman.gov.tr/tepge/Belgeler/PDF%20%C3%9Cr%C3%BCn%20Raporlar%C4 %B1/2022%20%C3%9Cr%C3%BCn%20Raporlar%C4%B1/Domates%20%C3%9Cr%C3%BCn%20 Raporu%202022-364%20TEPGE.pdf
2. [2] P. Wan, A. Toudeshki, H. Tan, H., and R. Ehsani, “A methodology for fresh tomato maturity detection using computer vision,” Computers and electronics in agriculture, vol. 146, pp. 43-50, 2018.
3. [3] S. Kaur, A. Girdhar, and J. Gill, “Computer vision-based tomato grading and sorting,” In Advances in Data and Information Sciences: Proceedings of ICDIS-2017, Singapore, 2018, pp. 75 84.
4. [4] M. Agarwal, S. K. Gupta, and K. K. Biswas, “Development of Efficient CNN model for Tomato crop disease identification,” Sustainable Computing: Informatics and Systems, vol. 28, p.100407, 2020.
5. [5] M. M. Mijwil, K. Aggarwal, R. Doshi, K. K. Hiran, and M. Gök, “The Distinction between R CNN and Fast RCNN in Image Analysis: A Performance Comparison,” Asian Journal of Applied Sciences, vol. 10(5), pp. 429-437, 2022.
6. [6] V. Shankar, V. Kumar, U. Devagade, V. Karanth, and K. Rohitaksha, “Heart disease prediction using CNN algorithm,” SN Computer Science, vol. 1(3), p. 170, 2020.
7. [7] M. Maity, S. Banerjee, and S. S. Chaudhuri, “Faster r-cnn and yolo based vehicle detection: A survey,” In 2021 5th international conference on computing methodologies and communication (ICCMC), India, 2021, pp. 1442-1447.
8. [8] S. L. Vini, and P. Rathika, “TrioConvTomatoNet: A robust CNN architecture for fast and accurate tomato leaf disease classification for real time application,” Scientia Horticulturae, vol. 330, p.113079, 2024.

9. [9] L. Sun, K. Liang, Y. Wang, W. Zeng, X. Niu, and L. Jin, “Diagnosis of tomato pests and diseases based on lightweight CNN model,” Soft Computing, vol. 28(4), pp. 3393-3413, 2024.
10. [10] A. Amune, S. Shinde, A. Samargade, S. Suryawanshi, and Y. Shirsat, “Tomato TriSort: Smart Sorting System for Size, Color, and Pest Detection,” In 2024 4th International Conference on Sustainable Expert Systems (ICSES), Nepal, 2024, pp. 539-545.
11. [11] M. Sokolova, and G. Lapalme, “A systematic analysis of performance measures for classification tasks,” Information processing & management, vol. 45(4), pp. 427-437, 2009.
12. [12] L. Chen, S. Li, Q. Bai, J. Yang, S. Jiang, and Y. Miao, “Review of image classification algorithms based on convolutional neural networks,” Remote Sensing, vol. 13(22), p.4712, 2021. [13] Y. Gao, W. Liu, and F. Lombardi, “Design and implementation of an approximate softmax layer for deep neural networks,” In 2020 IEEE international symposium on circuits and systems (ISCAS), Spain, 2020, pp. 1-5.
13. [14] G. Priyadharshini, and D. R. Judie Dolly, “Comparative Investigations on Tomato Leaf Disease Detection and Classification Using CNN, R-CNN, Fast R-CNN and Faster R-CNN,” 2023 9th International Conference on Advanced Computing and Communication Systems (ICACCS), India, 2023, pp. 1540-1545.
14. [15] M. Maity, S. Banerjee, and S. S. Chaudhuri, “Faster r-cnn and yolo based vehicle detection: A survey,” In 2021 5th international conference on computing methodologies and communication (ICCMC), India, 2021, pp. 1442-1447.
15. [16] S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards real-time object detection with region proposal networks,” In IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, pp. 1137-1149, 2017.