e-ksper: Çekirdeksiz Kuru Üzüm Kalite Değerlendirmesi için Evrişimsel Sinir Ağları Temelli Sistem

Abstract

Çekirdeksiz kuru üzümler, renk, boyut, doku ve nem gibi çeşitli özelliklere göre belirlenen kalitelerine göre değerlendirilir. Mevcut şartlarda kuru üzüm sınıflandırma işleminin çoğu insan uzmanlar tarafından manuel olarak gerçekleştirilmektedir. Bu işlemin manuel olarak yapılması insan gücü açısından zahmetli olmakla birlikte öznel sonuçlar ortaya çıkarmaktadır. Bu nedenle, kuru üzümlerin objektif bir şekilde değerlendirilmesini sağlayan otomatik bir sistem, bu süreçte hem kuru üzüm üreticilerine hem de uzmanlara yardımcı olacaktır. Bu çalışmada, standart arka plan ve aydınlatma koşulları altında kuru üzümlerin görüntülerini alan basit bir makine prototipi ve evrişimsel sinir ağları kullanarak kuru üzümlerin kalite derecelendirmesini yapan otomatik bir sistem öneriyoruz. Önerilen model sadece renk sınıflarını değil, aynı zamanda yabancı maddeleri ve kusurlu çekirdekleri de tespit etmeyi amaçlamaktadır. Model, dört renk sınıfı ve bir kusurlu çekirdek sınıfı dahil olmak üzere beş sınıf üzerinde ortalama %88,2 sınıflandırma doğruluğu elde ederken, kusurlu çekirdekler hariç tutulduğunda modelin doğruluğu %98,6 olmaktadır. Dolayısıyla, önerilen model renk sınıflarını ayırt etmede çok başarılıdır ve ayrıca yabancı maddeleri ve kusurlu kuru üzümleri tespit etmede de önemli bir başarıya sahiptir. Bu çalışmada elde edilen sonuçlar üzerine kapsamlı bir analiz ve tartışma sunuyoruz.

Keywords

• kuru üzüm değerlendirme
• kuru üzüm sınıflandırma
• evrişimsel sinir ağları
• yabancı madde tespiti

e-ksper: A Convolutional Neural Network Based System for Seedless Raisin Quality Grading

Abstract

Seedless raisins are graded according to their quality which is determined based on several features such as color, size, texture, and humidity. Currently, most of the raisin grading process is performed by human experts manually, which is laborious and subjective work. Therefore, an automated system that enables objective evaluation of the raisins would be helpful for both producers and experts during this process. In this study, we propose a simple machinery prototype that takes images of raisins under standard background and illumination conditions and an automated system that performs quality grading of raisins using convolutional neural networks. The proposed model not only targets color classes but also aims to identify foreign matters and defected kernels. The model achieves about 88.2% average classification accuracy on five classes including four color classes and a defected kernels class; whereas the model's accuracy becomes 98.6% if defected kernels are excluded. Hence, the proposed model is very successful in differentiating colour classes and has also considerable success in detecting foreign matters and defected raisins. We provide a comprehensive analysis and discussion on these results.

Keywords

• raisin grading
• raisin classification
• convolutional neural networks
• foreign matter detection

References

1. [1] H. Ü. Evcim. A. Yazgı, E. Gülsoylu, E. Aykas, B. Çakmak, V. Demir, H. Yürdem, H. Güler, E. Urkan, F. Alayunt, H. Yalçın, H. Bilgen ve T. Günhan, "Tarimsal Mekanizasyonda Mevcut Durum ve Gelecek," Türkiye Ziraat Mühendisliği IX. Teknik Kongresi, 2020, ss. 497-526.
2. [2] S. S. Sajid and G. Hu, “Optimizing Crop Planting Schedule Considering Planting Window and Storage Capacity,” Frontiers in Plant Science, vol. 13, pp. 762446, 2022. doi: 10.3389/fpls.2022.762446
3. [3] E. A. Abioye, O. Hensel, T. J. Esau, O. Elijah, M. S. Z. Abidin, A. S. Ayobami, O. Yerima and A. Nasirahmadi, “Precision irrigation management using machine learning and digital farming solutions,” AgriEngineering, vol. 4, no. 1, pp. 70-103, 2022. doi: 10.3390/agriengineering4010006
4. [4] J. G. A. Barbedo, “Detecting and classifying pests in crops using proximal images and machine learning: A review,” AI, vol. 1, no. 2, pp. 312-328, 2020. doi: 10.3390/ai1020021
5. [5] E. J. Van Henten, J. Hemming, B. A. J. Van Tuijl, J. G. Kornet, J. Meuleman, J. Bontsema and E. A. Van Os,. “An autonomous robot for harvesting cucumbers in greenhouses,” Autonomous robots, vol. 13, no. 2, 241-258, 2002. doi: 10.1023/A:1020568125418
6. [6] X. Zhang, J. Yang, T. Lin, Y. Ying, “Food and agro-product quality evaluation based on spectroscopy and deep learning: A review,” Trends in Food Science & Technology, vol. 112, pp. 431-441, 2021. doi: 10.1016/j.tifs.2021.04.008
7. [7] S. Jagtap, F. Bader, G. Garcia-Garcia, H. Trollman, T. Fadiji, K. Salonitis, Food logistics 4.0: Opportunities and challenges. Logistics, vol. 5, no. 1, 2020. doi: 10.3390/logistics5010002
8. [8] T. Halstead, "Raisins: World Markets and Trade," Foreign Agricultural Service U.S. Department of Agriculture, 2018. Available: https://www.fas.usda.gov/data/raisins-world-markets-and-trade. [Accessed: 20.01.2023].

9. [9] A. Kayabasi, A. Toktas, K. Sabanci and E. Yigit, “Automatic classification of agricultural grains: Comparison of neural networks,” Neural Network World, vol. 28, no. 3, pp. 213–224, 2018. doi: 10.14311/nnw.2018.28.013
10. [10] K. Sabanci, A. Toktas and A. Kayabasi, “Grain classifier with computer vision using adaptive neuro-fuzzy inference system,” Journal of the Sicence of Food an Agriculture, vol. 97, no. 12, pp. 3994–4000, September 2017. doi: 10.1002/jsfa.8264
11. [11] P. P. Prasobhkumar, C.R. Francis and S.S. Gorthi, “Automated quality assessment of cocoons using a smart camera based system,” Engineering in Agriculture, Environment and Food, vol. 11, no. 4, pp. 202-210, 2018. doi: 10.1016/j.eaef.2018.05.002
12. [12] K. Rai, M. Dutta and S. Aggarwal, “A Grading System For Fruits Maturity Using Neural Networks Approach,” International Journal of Advanced Research in Computer Science, vol. 2, no. 6, pp. 451-454, 2011. doi: 10.26483/ijarcs.v2i6.868
13. [13] J. A. Kodagali and S. Balaji, “Computer vision and image analysis based techniques for automatic characterization of fruits-a review,” International Journal of Computer Applications, vol. 50, no. 6, pp. 451-454, 2012. doi: 10.5120/7773-0856
14. [14] M. P. Raj and P. Swaminarayan, “Applications of image processing for grading agriculture products,” International Journal on Recent and Innovation Trends in Computing and Communication, vol. 3, no. 3, pp. 1194-1201, March 2015. doi: 10.17762/ijritcc.v3i3.4000
15. [15] D. Saha and A. Manickavasagan, “Machine learning techniques for analysis of hyperspectral images to determine quality of food products: A review,” Current Research in Food Science, vol. 4, pp. 28-44, 2021. doi: 10.1016/j.crfs.2021.01.002
16. [16] H. Chopra, H. Singh, M. S. Bamrah, F. Mahbubani, A. Verma, N. Hooda, P. S. Rana, R. K. Singla and A. K. Singh, “Efficient fruit grading system using spectrophotometry and machine learning approaches,” IEEE Sensors Journal, vol. 21, no. 14, pp. 16162-16169, 2021. doi: 10.1109/JSEN.2021.3075465
17. [17] I. Cınar, M. Koklu and S. Tasdemir, “Classification of Raisin Grains Using Machine Vision and Artificial Intelligence Methods,” Gazi Journal of Engineering Sciences, vol. 6, no. 3, pp. 200-209, December, 2020, doi: 10.30855/gmbd.2020.03.03
18. [18] S. Kılıçarslan, "Kurum Üzüm Tanelerinin Sınıflandırılması İçin Hibrit Bir Yaklaşım", Mühendislik Bilimleri ve Araştırmaları Dergisi, cilt 4, sayı 1, ss. 62-71, 2022, doi:10.46387/bjesr.1084590
19. [19] I. Terzi, " Derin Öğrenme Teknikleri ile Üzüm Çeşitlerinin Belirlenmesi," Doktora Tezi, Biyosistem Mühenisliği, Tokat Gaziosmanpaşa Üniversitesi, Tokat, 2023.
20. [20] J. Guo, C. Chen, C. Chen, E. Zuo, B. Dong, X. Lv and W. Yang, “Near-infrared spectroscopy combined with pattern recognition algorithms to quickly classify raisins,” Scientific Reports, vol. 12, no. 1, pp. 7928, 2022. doi: 10.1038/s41598-022-12001-1
21. [21] M. Omid, M. Abbasgolipour, A. Keyhani and S. S. Mohtasebi, “Implementation of an efficient image processing algorithm for grading raisins,” International Journal of Signal and Image Processing, vol. 1, no. 1, pp. 31-34, 2010.
22. [22] S. Wang, K. Liu, X. Yu, D. Wu and Y. He, “Application of hybrid image features for fast and non-invasive classification of raisin,” Journal of Food Engineering, vol. 109, no. 3, pp. 531-537, 2012. doi: 10.1016/j.jfoodeng.2011.10.028
23. [23] X. Yu, K. Liu, D. Wu and Y. He, “Raisin quality classification using least squares support vector machine (LSSVM) based on combined color and texture features,” Food and Bioprocess Technology, vol. 5, no. 5, pp. 1552-1563, 2012. doi: 10.1007/s11947-011-0531-9
24. [24] S. P. Pawar and A. Sarkar, “Cost Effective Grading Process for Grape Raisins based on HSI and Fuzzy Logic Algorithms,” International Journal of Computer Applications, vol. 67, no. 22, pp. 18-22, April 2013.
25. [25] X. Li and X. Liu, “Detection Level of Raisins Based on Neural Network and Digital Image,” 2011 Third Pacific-Asia Conference on Circuits, Communications and System, pp. 1-3, 2011. doi: 10.1109/PACCS.2011.5990209
26. [26] S. A. Angadi and N. Hiregoudar, “A Cost Effective Algorithm for Grading Raisins Using Image Processing,” International Journal of Recent Trends in Engineering & Research (IJRTER), vol. 2, pp. 2455-1457, 2016.
27. [27] K. Mollazade, M. Omid and A. Arefi, “Comparing data mining classifiers for grading raisins based on visual features,” Computers and Electronics in Agriculture, vol. 84, pp. 124-131, June 2012. doi: 10.1016/j.compag.2012.03.004
28. [28] N. Karimi, R. R. Kondrood and T. Alizadeh, “An intelligent system for quality measurement of Golden Bleached raisins using two comparative machine learning algorithms,” Measurement, vol. 107, pp. 68-76, September 2017. doi: 10.1016/j.measurement.2017.05.009
29. [29] M. Khojastehnazhand and H. Ramezani, “Machine vision system for classification of bulk raisins using texture features,” Journal of Food Engineering, vol. 271, no. 3, pp. 109864, April 2020. doi: 10.1016/j.jfoodeng.2019.109864
30. [30] Y. Zhao, X. Xu and Y. He, “A Novel Hyperspectral Feature-Extraction Algorithm Based on Waveform Resolution for Raisin Classification,” Applied Spectroscopy, vol. 69, no. 12, pp. 1194-1201, 2015.
31. [31] K. G. Shinde and B. G. Patil, “Sorting of raisins using computer vision approach,” International Research Journal of Engineering and Technology, vol. 4, no. 6, pp. 2540-2544, June 2017.
32. [32] M. Abbasgholipour, M. Omid and A. Keyhani, “Color image segmentation with genetic algorithm in a raisin sorting system based on machine vision in variable conditions,” Expert Systems with Applications, vol. 38, no. 4, pp. 3671-3678, April 2011. doi: 10.1016/j.eswa.2010.09.023
33. [33] TSE Ziraat İhtisas Grubu, “Seedless raisin (TS 3411),” Turkish Standards Institution, vol. TR3411, 2011.
34. [34] N. Otsu, “A threshold selection method from gray-level histograms,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 9, no. 1, pp. 62-66, January 1979.
35. [35] Y. LeCun, Y. Bengio and G. E. Hinton, “Deep learning,” Nature, vol. 521, pp. 436-444, May 2015. doi: 10.1038/nature14539
36. [36] A. Krizhevsky, I. Sutskever and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” Communications of the ACM, vol. 60, no. 6, pp. 84-90, June 2017. doi: 10.1145/3065386
37. [37] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke and A. Rabinovich, “Going Deeper With Convolutions,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, June 7-12, 2015, pp. 1-9.
38. [38] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, A. Rabinovich, “Imagenet: A large-scale hierarchical image database,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Miami, FL, USA, June 20-25, 2009, pp. 248-255.