Optik Mikroskopi ve Derin Öğrenme Kullanılarak Kepek Katmanından Buğday Tohumlarının Tanımlanması

Abstract

Özet Tohum analizi ve sınıflandırması, ekimden önce kullanılacak tohumların çeşitlerinin belirlenmesi ve ekim yapılacak alana uygun çeşitlerin kullanıldığının doğrulanması açısından son derece önemlidir. Ekim yapılan tarımsal alanlarda yüksek verimlilik ile birlikte kaliteli ve saf tohumların elde edilebilmesi ancak ekim öncesi uygulanacak analiz ve sınıflandırma ile mümkün olabilmektedir. Bu çalışmada farklı kalitelerdeki dokuz buğday çeşidine ait tohumları sınıflandırılarak ekimden önce tohumların çeşitlerini belirleyecek bir sistem oluşturulması amaçlanmıştır. Çalışmanın temel hedefleri, bilgisayar destekli akıllı sistemler kullanarak tahıl ürünlerini otomatik olarak tanımlamak ve ekilecek bölgenin ekolojik koşullarına en uygun buğday tohumlarını belirlemektir. Bu amaçla, incelenen buğday çeşitlerinin tohum kesitleri ışık mikroskobu ile fotoğraflanarak özel bir veri seti oluşturulmuş ve yüzeysel ile derin mimariler kullanılarak CNN tabanlı bir otomatik buğday tanımlama çerçevesi önerilmiştir. En iyi sonuçlar %97,67 test doğruluğu, %90,03 duyarlılık, %98,79 özgüllük, %90,50 hassasiyet ve %90,06 f1-skoru olarak elde edilmiştir. Deneyler, CNN tabanlı yöntemlerin buğday kepeğinin ayırt edici özelliklerini çıkarmada ve buğday tohumlarını tanımlamada başarılı olduğunu göstermektedir. Anahtar kelimeler: buğday;sınıflandırma;optik mikroskopi;derin öğrenme;tohum analizi

Keywords

• Optik Mikroskopi
• Derin Öğrenme
• Tohum Analizi
• Buğday
• Sınıflandırma

Identification of wheat seeds from bran layer using optical microscopy and deep learning

Abstract

Purpose: This study aims to automate the identification of grain varieties and select the most suitable wheat genotypes for specific ecological conditions using Artificial Intelligence (AI)-based systems. The goal is to facilitate high-yield and high-quality production through pre-sowing analysis. Method: Seeds from nine wheat genotypes with different qualities were used, and cross-sections of the wheat genotypes were photographed under a light microscope to create a specialized dataset. A Convolutional Neural Network (CNN)-based automated wheat identification framework was then proposed, utilizing both shallow and deep architectures. Findings: The experiments confirm that CNN-based methods are highly effective in extracting distinctive features from wheat bran and accurately identifying wheat seed varieties. Conclusion: The research successfully distinguished nine varieties and found that a simpler model (ResNet18) outperformed deeper networks, offering a practical solution for agricultural verification. Keywords: wheat;classification;optical microscopy;deep learning;seed analysis

Keywords

• wheat
• classification
• optical microscopy
• deep learning
• seed analysis

References

1. [1] Arslan, A., Aygun, Y. Z., Turkmen, M., Celiktas, N., & Mert, M. (2025). Combining non-destructive devices and multivariate analysis as a tool to quantify the fatty acid profiles of linseed genotypes. Talanta, 281, 126798. doi:https://doi.org/10.1016/j.talanta.2024.126798
2. [2] Bao, Y., Mi, C., Wu, N., Liu, F., & He, Y. (2019). Rapid Classification of Wheat Grain Varieties Using Hyperspectral Imaging and Chemometrics. Applied Sciences, 9(19), 4119. doi:https://doi.org/10.3390/app9194119
3. [3] Charytanowicz, M., Kulczycki, P., Kowalski, P. A., Łukasik, S., & Czabak-Garbacz, R. (2018). An evaluation of utilizing geometric features for wheat grain classification using X-ray images. Computers and Electronics in Agriculture, 144, 260-268. doi:https://doi.org/10.1016/j.compag.2017.12.004
4. [4] Diederichsen, A., & Raney, J. P. (2006). Seed colour, seed weight and seed oil content in Linum usitatissimum accessions held by Plant Gene Resources of Canada. Plant Breeding, 125(4), 372-377. doi:https://doi.org/10.1111/j.1439-0523.2006.01231.x
5. [5] Rahman, A., & Cho, B.-K. (2016). Assessment of seed quality using non-destructive measurement techniques: a review. Seed Science Research, 26(4), 285-305. doi:https://10.1017/S0960258516000234
6. [6] Wang, Q. G., Zhu, Q. B., Qin, J., & Huang, G. (2015). Review of seed quality and safety tests using optical sensing technologies. Seed Science and Technology, 43, 1-30. doi:https://doi.org/10.15258/sst.2015.43.3.16
7. [7] Olgun, M., Köse, A., Belen, S., Karaduman, Y., Budak Başçiftçi, Z., Ayter Arpacıoğlu, N. G., & Turan, M. (2024). Characterization of whole seeds lipids, extracted lipids composition in bread wheat (T.aestivum L.) genotypes grown in Eskisehir province in Türkiye. Biological Diversity and Conservation, 17(2), 175-189. doi:https://doi.org/10.46309/biodicon.2024.1394551
8. [8] Moss, R. (1973). Conditioning studies on Australian wheat. II. Morphology of wheat and its relationship to conditioning. Journal of the Science of Food and Agriculture, 24(9), 1067-1076. doi:https://doi.org/10.1002/jsfa.2740240908

9. [9] Chen, Z., Mense, A. L., Brewer, L. R., & Shi, Y. C. (2024). Wheat bran layers: composition, structure, fractionation, and potential uses in foods. Crit Rev Food Sci Nutr, 64(19), 6636-6659. doi:https://doi.org/10.1080/10408398.2023.2171962
10. [10] Saidani, S., Zairi, M., Meziani, S., Labga, L., Tiboura, G., Menadi, N., & Demmouche, A. (2022). Bioactive Compounds and Antioxidant Activity of Peripheral Layers of Soft Wheat Grown in Algeria During Seed Filling. Food and Environment Safety Journal, 21. doi:https://doi.org/10.4316/fens.2022.009
11. [11] Deniz, E., & Serttaş, S. (2023). Disease detection in bean leaves using deep learning. Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering, 65(2), 115-129. doi:https://doi.org/10.33769/aupse.1247233
12. [12] Özkan, K., Seke, E., & Işık, Ş. (2021). Wheat kernels classification using visible-near infrared camera based on deep learning. Pamukkale University Journal of Engineering Sciences, 27(5), 618-626. doi:https://dx.doi.org/10.5505/pajes.2020.80774
13. [13] Laabassi, K., Belarbi, M. A., Mahmoudi, S., Mahmoudi, S. A., & Ferhat, K. (2021). Wheat varieties identification based on a deep learning approach. Journal of the Saudi Society of Agricultural Sciences, 20(5), 281-289. doi:https://doi.org/10.1016/j.jssas.2021.02.008
14. [14] Lingwal, S., Bhatia, K., & Tomer, M. (2021). Image-based wheat grain classification using convolutional neural network. Multimedia Tools and Applications, 80, 1-25. doi:https://doi.org/10.1007/s11042-020-10174-3
15. [15] Anagun, Y., Isik, S., Olgun, M., Sezer, O., Basciftci, Z. B., & Arpacioglu, N. G. A. (2023). The classification of wheat species based on deep convolutional neural networks using scanning electron microscope (SEM) imaging. European Food Research and Technology, 249(4), 1023-1034. doi:https://doi.org/10.1007/s00217-022-04192-8
16. [16] Simonyan, K., & Zisserman, A. (2015). Very Deep Convolutional Networks for Large-Scale Image Recognition. Paper presented at the 3rd International Conference on Learning Representations (ICLR 2015).
17. [17] Huang, G., Liu, Z., Maaten, L. V. D., & Weinberger, K. Q. (2017, 21-26 July 2017). Densely Connected Convolutional Networks. Paper presented at the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
18. [18] He, K., Zhang, X., Ren, S., & Sun, J. (2016, 27-30 June 2016). Deep Residual Learning for Image Recognition. Paper presented at the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
19. [19] Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018, 18-23 June 2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks. Paper presented at the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.
20. [20] Tan, M., & Le, Q. V. (2019, 9-15 June 2019). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Paper presented at the 36th International Conference on Machine Learning (ICML 2019), Long Beach.
21. [21] Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., . . . Fei-Fei, L. (2015). ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision, 115(3), 211-252. doi:https://doi.org/10.1007/s11263-015-0816-y
22. [22] Khojastehnazhand, M., & Roostaei, M. (2022). Classification of seven Iranian wheat varieties using texture features. Expert Systems with Applications, 199, 117014. doi:https://doi.org/10.1016/j.eswa.2022.117014
23. [23] Ünlerşen, M., Sönmez, M., Aslan, M., Demir, B., Aydin, N., Sabanci, K., & Ropelewska, E. (2022). CNN-SVM hybrid model for varietal classification of wheat based on bulk samples. European Food Research and Technology, 248. doi:https://doi.org/10.1007/s00217-022-04029-4
24. [24] Yasar, A. (2022). Benchmarking analysis of CNN models for bread wheat varieties. European Food Research and Technology, 249. doi:https://doi.org/10.1007/s00217-022-04172-y [25] Agarwal, D., Sweta, & Bachan, P. (2023). Machine learning approach for the classification of wheat grains. Smart Agricultural Technology, 3, 100136. doi:https://doi.org/10.1016/j.atech.2022.100136