SavedAdd your journal

Journals / Bağbahçe Bilim Dergisi / 2026 / Cilt: 13 Sayı: 2

AI-Assisted Identification of Brassicaceae Species Distributed in Van Yüzüncü Yıl University Campus

Van Yüzüncü Yıl Üniversitesi Kampüsünde Yayılış Gösteren Brassicaceae (Hardalgiller) Ailesine Ait Türlerin Yapay Zekâ Yardımı ile Teşhis Edilmesi

Yahya Demir(VAN YÜZÜNCÜ YIL ÜNİVERSİTESİ)0009-0003-9102-6491
Murat Ünal(VAN YÜZÜNCÜ YIL ÜNİVERSİTESİ)0000-0002-6224-8269
Abdullah Eid0009-0006-7227-9049
Pages
87–93
Publication Date
2026-08-31
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Consequently, the resulting AI model was observed to identify species with an average accuracy of over 90%.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:This study aims to accurately and effectively identify plant species belonging to the Brassicaceae family found across the Van Yüzüncü Yıl University campus flora, using artificial intelligence-based image recognition systems.
📊
Key Findings & Data:This combined dataset was used to train the model with transfer learning techniques and analyzed with deep learning algorithms to ensure accurate species-level classification.
💡
Conclusion & Impact:Consequently, the resulting AI model was observed to identify species with an average accuracy of over 90%.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Bitki taksonomisi · Brassicaceae · derin öğrenme

Abstract

This study aims to accurately and effectively identify plant species belonging to the Brassicaceae family found across the Van Yüzüncü Yıl University campus flora, using artificial intelligence-based image recognition systems. Plant taxonomy is of great importance for the conservation of biodiversity, enhancing agricultural productivity, and understanding ecosystem dynamics. The traditional methods used in diagnosing biodiversity, which rely on the manual assessment of morphological variations and require expertise in the field, have made their integration with technology essential. The identification process is further complicated in the Brassicaceae family, which is known for its morphological similarities, due to intra-species resemblances, similarities across developmental stages, and phenotypic plasticity caused by environmental factors. Therefore, a dataset was created from high-resolution images of plant samples collected from the landscaped campus grounds. These images were produced to capture morphological variations by considering seasonal and developmental stages, focusing on leaf, flower, fruit, and stem characteristics, and were supplemented by visual materials obtained from the internet. This combined dataset was used to train the model with transfer learning techniques and analyzed with deep learning algorithms to ensure accurate species-level classification. Consequently, the resulting AI model was observed to identify species with an average accuracy of over 90%.

Özet

Bu çalışma, Van Yüzüncü Yıl Üniversitesi kampüs florasında yayılış gösteren Brassicaceae (Hardalgiller) familyasına ait bitki türlerinin, yapay zekâ tabanlı görüntü tanıma sistemleri kullanılarak doğru ve etkili bir biçimde teşhis edilmesini amaçlamaktadır. Bitki taksonomisi, biyolojik çeşitliliğin korunması, tarımsal verimliliğin artırılması ve ekosistem dinamiklerinin anlaşılması açısından büyük öneme sahiptir. Biyolojik çeşitliliğin teşhisinde kullanılan geleneksel yöntemler, morfolojik varyasyonların manuel olarak değerlendirilmesi, söz konusu alandaki uzmanlığa duyulan gereksinimden dolayı teknoloji ile entegrasyonunu zorunlu hale getirmiştir. Morfolojik benzerlikler yansıtan familyaların başında gelen Brassicaceae familyasında da tür içi ve türlerin gelişim aşamalarındaki benzerliklerin yanında çevresel faktörlerin sebep olduğu fenotipik plastisite de teşhis sürecini karmaşıklaştırmaktadır. Bundan dolayı peyzaj çalışmaları ile şekillenen kampüs yerleşkesinden toplanan bitki örneklerinin yaprak, çiçek, meyve ve gövde özelliklerinin yansıra morfolojik varyasyonları kapsayacak şekilde mevsimsel ve gelişimsel aşamalar dikkate alınarak üretilen yüksek çözünürlüklü görüntüleri ile genel ağdan alınan görsel materyallerin toplamından ortaya çıkan veri kümesi tür düzeyinde sınıflandırma doğruluğunu sağlamak için transfer öğrenme teknikleriyle modelin eğitiminde kullanılmış ve derin öğrenme algoritmaları ile analiz edilmiştir. Sonuçta, üretilen yapay zeka modelinin ortalama olarak %90’ın üzerinde bir doğrulukla tür teşhisi yapabildiği görülmüştür.

🔖

Cite This Article

Demir, Y., Ünal, M., Eid, A. (2026). AI-Assisted Identification of Brassicaceae Species Distributed in Van Yüzüncü Yıl University Campus. Bağbahçe Bilim Dergisi, Cilt: 13 Sayı: 2, 87–93. https://doi.org/10.35163/bagbahce.1812834

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (34)

  1. Al-Shehbaz, I. A. (2012). A generic and tribal synopsis of the Brassicaceae (Cruciferae). Taxon 61(5): 931–954.
  2. Bakis, Y., Babac, M. T. ve Uslu, E. (2011). Updates and improvements of Turkish Plants Data Service (TÜBİVES). Şu eserde: Health Informatics and Bioinformatics (HIBIT), 2011 6th International Symposium on: 136-140. IEEE.
  3. Bonnet, P., Joly, A., Bonnefille, C., Barthélémy, D., Boujemaa, N. ve Wählby, C. (2020). Plant identification: Experts vs. machines in the era of deep learning. Şu eserde: Multimedia Tools and Applications for Environmental & Biodiversity Informatics, s. 131–149. Springer, Cham.
  4. Cope, J. S., Corney, D., Clark, J. Y., Remagnino, P. ve Wilkin, P. (2012). Plant species identification using digital morphometrics: A review. Expert Syst. Appl. 39(8): 7562–7573.
  5. Davis, P.H. (ed.) (1965-1985) Flora of Turkey and The East Eagean Islands 1-9. Edinburg Universty Press, Edinburgh.
  6. Davis, P.H., Mill, R.R. ve Tan, K. (edlr.) (1988). Flora of Turkey and The East Eagean Islands 10. Edinburg Universty Press, Edinburg.
  7. Eunice, J., Popescu, D. E., Chowdary, M. K. ve Hemanth, J. (2022). Deep learning-based leaf disease detection in crops using images for agricultural applications. Agronomy 12(10): 2395.
  8. Farnsworth, E. J., Chu, M., Kress, W. J., Neill, A. K., Best, J. H., Pickering, J., Stevenson, R. D., Courtney, G. W., VanDyk, J. K. ve Ellison, A. M. (2013). Next-generation field guides. BioScience 63(11): 891–899.
  9. Facebook (Meta). (2023). React Native (Version 0.72.4) [Software]. ", er. tar.: 08 vii 2023”.
  10. Ghazi, M. M., Yanikoglu, B. ve Aptoula, E. (2017). Plant identification using deep neural networks via optimization of transfer learning parameters. Neurocomputing 235: 228–235.
  11. Goëau, H., Bonnet, P. ve Joly, A. (2020). Plant identification based on noisy web data: The power of machine learning and crowd sourcing. Biodivers. Inf. Sci. Stand. 4: e59125.
  12. Gonzalez, R. C. ve Woods, R. E. (2018). Digital Image Processing (4. baskı). Pearson Education, New York. Goodfellow, I., Bengio, Y. ve Courville, A. (2016). Deep Learning. MIT Press, Cambridge.
  13. Grinberg, M. (2018). Flask Web Development: Developing Web Applications with Python (2. baskı). O'Reilly Media, Sebastopol.
  14. Güner, A., Özhatay, N., Ekim, T. ve Başer, K.H.C. (edlr.). (2000). Flora of Turkey and the East Aegean Islands 11. Edinburgh University Press, Edinburgh.
  15. Haider, N. (2018). A brief review on plant taxonomy and its components. J. Plant Sci. Res. 34(2): 277-292.
  16. Joly, A., Bonnet, P., Goëau, H., Barbe, J., Selmi, S., Champ, J.,. ve Boujemaa, N. (2014). Interactive plant identification based on social image data. Ecol. Inform. 23: 22–34.
  17. Kreuzhage, A. (2021). iNaturalist Research-Grade Observation. ", er. tar.: 08 vii 2023”.
  18. Kingma, D. P. ve Ba, J. (2015). Adam: A Method for Stochastic Optimization. arXiv preprint arXiv:1412.6980.
  19. Koch, M. A., Karl, R., Kiefer, C. ve Al-Shehbaz, I. A. (2010). Colonizing the American continent: Systematics of the genus Arabis in North America (Brassicaceae). Am. J. Bot. 97(6): 1040–1057.
  20. Mäder, P., Boho, D., Rzanny, M., Seeland, M., Wittich, H. C., Deggelmann, A. ve Wäldchen, J. (2021). The Flora Incognita app: Automated wild plant identification. Methods Ecol. Evol. 12(11): 2195–2201.
  21. Meinke, D. W., Cherry, J. M., Dean, C., Rounsley, S. D. ve Koornneef, M. (1998). Arabidopsis thaliana: a model plant for genome analysis. Science 282(5389): 662-682.
  22. Otsu, N. (1979). A Threshold Selection Method from Gray-Level Histograms. IEEE T. Syst. Man Cy. 9(1): 62–66.
  23. Perez, L. ve Wang, J. (2017). The effectiveness of data augmentation in image classification using deep learning. arXiv preprint arXiv:1712.04621.
  24. Prechelt, L. (2012). Early Stopping – But When? Şu eserde: Neural Networks: Tricks of the Trade. Springer, Berlin. Rachakatla, S. K., Ravichandran, P. ve Kumar, N. (2022). Scalable machine learning workflows in data Warehousing: automating model training and deployment with AI. Aust. J. Artif. Intell. Data Sci. 1(1): 25-40.
  25. Reyes, A. K., Caicedo, J. C. ve Camargo, J. E. (2015). Fine-tuning deep convolutional networks for plant recognition. CEUR Workshop Proc. 1391: 1–8.
  26. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A. ve Chen, L. C. (2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks. Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 4510–4520.
  27. Unger, J., Merhof, D. ve Renner, S. (2016). Computer vision applied to herbarium specimens of German trees: Testing the future utility of the millions of herbarium specimen images for automated identification. BMC Evol. Biol. 16(1): 248.
  28. Wäldchen, J. ve Mäder, P. (2018). Machine learning for image based species identification. Methods Ecol. Evol. 9(11): 2216-2225.
  29. Wäldchen, J. ve Mäder, P. (2018). Plant species identification using computer vision techniques: A systematic literature review. Arch. Comput. Method. E. 25(2): 507–543.
  30. Wang, M. ve Deng, W. (2018). Deep visual domain adaptation: A survey. Neurocomputing 312: 135–53.
  31. Warwick, S. I., Francis, A. ve Al-Shehbaz, I. A. (2006). Brassicaceae: Species checklist and database on CD-Rom. Plant Syst. Evol. 259(2-4): 249-258.
  32. Facebook (Meta). (2023). React Native (Version 0.72.4) [Software]. ", er. tar.: 08 vii 2023”.
  33. Joly, A., Bonnet, P., Goëau, H., Barbe, J., Selmi, S., Champ, J.,. ve Boujemaa, N. (2014). Interactive plant identification based on social image data. Ecol. Inform. 23: 22–34.
  34. Kreuzhage, A. (2021). iNaturalist Research-Grade Observation. ", er. tar.: 08 vii 2023”.