A Comparative Analysis of Deep Learning Architectures for the Recognition of Endangered Flower Species in Kazakhstan

Zhanar Oralbekova; Tomiris Tapen; Ainur Shekerbek; Makpal Zhartybayeva; Alibek Orynbek

doi:10.48084/etasr.18465

Authors

Zhanar Oralbekova Astana IT University, Astana, Kazakhstan https://orcid.org/0000-0002-3726-8882
Tomiris Tapen Astana IT University, Astana, Kazakhstan https://orcid.org/0009-0008-1782-0909
Ainur Shekerbek L.N. Gumilyov Eurasian National University, Astana, Kazakhstan https://orcid.org/0000-0002-1088-4239
Makpal Zhartybayeva Astana IT University, Astana, Kazakhstan
Alibek Orynbek Astana IT University, Astana, Kazakhstan https://orcid.org/0009-0007-2102-1977

Volume: 16 | Issue: 3 | Pages: 36064-36070 | June 2026 | https://doi.org/10.48084/etasr.18465

Received: 1 March 2026 | Revised: 16 April 2026 and 23 April 2026 | Accepted: 30 April 2026 | Online: 5 May 2026

Corresponding author: Makpal Zhartybayeva

Abstract

Deep learning was used in this study to recognize endangered flower species in Kazakhstan. The results can help monitor biodiversity and protect those species. Convolutional Neural Network (CNN) models were used to classify different flower species. In this project, a publicly available Kaggle dataset was used, that included five flower species, namely sunflower, tulip, dandelion, rose, and daisy and two endangered species from the Red Book of Kazakhstan, Paeonia anomala and Crocus korolkowii. Employing transfer learning with pre-trained ImageNet weights, eight deep learning architectures were trained and evaluated: AlexNet, VGG16, GoogLeNet, ResNet50, DenseNet121, EfficientNet-B0, MobileNetV2, and YOLOv8-cls. To enhance generalization and address class imbalance, data augmentation and class equalization methods were applied. The evaluation criteria included accuracy, precision, recall, F1-score, and mean Average Precision (mAP). When comparing the models, YOLOv8-cls yielded the highest accuracy, whereas MobileNetV2 provided a noteworthy balance between speed and precision. This research reveals that image recognition systems rooted in deep learning can benefit ecological studies conducted in Kazakhstan by automatically recognizing common and endangered flowers, therefore playing a role in cataloging biodiversity and environmental monitoring.

Keywords:

convolutional neural networks, transfer learning, image classification, biodiversity monitoring, endangered flora

Downloads

Download data is not yet available.

References

The Red Data Book of Kazakhstan: Plants. Institute of Botany and Phytointroduction, 2014.

S. A. Kubentayev et al., "Current State of Natural Populations of Paeonia anomala (Paeoniaceae) in East Kazakhstan," Diversity, vol. 15, no. 11, Oct. 2023.

T. Abbas et al., "Deep Neural Networks for Automatic Flower Species Localization and Recognition," Computational Intelligence and Neuroscience, vol. 2022, no. 1, 2022, Art. no. 9359353.

H. Hiary, H. Saadeh, M. Saadeh, and M. Yaqub, "Flower classification using deep convolutional neural networks," IET Computer Vision, vol. 12, no. 6, pp. 855–862, 2018.

C. Narvekar and M. Rao, "Flower classification using CNN and transfer learning in CNN- Agriculture Perspective," in 2020 3rd International Conference on Intelligent Sustainable Systems (ICISS), Sept. 2020, pp. 660–664.

N. M. Rahim, M. A. Hairuddin, M. S. A. M. Ali, N. M. Tahir, A. A. Almisreb, and N. D. K. Ashar, "Pretrained Convolutional Neural Network for Fruit Classification Analysis of Pineapple Plantation Images," Engineering, Technology & Applied Science Research, vol. 15, no. 2, pp. 20819–20826, Apr. 2025.

S. Nuanmeesri, "A Hybrid Deep Learning and Optimized Machine Learning Approach for Rose Leaf Disease Classification," Engineering, Technology & Applied Science Research, vol. 11, no. 5, pp. 7678–7683, Oct. 2021.

A. I. R. H. Barat, W. S. Astuti, D. Hartama, A. P. Windarto, and A. Wanto, "Enhanced flower image classification using MobileNetV2 with optimized performance," JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer), vol. 11, no. 1, pp. 180–191, Aug. 2025.

G. Rajkomar and S. Pudaruth, "A Mobile App for the Identification of Flowers Using Deep Learning," International Journal of Advanced Computer Science and Applications, vol. 14, no. 5, pp. 76–102, 2023.

M. A. Valijonovich, "Bioecological Features and Anatomical Structure of <i>Crocus korolkovii</i> Regel & Maw in the Introduction of Uzbekistan," American Journal of Plant Sciences, vol. 08, no. 03, pp. 471–481, 2017.

K. He, X. Zhang, S. Ren, and J. Sun, "Deep Residual Learning for Image Recognition," in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016, pp. 770–778.

T.-M. Dutschmann, L. Kinzel, A. ter Laak, and K. Baumann, "Large-scale evaluation of k-fold cross-validation ensembles for uncertainty estimation," Journal of Cheminformatics, vol. 15, no. 1, Apr. 2023, Art. no. 49.

J. Deng, W. Dong, R. Socher, L.-J. Li, Kai Li, and Li Fei-Fei, "ImageNet: A large-scale hierarchical image database," in 2009 IEEE Conference on Computer Vision and Pattern Recognition, June 2009, pp. 248–255.

M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, "MobileNetV2: Inverted Residuals and Linear Bottlenecks," in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 2018, pp. 4510–4520.

G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, "Densely Connected Convolutional Networks," in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017, pp. 2261–2269.

M. Tan and Q. Le, "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks," in Proceedings of the 36th International Conference on Machine Learning, May 2019, pp. 6105–6114.

tensorflow, "models/research/slim/datasets/flowers.py at master tensorflow/models," GitHub. https://github.com/tensorflow/models/blob/master/research/slim/datasets/flowers.py.