Orchid Species Classification Using the DenseNet121 Deep Learning Model with a Data Imbalance Handling Approach
Keywords:
Data Imbalance, Deep Learning, DenseNet121, Orchid Classification,, UndersamplingAbstract
For conservation, commercial cultivation, and scientific research, accurate identification of orchid species often requires specialized expertise. In this study, the DenseNet121 deep learning architecture was employed to develop an automated classification system for four popular orchid species. DenseNet121 was selected for its ability to extract complex hierarchical features and its strong performance on limited-scale datasets. The initial dataset comprised 1,935 images of Phalaenopsis, Cattleya, Dendrobium, and Vanda orchids. However, after manual removal of duplicate images, only 1,658 images remained, revealing significant class imbalance. The undersampling method was applied to balance each class to 248 samples. The dataset was then split into 75% training, 15% validation, and 10% testing, and enhanced through data augmentation techniques such as rotation, flipping, brightness variation, width shift, height shift, and zoom. The final model achieved 97.00% accuracy with class-specific performance ranging from 92.59% to 100% accuracy across different orchid species. This research can serve as a foundation for developing mobile or web applications to assist researchers, farmers, and orchid enthusiasts in accurately identifying orchid species, while supporting conservation efforts for orchid biodiversity in Indonesia.
Downloads
References
[1] D. Zhang and others, “Advances and prospects of orchid research and industrialization,” 2022, doi: 10.1093/hr/uhac220.
[2] A. Lepcha, S. D. Khade, and T. Roy, “Economics of Flower Cultivation with Special Reference to Orchid in Hilly Areas of West Bengal,” Econ. Aff. New Delhi, vol. 65, no. 3, pp. 395–400, Sep. 2020, doi: 10.46852/0424-2513.3.2020.11.
[3] P. Tiwari, A. Sharma, S. K. Bose, and K. I. Park, “Advances in Orchid Biology: Biotechnological Achievements, Translational Success, and Commercial Outcomes,” Feb. 2024, doi: 10.3390/horticulturae10020152.
[4] A. Setiaji, R. R. R. Annisa, A. D. Santoso, A. Kinasih, and A. D. R. Riyadi, “Review: Factors affecting mass propagation of Vanda orchid in vitro,” Cell Biol. Dev., vol. 5, pp. 51–62, Dec. 2021, doi: 10.13057/cellbioldev/t050201.
[5] K. Balilashaki, S. Moradi, M. Vahedi, and A. A. Khoddamzadeh, “A molecular perspective on orchid development,” Sep. 2020, doi: 10.1080/14620316.2020.1727782.
[6] R. D. Phillips, N. Reiter, and R. Peakall, “Orchid conservation: From theory to practice,” Aug. 2020, doi: 10.1093/aob/mcaa093.
[7] J. D. Ackerman and others, “Beyond the various contrivances by which orchids are pollinated: global patterns in orchid pollination biology,” Bot. J. Linn. Soc., vol. 202, no. 3, pp. 295–324, Jun. 2023, doi: 10.1093/botlinnean/boac082.
[8] P. Sharma, Y. P. S. Berwal, and W. Ghai, “Performance analysis of deep learning CNN models for disease detection in plants using image segmentation,” Inf. Process. Agric., vol. 7, no. 4, pp. 566–574, Dec. 2020, doi: 10.1016/j.inpa.2019.11.001.
[9] J. Chen, J. Chen, D. Zhang, Y. Sun, and Y. A. Nanehkaran, “Using deep transfer learning for image-based plant disease identification,” Comput. Electron. Agric., vol. 173, pp. 1–11, Jun. 2020, doi: 10.1016/j.compag.2020.105393.
[10] D. Li and others, “A recognition method for rice plant diseases and pests video detection based on deep convolutional neural network,” Sens. Switz., vol. 20, no. 3, pp. 1–21, Feb. 2020, doi: 10.3390/s20030578.
[11] Q. Fu, X. Zhang, F. Zhao, R. Ruan, L. Qian, and C. Li, “Deep Feature Extraction for Cymbidium Species Classification Using Global–Local CNN,” Horticulturae, vol. 8, no. 6, p. 470, May 2022, doi: 10.3390/horticulturae8060470.
[12] I. A. Mohtar and A. A. M. Fadzil, “New Species Orchid Recognition System Using Convolutional Neural Network,” Math. Sci. Inform. J., vol. 2, no. 2, pp. 35–43, Nov. 2021, doi: 10.24191/mij.v2i2.14248.
[13] C.-H. Ou, Y.-N. Hu, D.-J. Jiang, and P.-Y. Liao, “An Ensemble Voting Method of Pre-Trained Deep Learning Models for Orchid Recognition,” in 2023 IEEE International Systems Conference (SysCon), IEEE, Apr. 2023, pp. 1–5. doi: 10.1109/SysCon53073.2023.10131263.
[14] L. Alzubaidi and others, “Review of deep learning: concepts, CNN architectures, challenges, applications, future directions,” J. Big Data, vol. 8, no. 1, pp. 1–74, Dec. 2021, doi: 10.1186/s40537-021-00444-8.
[15] Ü. Atila, M. Uçar, K. Akyol, and E. Uçar, “Plant leaf disease classification using EfficientNet deep learning model,” Ecol. Inform., vol. 61, pp. 1–21, Mar. 2021, doi: 10.1016/j.ecoinf.2020.101182.
[16] M. Bakr, S. Abdel-Gaber, M. Nasr, and M. Hazman, “DenseNet Based Model for Plant Diseases Diagnosis,” Eur. J. Electr. Eng. Comput. Sci., vol. 6, no. 5, pp. 1–9, Sep. 2022, doi: 10.24018/ejece.2022.6.5.458.
[17] T. S. Arulananth, S. W. Prakash, R. K. Ayyasamy, V. P. Kavitha, P. G. Kuppusamy, and P. Chinnasamy, “Classification of Paediatric Pneumonia Using Modified DenseNet-121 Deep-Learning Model,” IEEE Access, vol. 12, pp. 35716–35727, 2024, doi: 10.1109/ACCESS.2024.3371151.
[18] S. A. A. Shah and others, “Automatic and fast classification of barley grains from images: A deep learning approach,” Smart Agric. Technol., vol. 2, pp. 1–6, Dec. 2022, doi: 10.1016/j.atech.2022.100036.
[19] R. I. Hasan, S. M. Yusuf, and L. Alzubaidi, “Review of the state of the art of deep learning for plant diseases: A broad analysis and discussion,” Oct. 2020, doi: 10.3390/plants9101302.
[20] C. Fan, M. Chen, X. Wang, J. Wang, and B. Huang, “A Review on Data Preprocessing Techniques Toward Efficient and Reliable Knowledge Discovery From Building Operational Data,” Front. Energy Res., vol. 9, pp. 1–17, Mar. 2021, doi: 10.3389/fenrg.2021.652801.
[21] A. A. Khan, O. Chaudhari, and R. Chandra, “A review of ensemble learning and data augmentation models for class imbalanced problems: Combination, implementation and evaluation,” Expert Syst. Appl., vol. 244, pp. 1–29, Jun. 2024, doi: 10.1016/j.eswa.2023.122778.
[22] D. Schaudt and others, “Augmentation strategies for an imbalanced learning problem on a novel COVID-19 severity dataset,” Sci. Rep., vol. 13, no. 1, pp. 1–16, Oct. 2023, doi: 10.1038/s41598-023-45532-2.
[23] E. Strelcenia and S. Prakoonwit, “A Survey on GAN Techniques for Data Augmentation to Address the Imbalanced Data Issues in Credit Card Fraud Detection,” Mach. Learn. Knowl. Extr., vol. 5, no. 1, pp. 304–329, Mar. 2023, doi: 10.3390/make5010019.
[24] J. Hemalatha, S. A. Roseline, S. Geetha, S. Kadry, and R. Damaševičius, “An efficient densenet‐based deep learning model for Malware detection,” Entropy, vol. 23, no. 3, pp. 1–23, Mar. 2021, doi: 10.3390/e23030344.
[25] B. Solano-Rojas, R. Villalón-Fonseca, and G. Marín-Raventós, “Alzheimer’s Disease Early Detection Using a Low Cost Three-Dimensional Densenet-121 Architecture,” in Lecture Notes in Computer Science, vol. 12157, Springer, 2020, pp. 3–15. doi: 10.1007/978-3-030-51517-1_1.
[26] T. Capblancq and B. R. Forester, “Redundancy analysis: A Swiss Army Knife for landscape genomics,” Dec. 2021, doi: 10.1111/2041-210X.13722.
[27] B. Li, “Facial expression recognition by DenseNet-121,” in Multi-Chaos, Fractal and Multi-Fractional Artificial Intelligence of Different Complex Systems, vol. 51, 2021, pp. 263–276. doi: 10.1016/B978-0-323-90032-4.00019-5.
[28] G. Hiremath, J. A. Mathew, and N. K. Boraiah, “Hybrid Statistical and Texture Features with DenseNet 121 for Breast Cancer Classification,” Int. J. Intell. Eng. Syst., vol. 16, no. 2, pp. 24–34, 2023, doi: 10.22266/ijies2023.0430.03.
[29] D. Ezzat, A. E. Hassanien, and H. A. Ella, “An optimized deep learning architecture for the diagnosis of COVID-19 disease based on gravitational search optimization,” Appl. Soft Comput., vol. 98, pp. 1–13, Jan. 2021, doi: 10.1016/j.asoc.2020.106742.
[30] M. Seeland and P. Mäder, “Multi-view classification with convolutional neural networks,” Jan. 2021, doi: 10.1371/journal.pone.0245230.
[31] A. S. Vellaichamy, A. Swaminathan, C. Varun, and K. S, “Multiple Plant Leaf Disease Classification Using DenseNet-121 Architecture,” Int. J. Electr. Eng. Technol., vol. 12, no. 5, pp. 38–57, May 2021, doi: 10.34218/ijeet.12.5.2021.005.
[32] K. M. Hasib, N. A. Towhid, and M. R. Islam, “HSDLM,” Int. J. Cloud Appl. Comput., vol. 11, no. 4, pp. 1–13, Oct. 2021, doi: 10.4018/IJCAC.2021100101.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Fadhilah Aditya Akbar, Christy Atika Sari
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
