A comparative evaluation of visual accuracy in AI-Generated botanical illustrations
DOI:
https://doi.org/10.30998/jd.v13i4.4883Keywords:
Generative Artificial Intelligent, GenAI, Botanical Illustration, Scientific IllustrationAbstract
Generative Artificial Intelligence (GenAI) technology is now one of the most widely used tools for producing creative content, including text, images, sound, and video. GenAI represents a breakthrough in both art and education, particularly in aiding the creation of illustrations. Traditionally, producing scientific illustrations requires a high level of accuracy and adherence to established scientific standards. This challenge has prompted researchers to analyze the effectiveness of GenAI in supporting the creation of scientific illustrations, with a specific focus on botanical illustrations. The purpose of this research is to evaluate the accuracy of GenAI-generated botanical illustrations. This study employs a descriptive qualitative method with an experimental approach, specifically testing the application of GenAI to generate botanical images using four GenAI platforms. The resulting illustrations from these four platforms are then visually compared, evaluated, and validated by a botanical illustration expert. The results indicate that GenAI has potential for botanical illustration, especially as a source of inspiration for exploring different illustration styles, but it is still unable to consistently produce accurate scientific representations. The results also show differences in the accuracy and quality of the generated illustrations among the selected plants, which can lead to anatomical distortions or unrealistic features, highlighting the need for expert validation and careful selection of illustration styles.
Downloads
References
Braguez, J. (2024). Exploring the synergy between digital illustration and AI: An artist’s insight. In The IAFOR International Conference on Arts & Humanities–Hawaii 2024 official conference proceedings (pp. 389–400). The International Academic Forum. https://doi.org/10.22492/issn.2432-4604.2024.33
Chen, H.-C. (2023). Harnessing AI for scientific illustration: Exploring tornado dynamics through Midjourney. In 2023 12th International Conference on Awareness Science and Technology (iCAST) (pp. 136–141). IEEE. https://doi.org/10.1109/iCAST57874.2023.10359310
Escardó, A., & Wiedemann, J. (Eds.). (2022). Science illustration: A history of visual knowledge from the 15th century to today. TASCHEN.
Haider, S. A., Prabha, S., Gomez-Cabello, C. A., Borna, S., Pressman, S. M., Genovese, A., Trabilsy, M., Galvao, A., Aziz, K. T., Murray, P. M., Parte, Y., Yu, Y., Tao, C., & Forte, A. J. (2025). A validity analysis of text-to-image generative artificial intelligence models for craniofacial anatomy illustration. Journal of Clinical Medicine, 14(7), 2136. https://doi.org/10.3390/jcm14072136
Hickman, E. J., Yates, C. J., & Hopper, S. D. (2017). Botanical illustration and photography: A southern hemisphere perspective. Australian Systematic Botany, 30(4), 291–325. https://doi.org/10.1071/SB16059
Iwasa, J. H. (2016). The scientist as illustrator. Trends in Immunology, 37(4), 247–250. https://doi.org/10.1016/j.it.2016.02.002
Karakaya, S.A. (2024). The role of artificial intelligence in botanical gardens: Enhancing plant identification. Düzce Üniversitesi Süs ve Tıbbi Bitkiler Botanik Bahçesi Dergisi, 3(2), 23–38. https://izlik.org/JA36HS94GF
Kusumawardani, S. S., Wulandari, D., Pannen, P., Ekadiyanto, F. A., Wiryana, I. M., Purwarianti, A., & Alfarozi, S. A. I. (2024). Panduan penggunaan Generative Artificial Intelligence (GenAI) pada pembelajaran di perguruan tinggi. Direktorat Pembelajaran dan Kemahasiswaan, Direktorat Jenderal Pendidikan Tinggi, Riset, dan Teknologi, Kementerian Pendidikan, Kebudayaan, Riset, dan Teknologi.
Li, T., & Wang, J. (2026). Application of AI-based Visualization Design for Flora and Fauna: A Case Study of the Giant Panda National Park. International Journal of Computational Intelligence Systems, 19(1), 155.
Melanitis, I. (2025). Art, AI, strategies of biomimicry: Mimiphenia, the ambivalent mimicry. Proceedings of the European Academy of Sciences and Arts, 4. https://doi.org/10.4081/peasa.47
Noel, G. P. J. C. (2024). Evaluating AI-powered text-to-image generators for anatomical illustration: A comparative study. Anatomical Sciences Education, 17(5), 979–983. https://doi.org/10.1002/ase.2336
Oksanen, A., Cvetkovic, A., Akin, N., Latikka, R., Bergdahl, J., Chen, Y., & Savela, N. (2023). Artificial intelligence in fine arts: A systematic review of empirical research. Computers in Human Behavior: Artificial Humans, 1(2), 100004. https://doi.org/10.1016/j.chbah.2023.100004
Oxley, V., & Bebbington, A. (2017). The role and value of botanical illustration today. Eryngium, 13, 3–9. https://www.iapi.org.uk/wp-content/uploads/2021/05/Oxley-Bebbington-2017-bot.-illustration.pdf
Peregrym, M., Kozak, O., Yaprak, A. E., Elliott, A., Schwartsburd, P. B., Abidkulova, K., Voytsekhovich, A., & Danylevska, O. (2026). Assessing ChatGPT for taxonomic and floristic studies. Nordic Journal of Botany, e05206. https://doi.org/10.1002/njb.05206
Petroff, D. J., Nasir, A. A., Moin, K. A., Loveless, B. A., Moshirfar, O. A., Hoopes, P. C., & Moshirfar, M. (2024). Evaluating the accuracy of artificial intelligence (AI)-generated illustrations for laser-assisted in situ keratomileusis (LASIK), photorefractive keratectomy (PRK), and small incision lenticule extraction (SMILE). Cureus, 16(8), e67747. https://doi.org/10.7759/cureus.67747
Ramdhan, M. (2021). Metode penelitian. Cipta Media Nusantara.
Rykaczewski, M. (2021). Illustration in scientific research. ACADEMIA: The Magazine of the Polish Academy of Sciences, (3), 55–59. https://doi.org/10.24425/academiaPAS.2021.139785
Scholten, J. (2025). Should AI replace field botanists? A case study assessing the accuracy of automated plant identification applications on plant species from New York State. Northeastern Naturalist, 32(1), 40–51. https://doi.org/10.1656/045.032.0103
Sikandar, A., & Bahar, H. M. (2024). A comparative analysis to assess anatomical illustrations via three AI-driven text-to-image generators. European Journal of Anatomy, 28(5), 631–634. https://doi.org/10.52083/DLQJ8889
Swann, W., & Pye, M. (2019). Botany through the looking glass: Cognitive neuroscience and its role in the use of art in botanical education. International Journal of Innovation in Science and Mathematics Education, 27(7), 10–22. https://doi.org/10.30722/IJISME.27.07.002
Temsah, M.-H., Alhuzaimi, A. N., Almansour, M., Aljamaan, F., Alhasan, K., Batarfi, M. A., Altamimi, I., Alharbi, A., Alsuhaibani, A. A., Alwakeel, L., Alzahrani, A. A., Alsulaim, K. B., Jamal, A., Khayat, A., Alghamdi, M. H., Halwani, R., Khan, M. K., Al-Eyadhy, A., & Nazer, R. (2024). Art or artifact: Evaluating the accuracy, appeal, and educational value of AI-generated imagery in DALL·E 3 for illustrating congenital heart diseases. Journal of Medical Systems, 48(1), 54. https://doi.org/10.1007/s10916-024-02072-0
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Vidya Kharishma, Missel Steffany Khan (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Articles published in Jurnal Desain are licensed under the Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0), unless otherwise indicated.
This license allows users to:
- Share: Copy and redistribute the material in any medium or format.
- Adapt: Remix, transform, and build upon the material.
These permissions apply for non-commercial purposes and are subject to the following terms:
1. Attribution (BY)
Users must give appropriate credit to the original author(s), acknowledge the article’s original publication in Jurnal Desain, provide a link to the CC BY-NC 4.0 license, and indicate if changes were made.
Attribution may be provided in any reasonable manner, but not in a way that suggests that the author(s) or Jurnal Desain endorse the user or the use of the material.
Where available, users are encouraged to include the article’s Digital Object Identifier (DOI) when citing or redistributing the work to ensure persistent identification of the Version of Record.
2. NonCommercial (NC)
The material may not be used for commercial purposes.
Commercial use refers to use that is primarily intended for or directed toward commercial advantage or monetary compensation.
Users wishing to make commercial use of material covered by the license must obtain separate permission from the relevant copyright holder(s).
3. No Additional Restrictions
Users may not apply legal terms or technological measures that legally restrict others from exercising any rights permitted by the license.
4. Third-Party Material
The CC BY-NC 4.0 license applies to the article unless otherwise indicated. Figures, photographs, artworks, illustrations, tables, data, or other third-party materials may be subject to separate copyright or licensing terms.
Users are responsible for determining whether separate permission is required before reusing material that is excluded from the article’s Creative Commons license.
Official License Terms
The complete terms of the license are available from the Creative Commons Attribution-NonCommercial 4.0 International License: https://creativecommons.org/licenses/by-nc/4.0/
