Fractal Dimension and K-Nearest Neighbor Analysis for Turtle Species Classification Based on Carapace Pattern Complexity

Nadya Nafis Kartosen, Dwi Juniati

Abstract


Accurate turtle species identification supports biodiversity monitoring and conservation. This study classified seven turtle species using box-counting fractal dimension a single scalar numerical feature and K-Nearest Neighbor (K-NN) based on carapace pattern complexity. A dataset of 140 dorsal carapace images (20 per species) was compiled from iNaturalist Research Grade observations via random sampling with rejection-based screening against predefined inclusion criteria. Images were preprocessed (crop, resize, Gaussian smoothing, grayscale, Otsu thresholding, Canny edge detection) prior to fractal-dimension extraction. Stratified 3-, 5-, 7-, and 10-fold cross-validation was repeated over ten fixed random seeds. The best-performing observed configuration (10-fold, K = 3) achieved 87.14% ± 0.48% accuracy and 86.75% pooled macro-F1. A dataset-matched GLCM baseline achieved 61.14% ± 1.76% accuracy under the same setting, with a highly significant paired difference (paired t-test, p < 0.001; Wilcoxon signed-rank, p = 0.001953).

Keywords


Box-Counting; Carapace Pattern; Fractal Dimension; K-Nearest Neighbor; Species Classification.

Full Text:

PDF

References


C. Chen, J. Wang, M. Holyoak, L. Lin, and Y. Wang, “Global assessment of current extinction risks and future challenges for turtles and tortoises,” Nature Communications 2025 16:1, vol. 16, no. 1, pp. 7114-, Aug. 2025, doi: 10.1038/s41467-025-62441-2.

N. Cox et al., “A global reptile assessment highlights shared conservation needs of tetrapods,” Nature 2022 605:7909, vol. 605, no. 7909, pp. 285–290, Apr. 2022, doi: 10.1038/s41586-022-04664-7.

V. Nijman and C. R. Shepherd, “Trade in Southeast Asian Box Turtles from Indonesia: Legality, Livelihoods, Sustainability and Overexploitation,” Diversity 2022, Vol. 14, Page 970, vol. 14, no. 11, p. 970, Nov. 2022, doi: 10.3390/D14110970.

V. Nijman and C. R. Shepherd, “Legal freshwater turtle meat trade in Indonesia only marginally contributes to collectors’ livelihoods,” Discover Animals 2025 2:1, vol. 2, no. 1, pp. 17-, Mar. 2025, doi: 10.1007/S44338-025-00062-1.

C. Y. Hau, W. K. Ngan, and Y. Sadovy de Mitcheson, “Leveraging artificial intelligence for photo identification to aid CITES enforcement in combating illegal trade of the endangered humphead wrasse (Cheilinus undulatus),” Front. Ecol. Evol., vol. 13, p. 1526661, Mar. 2025, doi: 10.3389/FEVO.2025.1526661/TEXT.

S. Su, D. Gu, J. Y. Lai, N. Arcilla, and T. Y. Su, “A novel deep learning-based bioacoustic approach for identification of look-alike white-eye (Zosterops) species traded in wildlife markets,” Ibis, vol. 167, no. 1, pp. 41–55, Jan. 2025, doi: 10.1111/IBI.13309;REQUESTEDJOURNAL:JOURNAL:1474919X;WGROUP:STRING:PUBLICATION.

E. Eravci Yalin et al., “Carapace Morphology Variations in Captive Tortoises: Insights from Three-Dimensional Analysis,” Animals 2024, Vol. 14, Page 2664, vol. 14, no. 18, p. 2664, Sep. 2024, doi: 10.3390/ANI14182664.

W. Songpan, T. Chaianunporn, K. Lomthaisong, and S. Keithmaleesatti, “Automated classification in turtles genus Malayemys using ensemble multiview image based on improved YOLOv8 with CNN,” Scientific Reports 2024 14:1, vol. 14, no. 1, pp. 24993-, Oct. 2024, doi: 10.1038/s41598-024-76431-9.

J. W. Baek, J. Il Kim, and C. B. Kim, “Deep learning-based image classification of turtles imported into Korea,” Scientific Reports 2023 13:1, vol. 13, no. 1, pp. 21677-, Dec. 2023, doi: 10.1038/s41598-023-49022-3.

R. Faurina, A. Wijanarko, A. F. Heryuanti, S. I. Ishak, and I. Agustian, “Comparative study of ensemble deep learning models to determine the classification of turtle species,” Computer Science and Information Technologies, vol. 4, no. 1, pp. 24–32, Mar. 2023, doi: 10.11591/CSIT.V4I1.P24-32.

S. Binta Islam, D. Valles, T. J. Hibbitts, W. A. Ryberg, D. K. Walkup, and M. R. J. Forstner, “Animal Species Recognition with Deep Convolutional Neural Networks from Ecological Camera Trap Images,” Animals 2023, Vol. 13, Page 1526, vol. 13, no. 9, p. 1526, May 2023, doi: 10.3390/ANI13091526.

K. Seljebotn and I. A. Lawal, “Machine Learning Tool for Wildlife Image Classification,” ACM International Conference Proceeding Series, pp. 127–132, May 2024, doi: 10.1145/3674029.3674050;CSUBTYPE:STRING:CONFERENCE.

K. Tabuki, H. Nishizawa, O. Abe, J. Okuyama, and S. Tanizaki, “Utility of carapace images for long-term photographic identification of nesting green turtles,” J. Exp. Mar. Biol. Ecol., vol. 545, p. 151632, Dec. 2021, doi: 10.1016/J.JEMBE.2021.151632.

R. W. Burroughs, J. F. Parham, B. L. Stuart, P. D. Smits, and K. D. Angielczyk, “Morphological Species Delimitation in The Western Pond Turtle (Actinemys): Can Machine Learning Methods Aid in Cryptic Species Identification?,” Integrative Organismal Biology, vol. 6, no. 1, Jan. 2024, doi: 10.1093/IOB/OBAE010.

W. Jiang, Y. Liu, J. Wang, R. Li, X. Liu, and J. Zhang, “Problems of the Grid Size Selection in Differential Box-Counting (DBC) Methods and an Improvement Strategy,” Entropy 2022, Vol. 24, Page 977, vol. 24, no. 7, p. 977, Jul. 2022, doi: 10.3390/E24070977.

V. Muraleedharan, S. C. Rajan, and J. R, “Determining the limits of traditional box-counting fractal analysis in leaf complexity studies,” Flora, vol. 304, p. 152300, Jul. 2023, doi: 10.1016/J.FLORA.2023.152300.

G. Taraschi and J. B. Florindo, “Computing fractal descriptors of texture images using sliding boxes: An application to the identification of Brazilian plant species,” Physica A: Statistical Mechanics and its Applications, vol. 545, p. 123651, May 2020, doi: 10.1016/J.PHYSA.2019.123651.

C. Khotimah and D. Juniati, “Iris Recognition Using Feature Extraction of Box Counting Fractal Dimension,” J. Phys. Conf. Ser., vol. 947, no. 1, p. 012004, Jan. 2018, doi: 10.1088/1742-6596/947/1/012004.

K. Mahapatra, S. R, K. Mahapatra, and S. R, “Fractal Dimension and Entropy Analysis of Medical Images for KNN-Based Disease Classification,” Baghdad Science Journal, vol. 22, no. 4, pp. 1354–1365, Apr. 2025, doi: 10.21123/bsj.2024.10835.

R. Padhy, S. K. Dash, A. Khandual, and J. Mishra, “Image classification in artificial neural network using fractal dimension,” International Journal of Information Technology 2023 15:6, vol. 15, no. 6, pp. 3003–3013, Jun. 2023, doi: 10.1007/S41870-023-01318-3.

P. Langley et al., “Fractal dimension to classify the heart sound recordings with KNN and fuzzy c-mean clustering methods,” J. Phys. Conf. Ser., vol. 953, no. 1, p. 012202, Jan. 2018, doi: 10.1088/1742-6596/953/1/012202.

N. Iqbal, R. Mumtaz, U. Shafi, and S. M. H. Zaidi, “Gray level co-occurrence matrix (GLCM) texture based crop classification using low altitude remote sensing platforms,” PeerJ Comput. Sci., vol. 7, pp. 1–26, May 2021, doi: 10.7717/PEERJ-CS.536/TABLE-21.

Kiswanto, H. Hadiyanto, and E. Sediyono, “Evaluation of Wavelet and Gray Level Co-Occurrence Matrix Combination Model for Texture Image Feature Extraction of Various Types of Meat,” Ingenierie des Systemes d’Information, vol. 30, no. 4, pp. 933–943, Apr. 2025, doi: 10.18280/ISI.300410.

T. M. Cover and P. E. Hart, “Nearest Neighbor Pattern Classification,” IEEE Trans. Inf. Theory, vol. 13, no. 1, pp. 21–27, 1967, doi: 10.1109/TIT.1967.1053964.

“Centrochelys sulcata: Petrozzi, F., Luiselli, L., Hema, E.M., Diagne, T., Segniagbeto, G.H., Eniang, E.A., Leuteritz, T.E.J. & Rhodin, A.G.J.,” IUCN Red List of Threatened Species, Aug. 2020, doi: 10.2305/IUCN.UK.2021-1.RLTS.T163423A1006958.EN.

“Checklist - Tortoise and Freshwater Turtle Specialist Group.” Accessed: Aug. 27, 2026. [Online]. Available: https://iucn-tftsg.org/checklists/

N. Otsu, “THRESHOLD SELECTION METHOD FROM GRAY-LEVEL HISTOGRAMS.,” IEEE Trans Syst Man Cybern, vol. SMC-9, no. 1, pp. 62–66, 1979, doi: 10.1109/TSMC.1979.4310076.

J. Canny, “A Computational Approach to Edge Detection,” IEEE Trans. Pattern Anal. Mach. Intell., vol. PAMI-8, no. 6, pp. 679–698, 1986, doi: 10.1109/TPAMI.1986.4767851.

D. Juniati and I. K. Budayasa, Geometri Fraktal dan Aplikasinya. Surabaya: Unesa University Press, 2016.

S. Prusty, S. Patnaik, and S. K. Dash, “SKCV: Stratified K-fold cross-validation on ML classifiers for predicting cervical cancer,” Frontiers in Nanotechnology, vol. 4, p. 972421, Aug. 2022, doi: 10.3389/FNANO.2022.972421/TEXT.

T. Abedin, H. Xu, and S. Uddin, “The impact of K selection in K fold cross-validation on bias and variance in supervised learning models,” Scientific Reports 2026 16:1, vol. 16, no. 1, pp. 6084-, Jan. 2026, doi: 10.1038/s41598-026-37247-x.

Nadyanafis, nadyanafis/Turtle-Fractal-Dimension-KNN: Initial release for journal submission. (Sep. 12, 2026). Zenodo. doi: 10.5281/zenodo.22725148.




DOI: http://dx.doi.org/10.30829/zero.v10i2.31716

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Contact & Indexing
ZERO: Jurnal Sains, Matematika dan Terapan
Editorial office
UIN Sumatera UtaraDepartment of Mathematics
Department of Mathematics
Faculty of Science and Technology
UIN Sumatera Utara Medan
Medan, North Sumatra, Indonesia
For authors
Contact
zero_journal@uinsu.ac.id
+62 852-7000-9767
WhatsApp · Admin official
ISSN 2580-5754 (Online) · 2580-569X (Print)   |   DOI 10.30829   |   SINTA 2 2024–2028
Open access under CC BY-SA 4.0  ·  © 2017–2026 Department of Mathematics, UIN Sumatera Utara Medan