Koi Fish Species Classification Based on Image Using YOLOv3-Tiny and OpenCV Methods
DOI:
https://doi.org/10.51179/ilka.v3i1.52Keywords:
Koi Fish, Object Detection, YOLOv3-Tiny, Deep Learning, Computer VisionAbstract
Identification of koi fish (Cyprinus carpio) varieties in aquaculture and ornamental fish industries is commonly performed manually through visual observation, making the process subjective, inconsistent, and inefficient, particularly at large production scales. This study aims to develop an automated image-based detection and classification system for koi varieties using the YOLOv3-Tiny algorithm integrated with OpenCV, capable of operating in real-time conditions. The dataset consists of 3,154 images of six koi varieties—Asagi, Bekko, Hikarimono, Kohaku, Sanke, and Showa—which were expanded to 6,360 images through data augmentation techniques. Image labeling and annotation were conducted using Roboflow, while model training was implemented with the Darknet framework in a Google Colab environment supported by GPU acceleration. System performance was evaluated using mean Average Precision (mAP), loss function analysis, and both static image and real-time video testing. Experimental results demonstrate that the YOLOv3-Tiny model is capable of accurately detecting and classifying koi varieties with stable inference speed suitable for real-time applications. The proposed system enhances objectivity, consistency, and efficiency in koi variety identification and shows strong potential for practical implementation in technology-driven ornamental fish farming and trading industries
Downloads
References
[1] G. M. Aqshal and D. D. Hutagalung, “Klasifikasi Jenis Ikan Koi Menggunakan Ekstraksi Warna HSV dan Metode Adaptive Neuro-Fuzzy Inference System (ANFIS),” Jurnal ICT : Information Communication & Technology, vol. 23, no. 2, pp. 1–8, 2023, doi: 10.36054/jict-ikmi.v23i2.172.
[2] I. R. Muslem and T. M. Johan, “KLIK: Kajian Ilmiah Informatika dan Komputer Klasifikasi Citra Ikan Menggunakan Algoritma Convolutional Neural Network dengan Arsitektur VGG-16,” Media Online), vol. 4, no. 2, pp. 978–985, 2023, doi: 10.30865/klik.v4i2.1209.
[3] I. A. Iswanto and S. H. Almukhlish, “Automatic Koi Grading System using Image Processing and Support Vector Machine,” in 2020 International Conference on Computer Engineering, Network, and Intelligent Multimedia (CENIM), 2020, pp. 107–111. doi: 10.1109/CENIM51130.2020.9297943.
[4] KKP, “KKP Ajak Para Breeder Hasilkan Ikan Koi Kualitas Ekspor. Website:” [Online]. Available: https://ppid.kkp.go.id/upp/direktorat-jenderal-perikanan-budi-daya/news/detail/kkp-ajak-para-breeder-hasilkan-ikan-koi-kualitas-ekspor/
[5] BPS, “Statistik Ekspor Ikan Hias Indonesia. Website:,” Jakarta, 2025.
[6] A. L. Syafei, A. Sajiah, and T. W. Purboyo, “Koi Fish Detection and Classification System using YOLO Algorithm,” International Journal of Applied Engineering Research, vol. 17, no. 1, pp. 55–61, 2022.
[7] J. Zhao, S. Zhang, J. Liu, and H. Wang, “Application of Deep Learning in Fish Classification and Breeding: A Review,” Aquaculture, vol. 535, p. 736356, 2021, doi: 10.1016/j.aquaculture.2021.736356.
[8] D. Armiady and I. M. R, “Klasifikasi Kualitas Buah Pisang Berdasarkan Citra Buah Menggunakan Stochastic Gradient Descent,” KLIK: Kajian Ilmiah Informatika dan Komputer, vol. 4, no. 2, 2023.
[9] C. H. H. Jannah, I. Muslem, and D. Azmi, “Jurnal Ilmu Komputer Aceh Klasifikasi Plat Nomor Kenderaan Bedasarkan Wilayah Tertentu Menggunakan Algoritma Optical Character Recognition,” Jurnal Ilmu Komputer Aceh, Oct. 2025, [Online]. Available: https://jurnal.fikompublisher.com/ilka/article/view/16
[10] I. Muslem, I. Irvanizam, A. Almuzammil, and F. Johar, “Adaptive Heuristic-Based Ant Colony Optimization for Multi-Constraint University Course Timetabling with Morning Slot Preference for Energy Efficiency,” Jurnal Teknik Informatika (Jutif), vol. 6, no. 6, pp. 5930–5943, Jan. 2026, doi: 10.52436/1.jutif.2025.6.6.5588.
[11] X. Yang, S. Zhang, J. Liu, Q. Gao, S. Dong, and C. Zhou, “Deep learning for smart fish farming: applications, opportunities and challenges,” Reviews in Aquaculture, vol. 13, no. 1, pp. 66–90, 2021, doi: 10.1111/raq.12462.
[12] I. V. S. L. Haritha, M. Harshini, S. Patil, and J. Philip, “Real Time Object Detection using YOLO Algorithm,” in 2022 6th International Conference on Electronics, Communication and Aerospace Technology, 2022, pp. 1465–1468. doi: 10.1109/ICECA55336.2022.10009184.
[13] Z. Jiang, L. Zhao, S. Li, and Y. Jia, “Real-time object detection method based on improved YOLOv3-tiny,” IEEE Access, vol. 8, pp. 184535–184545, 2020, doi: 10.1109/ACCESS.2020.3030217.
[14] K. M. Knausgård, N. Wiker, and T. Andersen, “Temperate Fish Detection and Classification: a Deep Learning based Approach,” Applied Intelligence, vol. 52, pp. 6988–7001, 2022, doi: 10.1007/s10489-020-02154-9.
[15] L. Luthfi, R. I. Muslem, D. Armiady, S. Sriwinar, R. Fajri, and I. Iqbal, “Analysis of CNN Method for Image Classification of Coconut Ripeness Levels,” in 2023 Eighth International Conference on Informatics and Computing (ICIC), 2023, pp. 1–6. doi: 10.1109/ICIC60109.2023.10381964.
Downloads
Published
How to Cite
Issue
Section
Categories
License
Copyright (c) 2026 Aceh Journal of Computer Science
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
This journal is an open access journal that provides direct, barrier-free national access to the full text of all published articles without any cost to readers or their institutions. Readers are entitled to read, download, copy, distribute, print, search, or link to the full text of all articles in the ILKA Journal. This journal provides open access to its content on the principle that making research freely available to the public supports greater global knowledge exchange.
