A Computer Vision Approach for Bali Cattle Morphometric Measurement Using Multi-Threshold Segmentation and FIS–CF-Based Classification
DOI:
https://doi.org/10.15408/jti.v19i1.47324Keywords:
Cattle morphometrics, Bali cattle, computer vision, digital image processing, live weight estimation, livestock managementAbstract
Manual morphometric measurement of livestock is time-consuming, stressful to animals, and poses safety risks to handlers. This study presents a computer vision-based system for automatically measuring three key morphometric parameters of Bali cattle—withers height (WH), body length (BL), and chest girth (CG)—in accordance with the Indonesian National Standard (SNI). Images were captured from side and rear perspectives and processed using threshold-based image segmentation in the HSV color space to isolate the cattle contour. Pixel-to-centimeter calibration was performed using a fixed reference marker placed at a known distance of 1.5–2.0 m from the camera. The extracted morphometric values were subsequently fed into a Fuzzy Inference System with Certainty Factor (FIS-CF) for cattle grading and classification. Threshold values ranging from 0.5 to 0.9 were evaluated against manual ground-truth measurements using MAE, RMSE, MAPE, and R². The optimal threshold of 0.9 achieved MAPE values of 9.85% (WH), 6.04% (BL), and 11.49% (CG), representing up to 52% improvement over the lowest threshold. Although R² values remain negative due to limited sample size and non-linear pixel-to-metric variance, a consistent upward trend toward zero confirms measurement improvement with higher thresholds. The proposed method offers a practical, non-invasive alternative to manual measurement, with potential application in precision livestock farming and automated cattle grading systems.
References
[1] Sukoco H, Muladno, and Arnaldy D, “Livestock Smallholder Empowerment System based on Digital Technology and Internet of Things for Livestock Smallholder Communities in Indonesia,” in The 2022 LRI-FRI-IPB-FFTC Joint International Symposium on Intelligent Production of Livestock Industry and Aquaculture, Taiwan: Food and Fertilizer Technology Center , 2022.
[2] A. Irianto, A. Gunawan, and Muladno, “Genetic Quality Improvement Through Livestock Grading System to Support a Digitally-Based Breeding Program,” Jurnal Ilmu dan Teknologi Peternakan Tropis, vol. 7, no. 1, p. 29, Jan. 2020, doi: 10.33772/jitro.v7i1.8907.
[3] A. Ramadhan, A. M. Arymurthy, D. I. Sensuse, and Muladno, “Modeling e-Livestock Indonesia,” Heliyon, vol. 7, no. 8, Aug. 2021, doi: 10.1016/j.heliyon.2021.e07754.
[4] Mahendra VY, A. Riadi, and Evanita, “Digital Image Processing Application for Determining Cattle Weight Using the Center of Gravity Method Based on Android,” Jurnal Riset Sistem Informasi Dan Teknik Informatika (JURASIK), vol. 7, no. 1, pp. 88–94, 2022, doi: http://dx.doi.org/10.30645/jurasik.v7i1.
[5] F. Ariadi, B. B. Minto, and M. Jasa Afroni, “Pengolahan Citra Digital Untuk Pengukuran Morfometrik pada Sapi Potong Lokal Berbasis Android,” Science Electro, vol. 14, no. 2, 2022.
[6] [BPS] and Badan Pusat Statistik, “Statistik Perusahaan Peternakan Ternak Besar dan Ternak Kecil 2018,” Jakarta, 2018.
[7] Rahmat and W. Prasetya, Kupas Tuntas Beternak Sapi Potong, 1st ed. Depok: Penebar Swadaya, 2022.
[8] D. Arnaldy, H. Sukoco, S. N. Neyman, Muladno, and K. B. Seminar, “Cattle Breeding Management using Smart System: A Systematic Literature Review,” in 2022 5th International Conference of Computer and Informatics Engineering (IC2IE), IEEE, Sep. 2022, pp. 10–16. doi: 10.1109/IC2IE56416.2022.9970169.
[9] H. Afridi et al., “Analyzing Data Modalities for Cattle Weight Estimation Using Deep Learning Models,” J. Imaging, vol. 10, no. 3, Mar. 2024, doi: 10.3390/jimaging10030072.
[10] S. Washaya, W. Bvirwa, and G. Nyamushamba, “Use of Body Linear Measurements to Estimate Live Weight in Communal Beef Cattle,” Journal of Environmental and Agricultural Studies, vol. 2, no. 2, pp. 11–20, Oct. 2021, doi: 10.32996/jeas.2021.2.2.2.
[11] M. Tscharke and T. Banhazi, “Review of Methods to Determine Weight and Size of Livestock from Images,” Australian Journal of Multi-Disciplinary Engineering, vol. 10, pp. 1–17, Nov. 2015, doi: 10.7158/14488388.2013.11464860.
[12] D. Arnaldy, K. B. Seminar, S. N. Neyman, H. Sukoco, and Muladno, “A Novel Approach for Bali Cattle Classification: Integrating the Fuzzy Inference System with Certainty Factor and Morphometric Parameters,” JOIV : International Journal on Informatics Visualization, vol. 9, no. 4, p. 1602, Jul. 2025, doi: 10.62527/joiv.9.4.3218.
[13] A. Johar, A. Vatresia, and R. Faurina, “Pengolahan Citra Digital Untuk Penentuan Bobot Sapi Mengunakan Metode Sobel,” vol. 12, no. 2, 2022, [Online]. Available: https://jurnal.umj.ac.id/index.php/just-it/index
[14] A. Hakim, H. Nuraini, R. Priyanto, and T. Harsi, “Dimensi Tubuh Sapi Friesian Holstein dan Limousin Betina Berdasarkan Morfometrik dengan Citra Digital,” Jurnal Ilmu Produksi dan Teknologi Hasil Peternakan, vol. 7, no. 2, pp. 47–56, Jul. 2019, doi: 10.29244/jipthp.7.2.47-56.
[15] I. Supiyani, J. Haerul, and T. N. Padilah, “Pengolahan Citra Digital Prediksi Bobot Sapi Menggunakan Ekstraksi Fitur Canny Dan Klasifikasi K-Nearest Neighbor,” NUSANTARA: Jurnal Ilmu Pengetahuan Sosial , vol. 8, no. 7, pp. 2204–2212, 2021, doi: 10.31604/jips.v8i7.2021.2204-2212.
[16] E. Constantia, I. Bambang Hidayat, and M. W. Fatah, “Beef Cattle Weight Estimation Based On Digital Image Registration With Geometric Active Contour Method And Decision Tree Classification,” in e-Proceeding of Engineering, Apr. 2019, pp. 705–711.
[17] Ashari, N. Latif, and A. Astuti, “Pengolahan Citra Digital Untuk Menentukan Bobot Sapi Menggunakan Metode Canny Edge Detection,” Jurnal Ilmiah Ilmu Komputer, vol. 5, no. 1, 2019, [Online]. Available: http://ejournal.fikom-unasman.ac.id
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Defiana Arnaldy, Kudang Boro Seminar, Muladno, Heru Sukoco, Shelvie Nidya Neyman
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
