Email this article 
Classification of Beef Quality Using the HSV Color Model on Digital Images with MATLAB Software
Abstract
Abstract—This study was motivated by the importance of objectively and non-destructively classifying beef quality in accordance with Indonesian National Standard 9226:2023. The objective of this study was to develop a MATLAB R2025B-based application to identify beef quality grades based on meat and fat color using Hue Saturation Value color space modeling. The research methodology involved the following stages: image acquisition, image cropping, contrast enhancement, extraction of Red Green Blue (RGB) values, conversion to Hue Saturation Value (HSV), determination of color standards, and quality classification using an IF-THEN-ELSE decision tree. The results showed that the Bokong beef sample was classified as Grade III, the Kelapa beef as Grade I, and the Khas Dalam beef as Grade II. For fat, the Kelapa sample was classified as Class 1 and the Khas Dalam sample as Class 2. The Hue-Saturation-Value color space model proved effective in consistently and objectively classifying beef quality. The implications of this research are to provide a tool for the livestock industry and consumers for efficient and accurate meat quality assessment, as well as to serve as a reference for the development of digital image processing applications in the future.
Keywords: Beef Classification, Hue-Saturation-Value Color Space, Digital Image Processing, Indonesian National Standard 9226:2023, MATLABFull Text:
PDFReferences
[1] National Standardization Agency. SNI 9226:2023 Beef/Buffalo Carcasses and Meat. Jakarta: BSN. 2023.
[2] Liao, L., Xie, Y., Hu, Z., Chen, Y., Xiong, B., & Xiao, X. Improving traceability and quality control in the red-meat industry through computer vision-driven physical meat feature tracking. Food Chemistry, vol. 480. https://doi.org/10.1016/j.foodchem.2025.143830, July 15,
2025.
[3] Lee, S., Lee, J., Choi, Y., & Jo, C. Classification of beef using artificial intelligence. Webology, 19 (1), 3581–3594. https://doi.org/10.14704/web/v19i1/web19308.
2022.
[4] Liu, Y., Zhang, Y., Wang, X., & Chen, L. Research on a beef marbling grading algorithm based on improved YOLOv8x. Foods, 14 (10), 1664. https://doi.org/10.3390/foods14101664, 2025.
[5] Lee, J., Choe, J., Jo, D., Jayasena, K., Kim, Y., & Park, B. MSENet: A marbling score estimation network for automated assessment of Korean beef. Meat Science, 188, 108784. https://doi.org/10.1016/j.meatsci.2022.108784. 2022.
[6] Cai, W., Huang, Y., Jiang, Y., & Lu, R. Beef marbling assessment by structured-illumination reflectance imaging with deep learning. Journal of Food Engineering, 367,111936. https://doi.org/10.1016/j.jfoodeng.2024.111936. 2024.
[7] Cardenas, A., Ramirez, J., & Gonzalez, R. An electronic device for marbling meat grade detection based on digital image processing and support vector machines. Journal of the Saudi Society of Agricultural Sciences, 23 (6), 389-398. https://doi.org/10.1016/j.jssas.2024.05.001.
2024.
[8] Geletu, U. S., Usmael, A., & Bari, K. A. Quality of cattle meat and its compositional constituents. Veterinary Medicine International, 2021, 7340495.
https://doi.org/10.1155/2021/7340495
[9] Campo, M. M., Santolaria, P., Sañudo, C., Olleta, J. L., Panea, B., Albertí, P., & Ripoll, M. Nutrient composition of beef from the Pyrenees. Journal of Food Composition and Analysis, 134, 106452. https://doi.org/10.1016/j.jfca 2024.106452ruary 2024.
[10] Mortensen, B. M., Buhler, J. L., Hodges, J. M., Duckett, S. K., & Underwood, K. R. Nutrient analysis of raw and cooked USDA Prime beef cuts. Nutrients, 16 (17), 2912.
https://doi.org/10.3390/nu16172912, 2024.
[11] Büyükarikan, B. ConvColor DL: Concatenated convolutional and hand-crafted color features fusion for beef quality identification. Food Chemistry, 458, 140795.
https://doi.org/10.1016/j.foodchem.2024.140795. 2024.
[12] Cardenas, A., Rodriguez, J., & Sanchez, M. An electronic device for marbling meat grade detection based on digital image processing and support vector machines. Journal of the Saudi Society of Agricultural Sciences, 23 (6), 412-423. https://doi.org/10.1016/j.jssas.2024.05.001.
2024.
[13] Cai, J., Zhang, Y., & Wang, L. Beef marbling assessment by structured-illumination reflectance imaging with deep learning. Journal of Food Engineering, 365, 111936.
https://doi.org/10.1016/j.jfoodeng.2024.111936. 2024.
[14] Liu, X., Chen, H., & Zhao, Y. Research on a beef marbling grading algorithm based on an improved YOLOv8x. Foods, 14 (10), 1664. https://doi.org/10.3390/foods14101664.
2025.
[15] Kiswanto, Budiman, A., & Hartono, S. Modification of the Haar wavelet algorithm for texture identification of meat types using machine learning. In Advances in Intelligent Systems and Computing (Vol. 1456, pp. 245–258). Springer. https://doi.org/10.1007/978-981-99-6547-
February 18, 2024.
[16] Kiswanto, Setiawan, R., & Prasetyo, D. Evaluation of a combined wavelet and gray-level co-occurrence matrix model for texture image feature extraction of various types of meat. Ingénierie des Systèmes d’Information, 30 (4), 1245–1258.
https://doi.org/10.18280/isi.300410, 2025.
[17] Anwar, S., Hassan, M., & Rahman, A. The identification of beef and pork using a neural network based on texture features. Journal of Engineering Research, 10 (3A), 156-168. https://doi.org/10.36909/jer.17983. 2022.
[18] Lee, S., Kim, J., & Park, H. MSENet: Marbling score estimation network for automated assessment of Korean beef. Meat Science, 194, 108784. https://doi.org/10.1016/j.meatsci 2022.108784, 2022.
[19] Zhu, Y., Chen, L., & Wang, X. Computer vision-based beef grading for marbling using the RGB-HSV color model and Python software. In Proc. Int. Symp. on Power, Control, Electronics and Materials (pp. 542–547). IEEE. https://doi.org/10.1109/ispcem60569.2023.00115. 2023.
[20] Zhang, W., Liu, Q., & Yang, J. Grade-Mamba: Efficient visual representation learning for beef carcass classification of brown cattle. Research Square [Preprint]. https://doi.org/10.21203/rs.3.rs-7663462/v1. 2025.
[21] Sujana, A., Kurniawan, I., & Hidayat, R. Classification of tuna meat quality grades based on color space using the wavelet and k-Nearest Neighbor algorithms. In Proceedings of the International Conference on Smart Grid, Technology, Energy, and Information Systems (pp. 1–6). IEEE.
https://doi.org/10.1109/icsgteis60500.2023.10424189. 2023.
[22] Mulyana, A., Santoso, B., & Wijaya, D. The effectiveness of using the HSV color space for classifying fresh and spoiled beef in the food industry. JTIK Journal (Journal of Information and Communication Technology), 9 (1), 45–58. https://doi.org/10.35870/jtik.v9i1.3129. 2024.
[23] Wang, H., Chen, Y., & Liu, Z. A value mapping virtual staining framework for large-scale histological imaging. arXivpreprint, arXiv:2501.03592. https://doi.org/10.48550/arxiv.2501.03592. 2025.
[24] Tjandra, A., Setiawan, R., & Kusuma, M. Trigit: A free web application for rapid colorimetric analysis of images. Biosensors and Bioelectronics: X, 13, 100361.
https://doi.org/10.1016/j.biosx.2023.100361, 2023.
[25] Pérez-Palacios, T., Antequera, M., & Durán, R. Texture analysis and machine learning on MRI for the quality evaluation of meat products. In Advanced Imaging Techniques in Meat Science (pp. 189–215). CRC Press. https://doi.org/10.1201/9780367486099-10, 2024.
DOI: https://doi.org/10.18860/mat.v18i2.41670
Refbacks
- There are currently no refbacks.
Copyright (c) 2026 Merlin Diana
License URL: http://creativecommons.org/licenses/by-sa/4.0/
The journal is indexed by :
_______________________________________________________________________________________________________________
Editorial Office:
The Informatics Engineering Study Program
Faculty of Science and Technology
Universitas Islam Negeri Maulana Malik Ibrahim Malang
Jalan Gajayana 50 Malang, Jawa Timur, Indonesia 65144
Email: matics@uin-malang.ac.id
_______________________________________________________________________________________________________________
MATICS: Jurnal Ilmu Komputer dan Teknologi Informasi is licensed under a CC-BY-SA 4.0
ISSN : 1978-161X | e-ISSN : 2477-2550