ANALISIS PERBEDAAN SPEKTRUM WARNA MULTI-CHANNEL UNTUK DETEKSI TINGKAT KESEGARAN DAGING MENGGUNAKAN COLOR-SPACE FUSION

Fahmi Fauzia Al Malik; Dian Ade Kurnia; Yudhistira Arie Wijaya; Ahmad Rifa'i; Dodi Solihudin

Authors

Fahmi Fauzia Al Malik STMIK IKMI Cirebon, Indonesia
Dian Ade Kurnia STMIK IKMI Cirebon, Indonesia
Yudhistira Arie Wijaya STMIK IKMI Cirebon, Indonesia
Ahmad Rifa'i STMIK IKMI Cirebon, Indonesia
Dodi Solihudin STMIK IKMI Cirebon, Indonesia

Keywords:

kesegaran daging, color-space fusion, spektrum warna, klasifikasi citra, SVM

Abstract

-Penelitian ini bertujuan mengembangkan sistem klasifikasi kesegaran daging berbasis citra menggunakan pendekatan multi-channel color-space fusion. Penelitian ini memanfaatkan fitur statistik warna dari ruang warna RGB, HSV, Lab, dan YCrCb, kemudian menguji efektivitasnya dalam mendeteksi tingkat kesegaran daging secara non-destruktif melalui model Support Vector Machine. Metode yang digunakan bersifat kuantitatif eksperimental dengan tahapan akuisisi citra, eksplorasi visual, transformasi ruang warna, ekstraksi fitur, normalisasi, dan evaluasi klasifikasi. Hasil penelitian menunjukkan bahwa ruang warna Lab memberikan kontribusi signifikan terhadap keterpisahan visual antar kelas, sedangkan fusi fitur dari empat ruang warna menghasilkan representasi yang lebih informatif bagi model. Model SVM mencapai akurasi 88,43% dengan F1-Score tertinggi 0,96 pada kelas Busuk, menandakan kemampuan model dalam mengenali pola perubahan warna yang menjadi indikator kesegaran. Penelitian ini menegaskan bahwa pendekatan multi-channel color-space fusion efektif untuk klasifikasi kesegaran daging serta dapat menjadi dasar bagi pengembangan sistem inspeksi otomatis dalam industri pangan. Temuan ini membuka peluang penerapan metode serupa pada produk pangan lain yang bergantung pada perubahan warna sebagai indikator kualitas.

References

Alvarez-García, W. Y., Mendoza, L., Muñoz-Vílchez, Y., Nuñez-Melgar, D. C., & Quilcate, C. (2024). Implementing artificial intelligence to measure meat quality parameters in local market traceability processes. In International Journal of Food Science and Technology (Vol. 59, Issue 11, pp. 8058–8068). John Wiley and Sons Inc. https://doi.org/10.1111/ijfs.17546

Alvarez‑García, Y., W., Gómez‑Calcagno, A., García‑Mora, &, & E. (2024). Implementing artificial intelligence to measure meat quality: Trends and challenges. International Journal of Food Science & Technology, 59(11), Artikel 8058. https://doi.org/https://doi.org/10.1111/1750‑3841.7933044

Boruczkowska, H., Boruczkowski, T., Bronkowska, M., Prajzner, M., & Rytel, E. (2025). Comparison of colour measurement methods in the food industry. Processes, 13(5), 1268. https://doi.org/10.3390/pr13051268

Bu, Y., Hu, J., Chen, C., Bai, S., Chen, Z., Hu, T., Zhang, G., Liu, N., Cai, C., Li, Y., Xuan, Q., Wang, Y., Su, Z., & Xiang, Y. (2023). ResNet incorporating the fusion data of RGB & hyperspectral images improves classification accuracy of vegetable soybean freshness. Scientific Reports, 14, 51668. https://doi.org/10.1038/s41598-024-51668-6

Büyükarıkan, B. (n.d.). ConvColor DL: Concatenated convolutional and handcrafted colour feature extraction for beef quality classification. Food Research International, 172, 112814. https://doi.org/10.1016/j.foodres.2023.112814

Büyükarıkan, B., Tuncer, S. A., Özyurt, F., & Koçak, H. (2024). ConvColorDL: Concatenated convolutional and handcrafted colour-space features for beef quality classification. Food Research International, 179, 114456. https://doi.org/10.1016/j.foodres.2024.114456

Chomicki, A. (2025). Assessing the impact of dataset quality on the performance of machine learning classification tasks. Procedia Computer Science, 223, 187–195. https://doi.org/10.1016/j.procs.2025.03.031

Dalakleidi, K. V, Vlachos, K. A., & Tzovaras, D. (2022). Applying image-based food-recognition systems on mobile devices: A review. Smart Health, 24, 100293. https://doi.org/10.1016/j.smhl.2022.100293

Elangovan, P., Balasubramanian, V., & Vijayalakshmi, S. (2024). A novel approach for meat quality assessment using an ensemble framework of shallow convolutional neural networks. Applied Sciences, 14(14), 5979. https://doi.org/10.3390/app14145979

Feng, Y., Zhang, Y., Shi, H., & Wang, Y. (2024). Machine learning supported ground beef freshness detection via data fusion of near-infrared spectroscopy and paper chromogenic array. Food and Bioprocess Technology. https://doi.org/10.1002/fft2.438

Gong, Y., Huang, Z., & Liu, F. (2023). A survey on dataset quality in machine learning. Information and Software Technology, 150, 107236. https://doi.org/10.1016/j.infsof.2023.107236

Han, W., Hu, C., & Zhang, Y. (n.d.). SVM classification method of meat freshness based on QPSO. Computers and Electronics in Agriculture, 216, 108390. https://doi.org/10.1016/j.compag.2023.108390

Han, W., Hu, C., & Zhang, Y. (2024). SVM classification method of meat freshness based on QPSO. Computers and Electronics in Agriculture, 216, 108390. https://doi.org/10.1016/j.compag.2023.108390

Hoang, P.-H., Tran, N.-H., & Luu, T.-D. (2025). Enhanced Fish Freshness Classification with Incremental Handcrafted Feature Fusion. Artificial Intelligence in Agriculture, 5, 1–11. https://doi.org/10.1016/j.aiia.2025.10.003

Huang, X. (2024). Research progress on machine learning and computer vision in food quality assessment. Food Science, 45(4), 239–251. https://doi.org/10.7506/spkx1002-6630-20240131-284

Jeong, K., Jo, G., Lee, J. H., Kim, B., Choi, J., Oh, H., & Lee, E. (2025). Artificial intelligence in meat processing: A comprehensive review of data driven applications and future directions. Meat and Muscle Biology, 9(1), 20157. https://doi.org/10.22175/mmb.20157

King, D. A. (2023). American Meat Science Association guidelines for meat colour evaluation. Meat and Muscle Biology. https://doi.org/10.3168/mmb.2023-12473

Kurade, C. (2023). An automated image processing module for quality assessment of rice grains using machine learning. Foods, 12(6). https://doi.org/10.3390/foods12061273

Lhermitte, E., Bertaux, N., & Dupont, S. (2022). Deep learning and entropy-based texture features for image classification: Mean and standard-deviation normalization. Entropy, 24(11). https://doi.org/10.3390/e24111577

Liakos, K. G., Balafoutis, A., Bochtis, D., & Papageorgiou, E. (2025). Machine learning for quality control in the food industry. Foods, 14(19), 3424. https://doi.org/10.3390/foods14193424

Luo, D., Zhang, M., & Zhu, J. (2024). Quality detection and grading of peach fruit based on color, size and texture features. Frontiers in Plant Science, 15, 141509. https://doi.org/10.3389/fpls.2024.141509

Ma, W., Zhang, B., Xu, T., & Fan, C. (2023). Multiple Kernel-Based SVM Classification of Hyperspectral Images by Combining Spectral, Spatial, and Semantic Information. Remote Sensing, 15(1), 120. https://doi.org/10.3390/rs15010120

Medeiros, E. C., Oliveira, L. S., Britto, A. S., & Koerich, A. L. (2021). Computer vision and machine learning for tuna and beef quality classification. Information Processing in Agriculture, 8(4), 70–81. https://doi.org/10.3390/ipa8040070

Meenu, M. (2021). A concise review on food quality assessment using digital image processing. Trends in Food Science & Technology, 112, 412–422. https://doi.org/10.1016/j.tifs.2021.04.021

Mehdizadeh, S. A., Ghaffari, H., & Dehghan, S. (2025). AI-driven non-destructive detection of meat freshness using sensor arrays and machine learning algorithms. Food Bioscience, 59, 103665. https://doi.org/10.1016/j.fbio.2024.103665

Modzelewska-Kapituła, M., & Jun, S. (n.d.). The application of computer vision systems in meat science and industry – A review. Meat Science, 192, 108904. https://doi.org/10.1016/j.meatsci.2022.108904

Modzelewska-Kapituła, M., & Jun, S. (2022). The application of computer vision systems in meat science and industry – A review. Meat Science, 192, 108904. https://doi.org/10.1016/j.meatsci.2022.108904

Niu, W., Zhang, B., Chen, Q., Sun, T., & Wang, Y. (2024). Review of the deep learning for food image processing. International Journal of Agricultural and Biological Engineering, 17(5), 15–30. https://doi.org/10.25165/j.ijabe.20241705.8975

Olakanmi, S. J., Olaniyi, O. W., & Ojo, A. (2023). Applications of imaging systems for the assessment of quality attributes in foods. Comprehensive Reviews in Food Science and Food Safety, 22(4), 1570–1589. https://doi.org/10.1111/1541-4337.13131

risssssss. (n.d.). TY - JOUR%0AAU - Boruczkowska, H.%0AAU - Boruczkowski, T.%0AAU - Bronkowska, M.%0AAU - Prajzner, M.%0AAU - Rytel, E.%0APY - 2025%0ATI - Comparison of colour measurement methods in the food industry%0AJO - Processes%0AVL - 13%0AIS - 5%0ASP - 1268%0ADO - 10

Ruedt, C. (2023). Meat colour and iridescence: Origin, analysis, and approaches. Comprehensive Reviews in Food Science and Food Safety. https://doi.org/10.1111/1541-4337.13191

Sánchez, C. N., Orvañanos Guerrero, M. T., Domínguez Soberanes, J., & Álvarez Cisneros, Y. M. (2023a). Analysis of beef quality according to colour changes using computer vision and white box machine learning techniques. Heliyon, 9(7). https://doi.org/10.1016/j.heliyon.2023.e17976

Sánchez, C. N., Orvañanos Guerrero, M. T., Domínguez Soberanes, J., & Álvarez Cisneros, Y. M. (2023b). Analysis of beef quality according to colour changes using computer vision and white box machine learning techniques. Heliyon, 9(7), 17976. https://doi.org/10.1016/j.heliyon.2023.e17976

Shtepliuk, I., Domènech Gil, G., Almqvist, V., Kautto, A. H., Vågsholm, I., Boqvist, S., & Puglisi, D. (2025). Electronic nose and machine learning for modern meat inspection. Journal of Big Data, 12, 96. https://doi.org/10.1186/s40537

Simović, P., Ristić, S., & Petrović, M. (2024). The effects of data quality on deep learning performance in biological image recognition. Water, 17(1), 21. https://doi.org/10.3390/w17010021

Tahir, G. A. (2024). A comprehensive survey of image based food recognition and volume estimation. Foods, 10(9), 2125. https://doi.org/10.3390/foods10092125

Tan, K., Li, S., Wang, S., & Li, C. (2022). Classification of Hyperspectral Images by SVM Using a Composite Kernel by Employing Spectral, Spatial and Hierarchical Structure Information. Remote Sensing, 14(8). https://doi.org/10.3390/rs14081832

Tomasevic, I., Zdolec, N., Krocko, M., Skunca, D., & Aleksic, N. (2021). Recent advances in meat color research: Integrating traditional and high-throughput approaches. Meat Science, 181, 108695. https://doi.org/10.1016/j.meatsci.2021.108695

Wang, C., Zhang, X., Lv, Y., & Liu, Z. (2024). Deep Learning-Based Visual Quality Assessment of Agricultural Products: A Comprehensive Review. Computers and Electronics in Agriculture, 216, 108420. https://doi.org/10.1016/j.compag.2023.108420

Wu, X., Liang, X., Wang, Y., Wu, B., & Sun, J. (n.d.). Non-destructive techniques for the analysis and inspection of meat quality: A review. Foods, 11(22), 3713. https://doi.org/10.3390/foods11223713

Xiao, Z., Wang, J., Han, L., Guo, S., & Cui, Q. (2022). Application of machine vision system in food detection. Frontiers in Nutrition, 9, 888245. https://doi.org/10.3389/fnut.2022.888245

Xiao, Z., Wang, J., Han, L., Guo, S., & Cui, Q. (2024). Application of machine vision system in food detection. Frontiers in Nutrition, 9, 888245. https://doi.org/10.3389/fnut.2022.888245

Xu, W. (2024). Non-destructive detection of beef freshness based on optimized colour components. Journal of Food Engineering, 321, 110963. https://doi.org/10.1016/j.jfoodeng.2022.110963

Xu, Z., Chen, S., Zhao, D., Yao, H., Hao, J., & Bai, Y. (n.d.). Non-destructive detection of chilled meat quality based on hyperspectral technology combined with different data processing methods. Frontiers in Nutrition, 12, 1623671. https://doi.org/10.3389/fnut.2025.1623671

Xu, Z., Han, Y., Chen, S., Zhao, D., Yao, H., Hao, J., Li, J., Li, K., Li, S., & Bai, Y. (2024). Research on non destructive detection of chilled meat quality based on hyperspectral technology combined with different data processing methods. Frontiers in Nutrition, 12, 1623671. https://doi.org/10.3389/fnut.2025.1623671

Xu, Z., Han, Y., Zhao, D., Li, K., Li, J., Dong, J., Shi, W., Zhao, H., & Bai, Y. (2024a). Research progress on quality detection of livestock and poultry meat based on machine vision, hyperspectral and multi-source information fusion technologies. Foods, 13(3), 469. https://doi.org/10.3390/foods13030469

Xu, Z., Han, Y., Zhao, D., Li, K., Li, J., Dong, J., Shi, W., Zhao, H., & Bai, Y. (2024b). Research progress on quality detection of livestock and poultry meat based on machine vision, hyperspectral and multi source information fusion technologies. Foods, 13(3), 469. https://doi.org/10.3390/foods13030469

Zhang, J., Zhang, S., Liu, C., & Li, Q. (n.d.). Hyperspectral Image Classification Based on Adaptive Weighting Multiple Kernel Support Vector Machine. IEEE Transactions on Geoscience and Remote Sensing, 59(6), 5035–5048. https://doi.org/10.1109/TGRS.2020.3015525

Zhang, J., Zhang, S., Liu, C., & Li, Q. (2021). Hyperspectral Image Classification Based on Adaptive Weighting Multiple Kernel Support Vector Machine. IEEE Transactions on Geoscience and Remote Sensing, 59(6), 5035–5048. https://doi.org/10.1109/TGRS.2020.3015525

Zhang, J., Zhang, S., Liu, C., & Li, Q. (2022). Hyperspectral Image Classification Based on Adaptive Weighting Multiple Kernel Support Vector Machine. IEEE Transactions on Geoscience and Remote Sensing, 59(6), 5035–5048. https://doi.org/10.1109/TGRS.2020.3015525

Zou, X. G., Xin, C. R., Wang, C. Y., Li, Y. H., Wang, S. C., & Zhang, W. T. (2024). Non-destructive detection of chicken freshness based on multiple-feature image fusion and support vector machine. International Journal of Agricultural and Biological Engineering, 17(6), 264–272. https://doi.org/10.25165/j.ijabe.20241706.8783