Deteksi Kesegaran Daging Sapi Menggunakan Augmentasi Data Mosaic pada Model YOLOv5sM
DOI:
https://doi.org/10.30595/jrst.v9i1.24990Keywords:
Daging Sapi, Flip, Rotation, Mosaic, YOLOv5sMAbstract
Deteksi kesegaran daging sapi secara otomatis sangat penting dalam mendukung kualitas bahan pangan, terutama dalam mencegah konsumsi daging yang sudah tidak layak dan berisiko terhadap kesehatan. Metode manual yang saat ini umum digunakan bersifat subjektif, lambat, dan tidak efisien jika diterapkan pada skala industri. Oleh karena itu, diperlukan pendekatan berbasis kecerdasan buatan yang mampu melakukan deteksi secara cepat dan akurat. Penelitian ini mengusulkan model deteksi kesegaran daging sapi menggunakan YOLOv5sM, yaitu modifikasi dari YOLOv5s yang menggabungkan teknik augmentasi data Flip, Rotation, dan Mosaic. Dataset yang digunakan terdiri dari 4.000 citra daging sapi, terbagi menjadi 2.000 citra daging segar dan 2.000 citra daging tidak segar. Data kemudian dibagi menjadi data pelatihan, validasi, dan pengujian. Tiga model dikembangkan: model YOLOv5s tanpa augmentasi, model dengan Flip dan Rotation, serta model YOLOv5sM dengan tambahan Mosaic. Hasil penelitian menunjukkan bahwa YOLOv5sM menghasilkan kinerja terbaik dengan Precision dan Recall sebesar 100%, mAP50 sebesar 99,5%, dan mAP50:95 sebesar 96,2%. Hal ini menunjukkan peningkatan signifikan dibanding dua model lainnya. Dengan hasil tersebut, model YOLOv5sM memiliki potensi besar untuk diimplementasikan sebagai sistem pendeteksi kesegaran daging sapi dalam industri pengolahan pangan yang membutuhkan efisiensi dan keakuratan tinggi.
References
Asfiyatus Sholikhah, R. K. D. (2022). Peranan Protein Hewani dalam Mencegah Stunting pada Anak Balita. Jurnal Riset Sains Dan Teknologi, 6(1), 95–100.
Bahadur, T., Neupane, A., Koech, R., & Walsh, K. (2023). Detection and Counting of Root-Knot Nematodes Using YOLO Models with Mosaic Augmentation. Biosensors and Bioelectronics: X, 15(July), 100407. https://doi.org/10.1016/j.biosx.2023.100407
Bochkovskiy, A., Chien-Yao Wang, & Liao, H.-Y. M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. ArXiv Preprint ArXiv :2004 .10934, April. https://doi.org/10.48550/arXiv.2004.10934
Durve, M., Tiribocchi, A., Bonaccorso, F., Montessori, A., Bogdan, M., Guzowski, J., Succi, S., & May, C. V. (2022). DropTrack - automatic droplet tracking using deep learning for microfluidic applications Mihir Durve, 1,. ArXiv, 34(8), 1–24.
Engstrom, L., Tran, B., Tsipras, D., Schmidt, L., & Madry, A. (2019). A Rotation and a Translation Suffice: Fooling CNNs with Simple Transformations. ICLR 2019 Conference Blind Submission, 10.
Iswara, N. F., & Syafiq, A. (2024). Pentingnya Protein Hewani dalam Mencegah Balita Stunting: Systematic Review. Media Publikasi Promosi Kesehatan Indonesia The, 7(1), 110–117.
Jocher, G., Nishimura, K., Mineeva, T., & Vilariño, R. (2020). YOLOv5. Code Repository.
Khotimah, D. F., Faizah, U. N., & Sayekti, T. (2021). Protein sebagai Zat Penyusun dalam Tubuh Manusia: Tinjauan Sumber. Proceeding of Integrative Science Education Seminar, 1, 127–133.
Krizhevsky, A., & Hinton, G. E. (2012). ImageNet Classification with Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems, 1097–1105.
Liao, H. M. (2020). YOLOv4 : Optimal Speed and Accuracy of Object Detection. ArXiv, May. https://doi.org/10.48550/arXiv.2004.10934
Liur, I. J. (2020). Kualitas Kimia dan Mikrobiologis Daging Ayam Broiler Pada Pasar Tradisional Kota Ambon. Al-Hayat: Journal of Biology and Applied Biology, 3(2), 59–66.
Lopes, J. C., & Lopes, R. P. (2024). Jou rna lP. Visual Informatics. https://doi.org/10.1016/j.visinf.2024.11.002
Mahaur, B., & Mishra, K. K. (2023). Small-object detection based on YOLOv5 in autonomous driving systems. Pattern Recognition Letters, 168, 115–122. https://doi.org/10.1016/j.patrec.2023.03.009
Mikołajczyk, A., & Grochowski, M. (2018). Data Augmentation for Improving Deep Learning in Image Classification Problem. 2018 International Interdisciplinary PhD Workshop (IIPhDW), 117–122.
Nehete, J. Y., Bhambar, R. S., Narkhede, M. R., & Gawali, S. R. (2013). Natural proteins : Sources , isolation , characterization and applications. 7(14). https://doi.org/10.4103/0973-7847.120508
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, Real-Time Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. https://sci-hub.ren/https://www.cv-foundation.org/openaccess/content_cvpr_2016/html/Redmon_You_Only_Look_CVPR_2016_paper.html
Redmon, J., & Farhadi, A. (2017). YOLO9000: Better, Faster, Stronger. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.
Redmon, J., Farhadi, A., & Ap, C. (2018). YOLOv3 : An Incremental Improvement. ArXiv Preprint ArXiv :1804 .02767.
Roxana, A., Florin, T., Gheorghe, L., Grigorovici, R., Iancu, S., Hlusneac, M., & Grigorovici, A. (2022). Impact of quality , type and volume of data used by deep learning models in the analysis of medical images. Informatics in Medicine Unlocked, 29(March), 100911. https://doi.org/10.1016/j.imu.2022.100911
Sheffield, S., Fiorotto, M. L., & Davis, T. A. (2024). Nutritional Importance of Animal-Sourced Foods in a Healthy Diet. Frontiers in Nutrition, July, 1–6. https://doi.org/10.3389/fnut.2024.1424912
Shorten, C., & Khoshgoftaar, T. M. (2019). A Survey on Image Data Augmentation for Deep Learning. Journal of Big Data. https://doi.org/10.1186/s40537-019-0197-0
Su, J., Yu, X., Wang, X., Wang, Z., & Chao, G. (2024). Enhanced Transfer Learning with Data Augmentation. 129(August 2023).
Yan, J., Zeng, Y., Lin, J., Pei, Z., Fan, J., Fang, C., & Cai, Y. (2024). Enhanced Object Detection in Pediatric Bronchoscopy Images Using YOLO-Based Algorithms with CBAM Attention Mechanism. Heliyon, 10(12), e32678. https://doi.org/10.1016/j.heliyon.2024.e32678
Yusuf, Y. (2018). Modul Kimia Pangan dan Gizi. EduCenter Indonesia.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Anton Yudhana, Esi Putri Silmina, Sunardi
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access)
JRST (Jurnal Riset Sains dan Teknologi) is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
