Identifikasi Nomor Kontainer Menggunakan Resnet-50 Pada Gate-In PT. Pelindo Berlian Jasa Terminal Indonesia (Bjti) Berbasis Website
Abstrak
Abstrak — Proses pencatatan nomor kontainer secara manual di area gate-in PT Pelindo Berlian Jasa Terminal Indonesia (BJTI) masih menimbulkan berbagai kendala seperti kesalahan pencatatan, keterlambatan pemrosesan data, dan kesulitan validasi dalam kasus klaim kerusakan. Untuk mengatasi masalah tersebut, penelitian ini mengembangkan sistem identifikasi nomor kontainer otomatis berbasis deep learning yang terdiri dari tiga tahap utama, yaitu: deteksi area nomor kontainer menggunakan model YOLOv11, segmentasi karakter dengan model YOLOv11 lainnya, serta klasifikasi karakter menggunakan arsitektur ResNet-50. Dataset pada setiap tahap dikumpulkan dari lingkungan nyata di pelabuhan dan telah dianotasi secara manual. Model deteksi area nomor kontainer yang dilatih dengan optimizer AdamW selama 200 epoch menghasilkan mAP@0.5 sebesar 96.8%, precision 97.1%, dan recall 95.4%. Pada tahap segmentasi karakter, model mencatatkan mAP@0.5 sebesar 94.3%, precision 95.2%, dan recall 93.7%. Sedangkan pada tahap klasifikasi karakter menggunakan ResNet-50, akurasi tertinggi yang diperoleh mencapai 98.6%, dengan precision 98.9%, recall 98.3%, dan F1-score 98.6%. Seluruh sistem kemudian diintegrasikan ke dalam platform berbasis web untuk mendukung operasional, memungkinkan penyimpanan hasil deteksi dalam bentuk teks dan gambar, serta dilengkapi fitur login, pencarian data, dan tampilan statistik. Evaluasi menunjukkan bahwa sistem mampu beroperasi dengan efisien dan akurat di berbagai kondisi pencahayaan dan sudut pandang kamera. Sistem ini diharapkan dapat meningkatkan efisiensi, akurasi, dan transparansi pencatatan nomor kontainer di lingkungan operasional pelabuhan.
Kata kunci— sistem deteksi otomatis, YOLOv11, ResNet-50, nomor kontainer, pengolahan citra, pelabuhan, website.
Unduhan
Referensi
[1] D.-V. Licu, “Automatic container code identification using Machine Learning,” 2020.
[2] J. Liang and W. Jiang, “A ResNet50-DPA model for tomato leaf disease identification,” Front Plant Sci, vol. 14, 2023, doi: 10.3389/fpls.2023.1258658.
[3] G. S. Surjo, B. K. Ghosh, M. J. Alam, Mahamudullah, M. Razib, and S. Bilgaiyan, “A comparative analysis between single & dual-handed Bangladeshi Sign Language detection using CNN based approach,” in 2023 International Conference on Computer Communication and Informatics, ICCCI 2023, Institute of Electrical and Electronics Engineers Inc., 2023. doi: 10.1109/ICCCI56745.2023.10128583.
[4] N. Basuni and Amril Mutoi Siregar, “Comparison of the Accuracy of Drug User Classification Models Using Machine Learning Methods,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 7, no. 6, pp. 1348–1353, Dec. 2023, doi: 10.29207/resti.v7i6.5401.
[5] S. Bandong, Y. Y. Nazaruddin, and E. Joelianto, “Container Detection System Using CNN Based Object Detectors,” in Proceedings of the 2021 International Conference on Instrumentation, Control, and Automation, ICA 2021, Institute of Electrical and Electronics Engineers Inc., 2021, pp. 106–111. doi: 10.1109/ICA52848.2021.9625663
[6] R. Shinde, A. Patil, and N. Jadhav, “Automatic number plate recognition using YOLOv11 and PaddleOCR,” International Journal of Computer Trends (IJCT), vol. 12, no. 3, pp. 5–10, 2025. [Online]. Available: https://ijctjournal.org/wp-content/uploads/2025/06/IJCT-V12I3P2.pdf
[7] Z. Lin, C. Dong, and X. Wan, “Research on intelligent recognition algorithm of container numbers in ports based on deep learning,” in Proc. ICIC 2024, Lecture Notes in Computer Science, vol. 14868, pp. 179–190, 2024. [Online]. Available: https://doi.org/10.1007/978-981-97-5600-1_16
[8] Y. Zhao, J. Wu, X. Wang, and M. Li, “An improved character recognition framework for containers based on DETR ResNeSt50 MSLC,” Sensors, vol. 21, no. 14, p. 4678, 2021. [Online]. Available: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8272209/pdf/sensors-21-04678.pdf
[9] Y. Akkem, “Multi Disease Prediction Model by using Machine Learning and Flask API,” 2020 International Conference on Communication and Electronics Systems (ICCES), pp. 962–965, 2020. DOI: 10.1109/ICCES48766.2020.9137896
[10] U. M. Kotha, D. Bharathi, and P. K. D. Prakash, “Execution of Flask deployment on essay grading,” International Journal of Electrical and Computer Engineering (IJECE), vol. 13, no. 3, pp. 2990–2998, Jun. 2023. DOI: 10.11591/ijece.v13i3.pp2990-2998
[11] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778. doi: 10.1109/CVPR.2016.90
[12] R. Khanam and M. Hussain, "YOLOv11: An Overview of the Key Architectural Enhancements," *arXiv preprint*, arXiv:2410.17725, Oct. 2024. [Online]. Available: https://doi.org/10.48550/arXiv.2410.17725
[13] S. Balakrishna, S. Yadao, and V. K. Solanki, "Enhancing YOLOv11 for Real‑Time Object Detection: Advanced Architectures and Edge‑Optimized Training Pipeline," in *Proc. 9th Int. Conf. Res. Intelligent Computing in Engineering (ACSIS)*, vol. 42, pp. 89–96, May 2025, doi: 10.15439/2024R115.
[14] A. A. Salihu, M. H. Ahmad, N. Z. Jhanjhi, M. S. Khan, and A. Abdullah, “A Comprehensive Review on Evaluation Metrics for Deep Learning Classification Models Based on Confusion Matrix,” IEEE Access, vol. 9, pp. 145362–145377, 2021, doi: 10.1109/ACCESS.2021.3122606.
[15] J. Redmon and A. Farhadi, "YOLOv3: An Incremental Improvement," arXiv preprint arXiv:1804.02767, 2018. [Online]. Available: https://arxiv.org/abs/1804.02767.
[16] T. S. Fawcett, “An introduction to ROC analysis,” Pattern Recognition Letters, vol. 27, no. 8, pp. 861–874, 2006, doi: 10.1016/j.patrec.2005.10.010.
