Perbaikan Kualitas Gambar untuk Deteksi Plat Nomor Kendaraan dengan Metode Super Resolution GANs

Authors

  • Sugeng Program Studi Sistem Komputer, Fakultas Ilmu dan Teknik Komputer, Universitas Komputer Indonesia
  • Nugraha Widyanto Program Studi Sistem Komputer, Fakultas Ilmu dan Teknik Komputer, Universitas Komputer Indonesia

Keywords:

deep learning, machine learning, license plate, image resolution, SRGANs , plat nomor, resolusi gambar

Abstract

Penelitian tentang pembelajaran mendalam yang dapat meningkatkan resolusi gambar dapat diterapkan di berbagai bidang. Salah satu implementasinya adalah dalam deteksi plat nomor kendaraan. Dengan menggunakan teknologi Deep Learning SRGAN yang mampu meningkatkan resolusi gambar, membuat proses pengenalan objek menjadi lebih mudah. Dalam studi ini, model dilatih dengan 1.070 gambar, termasuk 535 gambar beresolusi rendah dan 535 gambar beresolusi tinggi. Model kemudian diuji dengan 10 gambar beresolusi rendah. Hasilnya menunjukkan bahwa model dapat meningkatkan resolusi gambar hingga 2x dari gambar masukan. Evaluasi model menghasilkan nilai PSNR rata-rata sebesar 20,1587 dB untuk input image dan 21,1831 dB untuk output model. Nilai SSIM rata-rata adalah 0,5215 untuk input image dan 0,6331 untuk output model.

References

R. Pahlevi, “Jumlah Tilang Lalu Lintas Capai 1,77 Juta hingga Oktober 2021,” Nov. 09, 2021. [Online]. Available: https://databoks.katadata.co.id/datapublish/2021/11/09/jumlah-tilang-lalu-lintas-capai-177-juta-hingga-oktober-2021 (accessed: Nov. 15, 2022).

G. Satria, “Ini Alasan Polisi Gencarkan Tilang Elektronik,” Feb. 03, 2021. [Online]. Available: https://otomotif.kompas.com/read/2021/02/03/102200115/ini-alasan-polisi-gencarkan-tilang-elektronik (accessed Nov. 15, 2022).

Korlantas Polri, “Korlantas Polri Luncurkan ETLE di Seluruh Indonesia - Korlantas Polri,” Sep. 22, 2022. [Online]. https://korlantas.polri.go.id/news/korlantas-polri-luncurkan-etle-di-seluruh-indonesia/ (accessed Nov. 15, 2022).

Arri Widiarto, “Efisienkah Tilang Elektronik di Kota Solo?,” Apr. 25, 2022. [Online]. Available: https://www.ayosemarang.com/netizen/pr-773276650/efisienkah-tilang-elektronik-di-kota-solo (accessed Jun. 11, 2023).

Abdul Alim Muhamad, “ETLE Punya Kelemahan di Blank Spot Area,” Mar. 30, 2021. [Online]. Available: https://www.gatra.com/news-507814-hukum-etle-punya-kelemahan-di-blank-spot-area.html (accessed Jun. 12, 2023).

Y. Puspito, F. X. Setyawan, and H. Fitriawan, "Deteksi posisi plat nomor kendaraan menggunakan metode transformasi Hough dan hit or miss," ELECTRICIAN–Jurnal Rekayasa dan Teknologi Elektro, pp. 118–123, 2018.

M. Mazlan, E. Ismaredah, H. Simaremare, and O. B. Kharisma, "Desain sistem pendeteksi plat kendaraan untuk pengisian BBM menggunakan metode K-Nearest Neighbor (KNN)," Journal of Information System Research (JOSH), vol. 4, no. 4, pp. 1118–1126, 2023.

S. Sugeng and E. Syamsuddin, “Perancangan Algoritma Optimasi Pada Pengenalan Karakter Plat Nomor Kendaraan Menggunakan Pengolahan Citra,” Komputika : Jurnal Sistem Komputer, vol. 9, no. 2, pp. 155–164, Oct. 2020, doi: 10.34010/komputika.v9i2.3682.

J. Huixian, "The Analysis of Plants Image Recognition Based on Deep Learning and Artificial Neural Network," IEEE Access, vol. 8, pp. 68828-68841, 2020, doi: 10.1109/ACCESS.2020.2986946.

I. Arifin, R. F. Haidi, and M. Dzalhaqi, "Penerapan computer vision menggunakan metode deep learning pada perspektif generasi ulul albab," Jurnal Teknologi Terpadu, vol. 7, no. 2, pp. 98–107, 2021, doi: 10.54914/jtt.v7i2.436.

R. Radikto, D. I. Mulyana, M. A. Rofik, and M. O. Z. Zakaria, "Klasifikasi kendaraan pada jalan raya menggunakan algoritma Convolutional Neural Network (CNN)," Jurnal Pendidikan Tambusai, vol. 6, no. 1, pp. 1668–1679, 2022, doi: 10.31004/jptam.v6i1.3179.

L. Alzubaidi et al., “Review of deep learning: concepts, CNN architectures, challenges, applications, future directions,” Journal of Big Data, vol. 8, no. 1, pp. 53, 2021, doi: 10.1186/s40537-021-00444-8.

A. Maulana, C. Fatichah, and N. Suciati, "Facial inpainting in unaligned face images using generative adversarial network with feature reconstruction loss", Jurnal Ilmiah Teknologi Informasi, vol. 18, no. 2, pp. 171–178, 2022.

A. R. P. Gondosiswojo and A. G. P. Kusuma, "Low resolution face recognition on CCTV images using a combination of super resolution and face recognition models", Journal of Theoretical and Applied Information Technology, vol. 101, pp. 20, 2023.

C. Ledig et al., “Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network.” arXiv, 2016. doi: 10.48550/ARXIV.1609.04802.

P. Liu, Y. Hong, and Y. Liu, “A Novel Multi-Scale Adaptive Convolutional Network for Single Image Super-Resolution,” IEEE Access, vol. PP, p. 1, Aug. 2019, doi: 10.1109/ACCESS.2019.2908003.

D. R. I. M. Setiadi, “PSNR vs SSIM: imperceptibility quality assessment for image steganography,” Multimed Tools and Applications, vol. 80, no. 6, pp. 8423–8444, 2021, doi: 10.1007/s11042-020-10035-z.

Downloads

Published

2025-10-01

Issue

Vol. 16 No. 2 (2025): Jurnal Buana Informatika, Volume 16, Nomor 02, Oktober 2025

Section

Articles

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Copyright of this journal is assigned to Jurnal Buana Informatika as the journal publisher by the knowledge of author, whilst the moral right of the publication belongs to author. Every printed and electronic publications are open access for educational purposes, research, and library. The editorial board is not responsible for copyright violation to the other than them aims mentioned before. The reproduction of any part of this journal (printed or online) will be allowed only with a written permission from Jurnal Buana Informatika.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.