Pengenalan Plat Nomor Kendaraan Indonesia Menggunakan Convolutional Neural Network dan BiLSTM
Kata Kunci:
CCTV, pengenalan plat nomor, convolutional neural network, bidirectional long short term memory, thin plate spline, freezing layerAbstrak
CCTV (Closed Circuit Television) adalah sistem pengawasan berbasis kamera yang banyak digunakan untuk memantau lalu lintas dan keamanan di kota-kota besar seperti Jakarta, Surabaya, dan Bandung. Dengan meningkatnya jumlah kendaraan, pengawasan lalu lintas menjadi tantangan besar, terutama bagi pihak kepolisian yang masih menggunakan metode manual. Oleh karena itu, diperlukan solusi otomatis yang dapat mengenali plat nomor kendaraan sebagai identitas unik setiap kendaraan. Dalam beberapa tahun terakhir, teknologi kecerdasan buatan telah digunakan untuk mengembangkan sistem pengenalan plat nomor berbasis machine learning dan deep learning. Salah satu metode yang populer adalah Convolutional Neural Network (CNN). Namun, CNN memiliki kelemahan dalam mengenali urutan karakter. Hal ini dapat diatasi dengan Bidirectional Long Short-Term Memory (BiLSTM), yang mampu memproses urutan data dari dua arah yang meningkatkan akurasi pengenalan. Penelitian ini menggabungkan CNN dan BiLSTM untuk mengenali plat nomor kendaraan, menghasilkan akurasi 86.869 dan Norm ED 0.971. Penggunaan transformasi gambar Thin Plate Spline (TPS) dan freezing layer juga terbukti meningkatkan kemampuan generalisasi model. Kombinasi metode ini memberikan solusi efektif untuk pengenalan plat nomor secara otomatis.
Referensi
Alkaf, A.M. & Sutrisno, B., 2019. SMART SURVEILLANCE DAN KETERATURAN SOSIAL (STUDI KASUS IMPLEMENTASI SMART CITY DI KOTA BANDUNG). Jurnal Sosioteknologi.
Badan Pusat Statistik (BPS), 2022. Perkembangan Jumlah Kendaraan Bermotor Menurut Jenis. [online] Available at: https://www.bps.go.id/id/statistics-table/2/NTcjMg==/perkembangan-jumlah-kendaraan-bermotor-menurut-jenis.html [Accessed 20 Dec. 2024].
Baek, J., Kim, G., Lee, J., Park, S., Han, D., Yun, S., Oh, S.J. & Lee, H., 2019. What is Wrong with Scene Text Recognition Model Comparisons? Dataset and Model Analysis. Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 4715-4723.
Bismantoko, S., Chasanah, U., Suksmono, A. & Widodo, T., 2023. Character Recognition for Indonesian License Plate by Using Image Enhancement and Convolutional Neural Network. Majalah Ilmiah Pengkajian Industri; Journal of Industrial Research and Innovation, 14(2), pp. 145–152.
Couprie, C., Farabet, C., Najman, L. & Lecun, Y., 2014. Convolutional nets and watershed cuts for real-time semantic labeling of rgbd videos. The Journal of Machine Learning Research, 15(1), pp. 3489-3511.
Ekandana, M.R. & Kurniawan, B., 2022. Implementasi Program Electronic Traffic Law Enforcement (E-TLE) Sebagai Upaya Meningkatkan Ketertiban Lalu Lintas di Kota Surabaya. Publika.
Graves, A., Fernández, S., Gomez, F. & Schmidhuber, J., 2006. Connectionist temporal classification: Labelling unsegmented sequence data with recurrent neural networks. Proceedings of the 23rd International Conference on Machine Learning (ICML), pp. 369–376.
Imaduddin, H., Anwar, M., Perdana, M., Sulistijono, I.A. & Risnumawan, A., 2018. Indonesian Vehicle License Plate Number Detection Using Deep Convolutional Neural Network. Proceedings of the 2018 International Conference on Knowledge Creation and Intelligent Computing (KCIC), pp. 158–163. Available at: https://doi.org/10.1109/KCIC.2018.8628488.
Jaderberg, M., Simonyan, K., Zisserman, A. & Kavukcuoglu, K., 2016. Spatial Transformer Networks. Proceedings of the Advances in Neural Information Processing Systems (NIPS).
MathWorks, 2023. Create a Bidirectional Long Short-Term Memory (BiLSTM) Function. [online] Available at: https://www.mathworks.com/help/deeplearning/ug/create-bilstm-function.html [Accessed 20 Dec. 2024].
Mousa, A.E. & Schuller, B., 2017. Contextual Bidirectional Long Short-Term Memory Recurrent Neural Network Language Models: A Generative Approach to Sentiment Analysis. Conference of the European Chapter of the Association for Computational Linguistics.
Putra, A.S., 2020. Hubungan Penggunaan Closed Circuit Television (CCTV) Untuk Pengawasan Kota Dalam Perkembangan Kota DKI Jakarta Menuju Kota Pintar. Publika.
Shi, B., Bai, X. & Yao, C., 2017. An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(11), pp. 2298–2304.
Simonyan, K. & Zisserman, A., 2015. Very deep convolutional networks for large-scale image recognition. In International Conference on Learning Representations (ICLR).
Tan, H. H., Ooi, S. T. & Rahman, A., 2023. Malaysian Vanity License Plate Recognition Using Convolutional Neural Network. Journal of Multimedia Tools and Applications, 82(5), pp. 4567–4583.
Yudistira, N., Alfiansih, L. M. D., Andriyani, N. I., Essayem, W., Maulida, N., Maghfiroh, N. A. & Nurdian, I. W., 2023. Prediksi Deret Waktu Menggunakan Deep Learning. UB Press.
Zakiyamani, M., Cahyani, T. I., Riana, D. & Hardianti, S., 2022. Deteksi dan Pengenalan Plat Karakter Nomor Kendaraan Menggunakan OpenCV dan Deep Learning Berbasis Python. Journal of Information Technology and Computer Science (INTECOMS), 5(1), pp. 56–64.
Zhang, X., Ni, X., Deng, Y., Jiang, C. & Maleki, M., 2021. Chinese License Plate Recognition Using Machine and Deep Learning Models. 2021 IEEE 2nd International Conference on Pattern Recognition and Machine Learning (PRML), Chengdu, China, pp. 342–346.
Zou, Y., Xu, Z., Yang, W., Meng, A. & Lu, N., 2020. A Robust License Plate Recognition Model Based on Bi-LSTM. IEEE Access, 8, pp. 211630–211641.
Alkaf, A.M. & Sutrisno, B., 2019. SMART SURVEILLANCE DAN KETERATURAN SOSIAL (STUDI KASUS IMPLEMENTASI SMART CITY DI KOTA BANDUNG). Jurnal Sosioteknologi.
Badan Pusat Statistik (BPS), 2022. Perkembangan Jumlah Kendaraan Bermotor Menurut Jenis. [online] Available at: https://www.bps.go.id/id/statistics-table/2/NTcjMg==/perkembangan-jumlah-kendaraan-bermotor-menurut-jenis.html [Accessed 20 Dec. 2024].
Baek, J., Kim, G., Lee, J., Park, S., Han, D., Yun, S., Oh, S.J. & Lee, H., 2019. What is Wrong with Scene Text Recognition Model Comparisons? Dataset and Model Analysis. Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 4715-4723.
Bismantoko, S., Chasanah, U., Suksmono, A. & Widodo, T., 2023. Character Recognition for Indonesian License Plate by Using Image Enhancement and Convolutional Neural Network. Majalah Ilmiah Pengkajian Industri; Journal of Industrial Research and Innovation, 14(2), pp. 145–152.
Couprie, C., Farabet, C., Najman, L. & Lecun, Y., 2014. Convolutional nets and watershed cuts for real-time semantic labeling of rgbd videos. The Journal of Machine Learning Research, 15(1), pp. 3489-3511.
Ekandana, M.R. & Kurniawan, B., 2022. Implementasi Program Electronic Traffic Law Enforcement (E-TLE) Sebagai Upaya Meningkatkan Ketertiban Lalu Lintas di Kota Surabaya. Publika.
Graves, A., Fernández, S., Gomez, F. & Schmidhuber, J., 2006. Connectionist temporal classification: Labelling unsegmented sequence data with recurrent neural networks. Proceedings of the 23rd International Conference on Machine Learning (ICML), pp. 369–376.
Imaduddin, H., Anwar, M., Perdana, M., Sulistijono, I.A. & Risnumawan, A., 2018. Indonesian Vehicle License Plate Number Detection Using Deep Convolutional Neural Network. Proceedings of the 2018 International Conference on Knowledge Creation and Intelligent Computing (KCIC), pp. 158–163. Available at: https://doi.org/10.1109/KCIC.2018.8628488.
Jaderberg, M., Simonyan, K., Zisserman, A. & Kavukcuoglu, K., 2016. Spatial Transformer Networks. Proceedings of the Advances in Neural Information Processing Systems (NIPS).
MathWorks, 2023. Create a Bidirectional Long Short-Term Memory (BiLSTM) Function. [online] Available at: https://www.mathworks.com/help/deeplearning/ug/create-bilstm-function.html [Accessed 20 Dec. 2024].
Mousa, A.E. & Schuller, B., 2017. Contextual Bidirectional Long Short-Term Memory Recurrent Neural Network Language Models: A Generative Approach to Sentiment Analysis. Conference of the European Chapter of the Association for Computational Linguistics.
Putra, A.S., 2020. Hubungan Penggunaan Closed Circuit Television (CCTV) Untuk Pengawasan Kota Dalam Perkembangan Kota DKI Jakarta Menuju Kota Pintar. Publika.
Shi, B., Bai, X. & Yao, C., 2017. An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(11), pp. 2298–2304.
Simonyan, K. & Zisserman, A., 2015. Very deep convolutional networks for large-scale image recognition. In International Conference on Learning Representations (ICLR).
Tan, H. H., Ooi, S. T. & Rahman, A., 2023. Malaysian Vanity License Plate Recognition Using Convolutional Neural Network. Journal of Multimedia Tools and Applications, 82(5), pp. 4567–4583.
Yudistira, N., Alfiansih, L. M. D., Andriyani, N. I., Essayem, W., Maulida, N., Maghfiroh, N. A. & Nurdian, I. W., 2023. Prediksi Deret Waktu Menggunakan Deep Learning. UB Press.
Zakiyamani, M., Cahyani, T. I., Riana, D. & Hardianti, S., 2022. Deteksi dan Pengenalan Plat Karakter Nomor Kendaraan Menggunakan OpenCV dan Deep Learning Berbasis Python. Journal of Information Technology and Computer Science (INTECOMS), 5(1), pp. 56–64.
Zhang, X., Ni, X., Deng, Y., Jiang, C. & Maleki, M., 2021. Chinese License Plate Recognition Using Machine and Deep Learning Models. 2021 IEEE 2nd International Conference on Pattern Recognition and Machine Learning (PRML), Chengdu, China, pp. 342–346.
Zou, Y., Xu, Z., Yang, W., Meng, A. & Lu, N., 2020. A Robust License Plate Recognition Model Based on Bi-LSTM. IEEE Access, 8, pp. 211630–211641.
Unduhan
Diterbitkan
Cara Mengutip
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2025 Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Artikel ini berlisensiCreative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
