Detection and Recognition of Bangla Nameplates Using YOLOV6 and BLPNET Models

Sinthia, Camelia

dc.contributor.author	Sinthia, Camelia
dc.date.accessioned	2025-03-13T08:39:26Z
dc.date.available	2025-03-13T08:39:26Z
dc.date.issued	2024-09-02
dc.identifier.citation	[1] Wikipedia. (June 23, 2024) Automatic number-plate recognition. [Online]. Available: https://en.wikipedia.org/wiki/Automatic_number-plate_recognition# References [2] N. Saif, N. Ahmmed, S. Pasha, M. S. K. Shahrin, M. Hasan, S. Islam, and A. Jameel. (2019, 12) Automatic license plate recognition system for bangla li cense plates using convolutional neural network. [3] Wikipedia contributors, “Vehicle registration plates of bangladesh,” https://en. wikipedia.org/wiki/Vehicle_registration_plates_of_Bangladesh, 2024, accessed: 2024-08-25. [4] M. Lagunas and E. Garces. (2018, 05) Transfer learning for illustration classifi cation. [5] N. Haque, M. Islam, A. Tithy, and S. Islam, “Bangla license plate dataset 2.5k,” Sep. 2022. [Online]. Available: https://doi.org/10.5281/zenodo.7110401 [6] G. Rabbani, M. Aminul Islam, M. Anwarul Azim, M. Khairul Islam, and M. M. Rahman, “Bangladeshi license plate detection and recognition with morphologi cal operation and convolution neural network,” in 2018 21st International Con ference of Computer and Information Technology (ICCIT), 2018, pp. 1–5. [7] R. Rahman, A. F. Rakib, M. Rahman, T. Helaly, and T. S. Pias, “A real-time end to-end bangladeshi license plate detection and recognition system for all situa tions including challenging environmental scenarios,” in 2021 5th International Conference on Electrical Engineering and Information Communication Technol ogy (ICEEICT), 2021, pp. 1–6. [8] S. Abdullah, M. M. Hasan, and S. M. S. Islam, “Yolo-based three-stage network for bangla license plate recognition in dhaka metropolitan city,” 2018 International Conference on Bangla Speech and Language Processing (ICBSLP), pp. 1–6, 2018. [Online]. Available: https://api.semanticscholar.org/CorpusID: 54200221 50 [9] T. Islam and R. I. Rasel. (2019, 11) Real-time bangla license plate recognition system using faster r-cnn and ssd: A deep learning application. [10] R. Islam, M. R. Islam, and K. Talukder, “An efficient method for extraction and recognition of bangla characters from vehicle license plates,” Multimedia Tools and Applications, vol. 79, 07 2020. [11] S. R, A. S. Manjunath, R. Kumar, M. Roopa, and P. S B. (2021, 12) Vehicle number plate detection and recognition using yolo- v3 and ocr method. [12] A. Ashrafee, A. Khan, M. S. Irbaz, and M. A. Nasim. (2022, 01) Real-time bangla license plate recognition system for low resource video-based applications. [13] www.kaggle.com. Car license plate detection. [Online]. Available: https: //www.kaggle.com/datasets/andrewmvd/car-plate-detection [14] Roboflow. License plates object detection dataset. [Online]. Available: https://public.roboflow.com/object-detection/license-plates-us-eu [15] V. Sudha and D. Ganeshbabu, “A convolutional neural network classifier vgg 19 architecture for lesion detection and grading in diabetic retinopathy based on deep learning,” Computers, Materials Continua, vol. 66, pp. 827–842, 01 2020. [16] GeeksforGeeks. (Feb, 2020) Vgg-16 \| cnn model. [Online]. Available: https://www.geeksforgeeks.org/vgg-16-cnn-model/ [17] T. Akiba, S. Suzuki, and K. Fukuda. (2017, 11) Extremely large minibatch sgd: Training resnet-50 on imagenet in 15 minutes. [18] C.-N. Anagnostopoulos, I. Anagnostopoulos, I. Psoroulas, V. Loumos, and E. Kayafas, “License plate recognition from still images and video sequences: A survey,” Intelligent Transportation Systems, IEEE Transactions on, vol. 9, pp. 377 – 391, 10 2008. [19] S. Du, M. Ibrahim, M. Shehata, and W. Badawy, “Automatic license plate recog nition (alpr): A state-of-the-art review,” IEEE Transactions on Circuits and Sys tems for Video Technology, vol. 23, no. 2, pp. 311–325, 2013. [20] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Uni fied, real-time object detection,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 779–788. [21] S. Ren, K. He, R. Girshick, and J. Sun, “Faster r-cnn: Towards real-time object detection with region proposal networks,” 2016. [Online]. Available: https://arxiv.org/abs/1506.01497 51 [22] R. Al Batat, A. Angelopoulou, S. Premkumar, J. Hemanth, and E. Kapetanios, “An end-to-end automated license plate recognition system using yolo based ve hicle and license plate detection with vehicle classification,” Sensors, vol. 22, p. 9477, 12 2022. [23] M. F. Sadique and S. M. R. Haque. (2019, 12) A comparative study of license plate detection and recognition techniques. [24] S. Montazzolli and C. Jung. (2018, 09) License plate detection and recognition in unconstrained scenarios. [25] K. He, G. Gkioxari, P. Dollár, and R. Girshick, “Mask r-cnn,” in 2017 IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2980–2988. [26] S. Raj, Y. Gupta, and R. Malhotra. (2022, 03) License plate recognition system using yolov5 and cnn. [27] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi. (2016, 06) You only look once: Unified, real-time object detection. [28] M. Suvon, R. Khan, and M. Ferdous. (2020, 09) Real time bangla number plate recognition using computer vision and convolutional neural network. [29] S. Abdullah, M. M. Hasan, and S. M. S. Islam, “Yolo-based three-stage network for bangla license plate recognition in dhaka metropolitan city,” 2018 International Conference on Bangla Speech and Language Processing (ICBSLP), pp. 1–6, 2018. [Online]. Available: https://api.semanticscholar.org/CorpusID: 54200221 [30] M. S. H. Onim, H. Nyeem, K. Roy, M. Hasan, A. Ishmam, M. A. H. Akif, and T. B. Ovi, “Blpnet: A new dnn model and bengali ocr engine for automatic licence plate recognition,” Array, vol. 15, p. 100244, 2022. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S2590005622000789 [31] GeeksforGeeks, “Convolutional neural network (cnn) in machine learning,” GeeksforGeeks, accessed: 2024-08-25. [Online]. Available: https://www. geeksforgeeks.org/convolutional-neural-network-cnn-in-machine-learning/ [32] D. Sen Maitra, U. Bhattacharya, and S. Parui. (2015, 08) Cnn based common approach to handwritten character recognition of multiple scripts. [33] R. Laroca, E. Severo, L. Zanlorensi, L. Soares de Oliveira, G. Gonçalves, W. Schwartz, and D. Menotti. (2018, 07) A robust real-time automatic license plate recognition based on the yolo detector. [34] ——. (2018, 07) A robust real-time automatic license plate recognition based on the yolo detector. 52 [35] R. Laroca, L. Zanlorensi, G. Gonçalves, E. Todt, W. Schwartz, and D. Menotti. (2021, 02) An efficient and layout-independent automatic license plate recogni tion system based on the yolo detector. [36] T. Saidani and Y. El TOUATI, “A vehicle plate recognition system based on deep learning algorithms,” Multimedia Tools and Applications, vol. 80, pp. 1–12, 12 2021. [37] DataCamp, “Yolo object detection explained,” DataCamp Blog, n.d., ac cessed: 2024-08-25. [Online]. Available: https://www.datacamp.com/blog/ yolo-object-detection-explained [38] R. Laroca, L. Zanlorensi, G. Gonçalves, E. Todt, W. Schwartz, and D. Menotti. (2021, 02) An efficient and layout-independent automatic license plate recogni tion system based on the yolo detector. [39] C.-Y. Wang, A. Bochkovskiy, and H.-y. Liao. (2022, 07) Yolov7: Trainable bag of-freebies sets new state-of-the-art for real-time object detectors. [40] GeeksforGeeks, “Faster r-cnn - machine learning,” GeeksforGeeks, n.d., accessed: 2024-08-25. [Online]. Available: https://www.geeksforgeeks.org/ faster-r-cnn-ml/ [41] pawangfg. (June, 2020) Residual networks (resnet) - deep learning. [Online]. Available: https://www.geeksforgeeks.org/ residual-networks-resnet-deep-learning/ [42] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A. C. Berg, “Ssd: Single shot multibox detector,” in Computer Vision – ECCV 2016, B. Leibe, J. Matas, N. Sebe, and M. Welling, Eds. Cham: Springer International Publishing, 2016, pp. 21–37. [Online]. Available: https://github.com/weiliu89/caffe/tree/ssd. [43] Roboflow. (June, 2020) Roboflow: Go from raw images to a trained computer vision model in minutes. [Online]. Available: ttps://roboflow.com/ [44] Z. Selmi, M. Ben Halima, and A. M. Alimi, “Deep learning system for auto matic license plate detection and recognition,” in 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 01, 2017, pp. 1132–1138. [45] N. Omar, A. Sengur, and S. Al-Ali, “Cascaded deep learning-based efficient ap proach for license plate detection and recognition,” Expert Systems with Applica tions, vol. 149, p. 113280, 02 2020. 53 [46] Roboflow. (July 04, 2022) What’s new in yolov6? [Online]. Available: https://blog.roboflow.com/yolov6/ [47] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” in 3rd International Conference on Learning Representations (ICLR 2015), 2015, pp. 1–14. [Online]. Available: https: //arxiv.org/abs/1409.1556 [48] N. Kundu, “Exploring resnet50: An in-depth look at the model architecture and code implementation,” https://medium.com/@nitish, 2023.	en_US
dc.identifier.uri	http://hdl.handle.net/123456789/2400
dc.description	Supervised by Dr. Md. Hasanul Kabir, Professor, Department of Computer Science and Engineering (CSE) Islamic University of Technology (IUT) Board Bazar, Gazipur, Bangladesh. This thesis is submitted in partial fulfillment of the requirement for the degree of Master of Science in Computer Science and Engineering, 2024	en_US
dc.description.abstract	With an emphasis on Bangladeshi car number plates, this thesis offers a successful method for identifying and recognizing license plates. Character recognition, plate detection, and dataset creation are the three stages of the study procedure. A collec tion of 1,000 live-captured and online source pictures of Bangladeshi license plates was assembled from internet resources. With the help of the hybrid model BLPNET, which combines VGG19 and RESNET50, and the YOLOV6 object detection method, we were able to obtain an F1 score of 96.4% for character recognition and a pre cision of 96% for license plate detection. The system addresses challenges unique to Bangladeshi number plates, such as complex design, diverse weather conditions, and poor image quality due to occlusion in dense urban environments. The study contributes to the development of smart traffic management systems, aligning with Bangladesh’s vision of becoming a "smart" nation. This work also highlights the gap in public datasets for Bangla license plates, presenting a new dataset and models that push the boundaries of license plate recognition technology.	en_US
dc.language.iso	en	en_US
dc.publisher	Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh	en_US
dc.subject	BRTA-Bangladesh Road Transport Authority ANPR-Automatic Number Plate Recognition BLPNET-Mixture of VGG-19 and Resnet-50 YOLOV6 OCR-Optical Character Recognition	en_US
dc.title	Detection and Recognition of Bangla Nameplates Using YOLOV6 and BLPNET Models	en_US
dc.type	Thesis	en_US