USAGE OF MASK R-CNN FOR AUTOMATIC LICENSE PLATE RECOGNITION
Main Article Content
The subject of study is the creation process of an artificial intelligence system for automatic license plate detection. The goal is to achieve high license plate recognition accuracy on large camera angles with character extraction. The tasks are to study existing license plate recognition technics and to create an artificial intelligence system that works on big shooting camera angles with the help of modern machine learning solution – deep learning. As part of the research, both hardware and software-based solutions were studied and developed. For testing purposes, different datasets and competing systems were used. Main research methods are experiment, literature analysis and case study for hardware systems. As a result of analysis of modern methods, Mask R-CNN algorithm was chosen due to high accuracy. Conclusions. Problem statement was declared; solution methods were listed and characterized; main algorithm was chosen and mathematical background was presented. As part of the development procedure, accurate automatic license plate system was presented and implemented in different hardware environments. Comparison of the network with existing competitive systems was made. Different object detection characteristics, such as Recall, Precision and F1-Score, were calculated. The acquired results show that developed system on Mask R-CNN algorithm process images with high accuracy on large camera shooting angles.
Ministry of Internal Affairs of Ukraine. “Adresy kamer fotovideofiksaciji ta dozvolena shvydkistj rukhu” [Addresses of photo and video recording cameras and permitted speed], available at: https://mvs.gov.ua/uk/ministry/projekti-mvs/avtofotovideofiksaciya-porusen-pdr/adresi-kamer-fotovideofiksaciyi-ta-dozvolena-svidkist-ruxu-1
Verified Market Research “Global Automatic License Plate Recognition (ALPR) Market Size And Forecast”, available at: https://www.verifiedmarketresearch.com/product/automatic-license-plate-recognition-alpr-market/
Press Release “Automatic License Plate Recognition Market Size 2022 Report”, available at: https://www.marketwatch.com/press-release/automatic-license-plate-recognition-alpr-market-size-2022-report-examines-latest-trends-and-key-drivers-supporting-regional-outlook-2028-2022-12-08
Psyllos, A., Anagnostopoulos, C. N., and Kayafas, E. (2011), “Vehicle model recognition from frontal view image measurements,” Computer Standards & Interfaces, 2011, vol. 33, no. 2, pp. 142–151. DOI: https://doi.org/10.1016/j.csi.2010.06.005.
Liubchenko, N., Nakonechnyi, O., Podorozhniak, A., and Siulieva, H. (2018), “Automation of vehicle plate numbers identification on one-aspect images,” Advanced Information Systems, 2018, vol. 2, no. 1, pp. 52 – 55. DOI: https://doi.org/10.20998/2522-9052.2018.1.10.
Kranthi, S., Pranathi, K., and Srisaila, A. (2011), “Automatic number plate recognition,” International Journal of Advancements in Technology, vol. 2, no. 3, pp. 408– 422, available at: https://www.longdom.org/open-access-pdfs/automatic-number-plate-recognition-0976-4860-2-408-422.pdf
Lubna, Mufti, N., and Shah, S. A. A. (2021), “Automatic Number Plate Recognition: A Detailed Survey of Relevant Algorithms,” Sensors, 2021, vol. 21, iss. 9, article no. 3028. DOI: https://doi.org/10.3390/s21093028.
Li, H., Wang, P., and Shen C. (2019), “Toward end-to-end car license plate detection and recognition with deep neural networks,” IEEE Transactions on Intelligent Transportation Systems, vol. 20, issue 3, pp. 1126–1136. DOI: https://doi.org/10.1109/TITS.2018.2847291.
Firasanti, A., Ramadhani, T. E., Bakri, M. A., and Zaki, H. E. A. (2021), “License Plate Detection Using OCR Method with Raspberry Pi,” 15th International Conference on Telecommunication Systems, Services, and Applications, TSSA 2021, 18-19 November 2021. DOI: https://doi.org/10.1109/TSSA52866.2021.9768252.
Khokhar, S., Kedia, D., and Dahiya, P.K. (2019), “Toward end-to-end car license plate detection and recognition with deep neural networks,” IEEE Transactions on Intelligent Transportation Systems, vol. 20, issue 3, pp. 1126–1136. DOI: https://doi.org/10.1109/TITS.2018.2847291.
Khudov, H., Makoveichuk, O., Misiuk, D., Pievtsov, H., Khizhnyak, I., Solomonenko, Y., Yuzova, I., Cherneha, V., Vlasiuk, V., and Khudov, V. (2022), “Devising a method for processing the image of a vehicle's license plate when shooting with a smartphone camera,” Eastern-European Journal of Enterprise Technologies, vol. 1, issue 2-115, pp. 6-21, DOI: https://doi.org/10.15587/1729-4061.2022.252310.
Onishchenko, D., and Tkachenko, S. (2022), “Istorija rozvytku simejstva nejronnykh merezh R-CNN” [History of development of the family of neural networks R-CNN], Ukraine and the world: humanitarian and technical elite and social progress 2022, Kharkiv, Ukraine, pp. 640 – 642, available at: http://repository.kpi.kharkov.ua/bitstream/KhPI-Press/60729/1/Onishchenko_Istoriia_2022.pdf (last accessed January 15, 2023).
He, K., Gkioxari, G., Dollár, P., Girshick, R. (2017), “Mask R-CNN,” Proceedings of the IEEE international conference on computer vision (ICCV), pp. 2961-2969. DOI: https://doi.org/10.1109/ICCV.2017.322.
Kuchuk, H., Podorozhniak, A., Liubchenko, N., and Onishchenko, D. (2021), “System of license plate recognition considering large camera shooting angles,” Radioelectronic and Computer Systems, no. 4 (100), pp. 82 – 91. DOI: https://doi.org/10.32620/reks.2021.4.07.
AUTO.RIA, “Nomeroff Net. Automatic numberplate recognition system. Version 0.2.3,” available at: https://nomeroff.net.ua/ (last accessed January 15, 2023).
FF-Group, “SeeAuto”, available at: https://ff-group.org/seeauto
Podorozhniak, A., Liubchenko, N., and Heiko, H. (2020), “Neural network system for license plates recognizing,” Control, Navigation and Communication Systems, 2020, vol. 4 (62), pp. 88-91. DOI: https://doi.org/10.26906/SUNZ.2020.4.088.
Medialab, “LPR database”, available at: http://www.medialab.ntua.gr/research/LPRdatabase.html
Padmasiri, H., Shashirangana, J., Meedeniya, D., Rana, O., and Perera, C. (2022) “Automated License Plate Recognition for Resource-Constrained Environments,” Sensors, vol. 22, iss. 4, article number 1434, DOI: https://doi.org/10.3390/s22041434.
Chiriac, R. L. (2020), “I built a DIY license plate reader with a Raspberry Pi and machine learning,” available at: https://towardsdatascience.com/i-built-a-diy-license-plate-reader-with-a-raspberry-pi-and-machine-learning-7e428d3c7401
Aswinth, R. (2021) “License Plate Recognition using Raspberry Pi and OpenCV,” available at: https://circuitdigest.com/microcontroller-projects/license-plate-recognition-using-raspberry-pi-and-opencv
Kanakaraja, P., Kumar, K. S., Nadipalli, L. S., Aswin, K. S. V., and Kavya, K. C. (2022), “An Implementation of Outdoor Vehicle Localization and Tracking Using Automatic License Plate Recognition (ALPR),” International Journal of e-Collaboration (IJeC), vol. 18, issue 2, pp. 1-11. DOI: https://doi.org/10.4018/IJeC.304043.
Kaimkhani, N. A. K., Noman, M., Rahim, S., and Liaqat, H. B. (2022), “UAV with Vision to Recognize Vehicle Number Plates,” Mobile Information System, vol. 4, article ID 7655833. DOI: https://doi.org/10.1155/2022/7655833.
Mokayed, H., Shivakumara, P., Woon, H. H., Kankanhalli, M., Lu, T., and Pal, U. (2021), “A new DCT-PCM method for license plate number detection in drone images,” Pattern Recognition Letters, vol. 148, pp. 45-53, DOI: https://doi.org/10.1016/j.patrec.2021.05.002.