MVSR Normalization Algorithm Method for Improving Vehicle License Plate Recognition

Abstract

Image processing and embedded systems are used in many applications such as object recognition, robotic applications, autonomous and remote control systems developed for the defense industry, medical applications, face recognition, and vehicle license plate recognition. Many vehicle license number plate detection methods are not effective under vehicle license plate images have a degree of rotation or low resolution images. Thus, we used MVSR normalization algorithm to detect vehicle license plate recognition for better accuracy and lower computational cost. The MVSR normalization algorithm, Mean–Variance-Softmax-Rescale processes respectively is applied for high-accuracy real-time vehicle license plate detection.

Keywords

• MVSR algorithm
• Vehicle License Plate Recognition
• Normalization
• Artificial neural network.

Araç Plaka Tespitinin İyileştirilmesine Yönelik MVSR Normalleştirme Algoritması Yöntemi

Abstract

Görüntü işleme ve gömülü sistemler; nesne tanıma, robotik uygulamalar, savunma sanayi için geliştirilen otonom ve uzaktan kontrol sistemleri, medikal uygulamalar, yüz tanıma, araç plaka tanıma gibi birçok uygulamada kullanılmaktadır. Dönme derecesine sahip veya düşük çözünürlüklü görüntülere sahip araç plaka görüntüleri altında birçok araç plakası tespit yöntemi etkili değildir. Bu nedenle, daha iyi doğruluk ve daha düşük hesaplama maliyeti için araç plakası tanımayı tespit etmek amacıyla MVSR normalleştirme algoritmasını kullandık. Yüksek doğruluklu, gerçek zamanlı araç plakası tespiti için sırasıyla MVSR normalleştirme algoritması, Ortalama-Varyans-Softmax-Yeniden Ölçeklendirme işlemleri uygulanmıştır.

Keywords

• MVSR algoritması
• araç plaka tespiti
• normalizasyon
• yapay sinir ağı

References

1. Nagare AP. License plate character recognition system using neural network. International Journal of Computer Applications 2011; 25(10): 36-39
2. Zhai X, Bensaali F, Ramalingam S. Real-time license plate localisation on FPGA. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. Work., IEEE Computer Society 2011; 14–19.
3. Patel C, Patel A, Patel D. Optical character recognition by open source OCR tool tesseract: A case study. International Journal of Computer Applications 2012; 55(10): 50-56.
4. Du S, Ibrahim M, Shehata M, Badawy W. Automatic license plate recognition (ALPR): A state-of-the-art review. IEEE Trans. Circuits Syst. Video Technol. 2013; 23: 311–325.
5. Massoud MA, Sabee M, Gergais M, Bakhit R. Automated new license plate recognition in Egypt. Alexandria Eng. J. 2013; 52(3): 319–326.
6. Zang D, Chai Z, Zhang J, Zhang D, Cheng J. Vehicle license plate recognition using visual attention model and deep learning. Journal of Electronic Imaging 2015; 24(3): 033001.
7. Zhai X, Bensaali F. Improved number plate character segmentation algorithm and its efficient FPGA implementation. J. Real-Time Image Process 2015; 10: 91–103.
8. Fan R, Prokhorov V, Dahnoun N. Faster-than-real-time linear lane detection implementation using SoC DSP TMS320C6678. IST 2016 IEEE Int. Conf. Imaging Syst. Tech. Proc.; 2016; pp. 306–311.

9. Calderon JAF, Vargas JS, Pérez-Ruiz A. License plate recognition for Colombian private vehicles based on an embedded system using the ZedBoard. 2016 IEEE Colombian Conference on Robotics and Automation (CCRA); 2016; Bogota, Colombia. pp. 1-6.
10. Promrit P, Suntiamorntut W. Design and development of lane detection based on FPGA. 2017 14th International Joint Conference on Computer Science and Software Engineering (JCSSE); 2017; NakhonSiThammarat, Thailand. pp. 1-4.
11. Li H, Wang P, You M, Shen C. Reading car license plates using deep neural networks. Image Vis. Comput. 2018; 72: 14–23.
12. Xie L, Ahmad T, Jin L, Liu Y, Zhang S. A new CNN-based method for multi-directional car license plate detection. IEEE Trans. Intell. Transp. Syst. 2018; 19: 507– 517.
13. Hendry, Chen RC. Automatic License plate recognition via sliding-window darknet-YOLO deep learning. Image Vis. Comput. 2019; 87: 47–56.
14. Viju VR, Radha. License plate recognition based on K-means clustering algorithm. Intell. Syst. Ref. Libr. Springer 2019; pp. 23–29.
15. Yousif BB, Ata MM, Fawzy N, Obaya M. Toward an optimized neutrosophic k-means with genetic algorithm for automatic vehicle license plate recognition. IEEE Access. 2020; 8: 49285–49312.
16. Zhang L, Wang P, Li H, Li Z, Shen C, Zhang Y. A Robust attentional framework for license plate recognition in the wild. IEEE Transactions on Intelligent Transportation Systems, 2020; 22(11): 6967-6976
17. Agbeyangi AO, Alashiri OA, Otunuga AE. Automatic identification of vehicle plate number using Raspberry Pi. Int. Conf. Math. Comput. Eng. Comput. Sci. (ICMCECS); 2020; Institute of Electrical and Electronics Engineers Inc. pp. 1-4.
18. Fernandes LS, Silva FHS, Ohata EF, Medeiros A, Neto AVL, Nogueira YLB, Rego PAL, Filho PPR. A Robust automatic license plate recognition system for embedded devices. Lect. Notes Comput. Sci. (Including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics). Springer Science and Business Media Deutschland GmbH 2020; 226-239.
19. Izidio DMF, Ferreira AP, Medeiros HR, Da EN, Barros S. An embedded automatic license plate recognition system using deep learning. Des. Autom. Embed. Syst. 2020; 24: 23–43.
20. Castro-Zunti RD, Yépez J, Ko SB. License plate segmentation and recognition system using deep learning and OpenVINO. IET Intell. Transp. Syst. 2020; 14: 119–126.
21. Weihong W, Jiaoyang T. Research on license plate recognition algorithms based on deep learning in complex environment. IEEE Access. 2020; 8: 91661–91675.
22. Ma L, Zhang Y. Research on vehicle license plate recognition technology based on deep convolutional neural networks. Microprocessors and Microsystem 2021; 82: 103932.
23. Rafique AM, Pedrycz W, Jeon M. Vehicle license plate detection using region-based convolutional neural networks. Soft Computing 2018; 22: 6429-6440.
24. Yaman S, Karakaya B, Erol Y. A novel normalization algorithm to facilitate pre-assessment of Covid-19 disease by improving accuracy of CNN and its FPGA implementation. Evolving Systems.Springer Berlin Heidelberg 2023; 8(14): 581-591.
25. Microsoft. Microsoft Research Cambridge Object Recognition Image Database, 2021.
26. Bengio Y. Practical recommendations for gradient-based training of deep architectures, Lecture notes in computer Science. Berlin, Heidelberg: Springer, 2012.