Abstract

The rapid transformation of urban environments across India has led to a sudden surge in vehicular traffic, creating unforeseen challenges for traffic management, law enforcement, and the development of smart city infrastructure. Conventional license plate recognition systems are tested by India’s unique challenges, such as multi-regional scripts, varying plate formats, harsh weather conditions, and variable traffic flows. This paper introduces an end-toend Automatic Number Plate Recognition (ANPR) system tailored to Indian road conditions, with the state-of-the-art YOLOv11 object detection framework coupled with EasyOCR’s robust character recognition module. Our new method addresses practical application use cases in a well-organized pipeline with cutting-edge image preprocessing methods, such as Contrast Limited Adaptive Histogram Equalization (CLAHE) and smart skew correction methods. Our method was extensively trained and validated on the massive Roboflow Indian License Plate Dataset under a broad spectrum of conditions, from disorderly urban settings to difficult rural settings. The test results are superior, with a mean Average Precision (mAP) of 92.4% for license plate detection and 88.2% accuracy in character recognition. The system comes as a surprise with the capability of real-time processing with a high inference speed of 43 milliseconds per frame, making it extremely appropriate for use in traffic monitoring systems, automated toll booths, and security systems. Comparison to existing YOLOv5 and YOLOv8-based systems is significantly better in terms of accuracy and computational cost. Modular architecture allows seamless integration with existing smart city infrastructure and, at the same time, provides room for flexibility for future upgrades and the addition of multilingual support.

References

• C. N. E. Anagnostopoulos, I. E. Anagnostopoulos, I. D. Psoroulas, V. Loumos, and E. Kayafas, “License plate recognition from still images and video sequences: A survey,” IEEE Trans. on Intelligent Transportation Systems, vol. 9, no. 3, pp. 377–391, 2008.
• R. O. Duda and P. E. Hart, “Use of the Hough transformation to detect lines and curves in pictures,” Commun. of the ACM, vol. 15, no. 1, pp. 11–15, 1972.
• Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015.
• A. Vaswani et al., “Attention is all you need,” in Advances in Neural Information Processing Systems, 2017, pp. 5998– 6008.
• J. Redmon et al., “You only look once: Unified, real-time object detection,” in Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 2016, pp. 779–788.
• A. Bochkovskiy et al., “YOLOv4: Optimal speed and accuracy of object detection,” arXiv:2004.10934, 2020.
• R. Khanam and M. Hussain, “YOLOv11: An overview of the key architectural enhancements,” arXiv:2410.17725, 2024.
• G. Jocher, “ultralytics/yolov5,” GitHub, 2022. [Online]. Available: https://github.com/ultralytics/yolov5
• Ultralytics, “YOLOv8 documentation,” 2023. [Online]. Available: https://docs.ultralytics.com
• R. Laroca et al., “An efficient and layout-independent automatic license plate recognition system based on the YOLO detector,” arXiv:1909.01754, 2019.
• R. T. Vempati, “Real-time detection and recognition of license plates using YOLOv11,” Kansas State Univ., 2024. [Online]. Available: https://krex.k-state.edu/
• P. P. Reddy et al., “License plate detection using YOLO v8 and performance evaluation of EasyOCR, PaddleOCR and Tesseract,” in Proc. Int. Conf. on Artificial Intelligence and Data Engineering, IEEE, 2024.
• E. I. Singh et al., “Recognition system: Detection of license plate,” in Proc. ICCPCT, IEEE, 2024, pp. 171–177.
• M. Thatikonda, “An enhanced real-time object detection of helmets and license plates using YOLOv8,” M.S. thesis, Wright State Univ., 2024.
• R. Smith, “An overview of the Tesseract OCR engine,” in Proc. Int. Conf. on Document Analysis and Recognition, 2007, pp. 629–633.
• J. Hwang and J. Park, “EasyOCR: Ready-to-use OCR with 80+ supported languages,” GitHub, 2020. [Online]. Available: https://github.com/JaidedAI/EasyOCR
• J. Du et al., “PaddleOCR: A practical ultra-lightweight OCR system,” arXiv:2109.03144, 2021.
• K. Anand et al., “Virtual toll booth based on number plate recognition using YOLO V8 and EasyOCR,” in Proc. ICDSAAI, IEEE, 2023, pp. 1–8.
• A. Nafis et al., “Automatic number plate recognition using YOLOv11,” Int. J. of Computer Techniques, vol. 12, no. 3, 2025.
• Roboflow, “Indian number plate detection dataset,” 2024. [Online]. Available: https://universe.roboflow.com/
• K. Zuiderveld, “Contrast limited adaptive histogram equalization,” Graphics Gems, pp. 474–485, 1994.
• R. C. Gonzalez and R. E. Woods, Digital Image Processing, 4th ed., Pearson, 2018.
• J. Davis and M. Goadrich, “The relationship between precision-recall and ROC curves,” in Proc. ICML, 2006, pp. 233–240.
• J. Huang et al., “Speed/accuracy trade-offs for modern convolutional object detectors,” in Proc. CVPR, 2017, pp. 7310– 7311.
• J. Jacob et al., “Quantization and training of neural networks for efficient integer-arithmetic-only inference,” in Proc. CVPR, 2018, pp. 2704–2713.
• G. Hinton et al., “Distilling the knowledge in a neural network,” arXiv:1503.02531, 2015.
• M. Arshid et al., “A comparative study on detection and recognition of nonuniform license plates,” Big Data and Cognitive Computing, vol. 8, no. 11, art. 155, 2024.
• T. M. Al-Hasan et al., “Enhanced YOLOv8-based system for automatic number plate recognition,” Technologies, vol. 12, 2024.
• R. Singh and S. Thakur, “OCR post-processing using regexbased format correction for ANPR,” SSRN, 2021. [Online]. Available: https://papers.ssrn.com/
• N. Lubna et al., “Automatic number plate recognition: A detailed survey of relevant algorithms,” Sensors, vol. 21, no. 9, art. 3028, 2021.
• A. Zanella et al., “Internet of things for smart cities,” IEEE Internet of Things J., vol. 1, no. 1, pp. 22–32, 2014.