Skip to main content
SpringerLink
Log in

FPGA implementation of proposed number plate localization algorithm based on YOLOv2 (You Only Look Once)

  • Technical Paper
  • Published:
Microsystem Technologies Aims and scope Submit manuscript

Abstract

Many algorithms used in machine learning and artificial intelligence rely on exact object identification and recognition as their foundation for efficiency and accuracy. Hardware implementation of such methods, when implemented, serves to boost the reliability and productivity of object detection in a wide range of contexts. Hardware implementation of such an algorithm takes a lot of resources and a huge amount of calculation time. The object detection and recognition process require a collection of complex algorithms and a series of filtering approaches to work beyond the boundary conditions. The YOLOv2 network is superior to filters and complicated algorithms for this problem. The authors of this study propose an enhanced YOLOv2 Network for object recognition and a novel approach for optimising the existing YOLOv2 Network for localization to pinpoint the ROI that can be used to scale down and contain the object's original area. The network is proposed by configuring the existing YOLOv2 with additional convolution layers and dropout layers. The dropout layers are added to reduce the dependency on a single neuron and is an effective way of preventing overfitting of the network. Also, instead of ReLU as the activation function, we are using the Swish activation function which tends to provide better results. By isolating and producing the region of interest (ROI) from the original image, the algorithm was able to significantly cut down on both the number of resources needed and the time needed to complete the task. The proposed work is implemented on an FPGA board (Xilinx Zynq-Z7010 FPGA board), and the dataset is collected and prepared by the authors. Data augmentation is done to enhance the training data to enhance the training data, which results in better trained network. MATLAB is used to demonstrate the feasibility of the work and provide a thorough evaluation of its merits. The results show that the accuracy of the conventional algorithm approach drops to 20–30% once you move outside the boundaries, whereas the accuracy of the proposed work increases to 60–70% and a 15–20% increase in efficiency with proposed network based on YOLOv2. The proposed algorithm is three times as fast as the standard method while using only 35 percent as much technology.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

References

  • Ahmad A, Ullah A, Feng C, Khan M, Ashraf S, Adnan M, Khan HU (2020) Towards an improved energy efficient and end-to-end secure protocol for iot healthcare applications. Secur Commun Networks. https://doi.org/10.1155/2020/8867792

    Article  Google Scholar 

  • Albawi S, Mohammed TA, Al-Zawi S (2017) Understanding of a convolutional neural network. In: 2017 International Conference on Engineering and Technology (ICET), 2017, pp 1–6, https://doi.org/10.1109/ICEngTechnol.2017.8308186

  • Amrouche A, Hezil N, Bentrcia Y, Abed A (2022) Real-time detection of vehicle license plates numbers. In: 2022 2nd International Conference on New Technologies of Information and Communication (NTIC), Mila, Algeria, 2022, pp 1–5, https://doi.org/10.1109/NTIC55069.2022.10100479

  • Ashraf S, Saleem S, Chohan AH, Aslam Z, Raza A (2020a) Challenging strategic trends in green supply chain management. Int J Res Eng Appl Sci JREAS 5(2):71–74

    Google Scholar 

  • Ashraf S, Ahmed T, Aslam Z, Muhammad D, Yahya A, Shuaeeb M (2020b) Depuration based efficient coverage mechanism for wireless sensor network. J Electr Comput Eng Innov (JECEI) 8(2):145–160

    Google Scholar 

  • Bellas N, Chai SM, Dwyer M, Linzmeier D (2006) FPGA implementation of a license plate recognition SoC using automatically generated streaming accelerators. In: Proceedings 20th IEEE International Parallel & Distributed Processing Symposium, 2006, p 8, https://doi.org/10.1109/IPDPS.2006.1639437

  • Deng L (2014) A tutorial survey of architectures, algorithms, and applications for deep learning. Found Trends® Signal Process 7(3–4):197–387. https://doi.org/10.1561/2000000039

    Article  Google Scholar 

  • He L, Chao Y, Suzuki K (2011) Two efficient label-equivalence-based connected-component labeling algorithms for 3-D binary images. IEEE Trans Image Process 20(8):2122–2134. https://doi.org/10.1109/TIP.2011.2114352

    Article  MathSciNet  MATH  Google Scholar 

  • He K, Zhang X, Ren S, Sun J (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37(9):1904–1916. https://doi.org/10.1109/TPAMI.2015.2389824

    Article  Google Scholar 

  • Histograms of Oriented Gradients for Human Detection (2005) Conference on computer vision and pattern recognition, 2005

  • Mikołajczyk A, Grochowski M (2018) Data augmentation for improving deep learning in image classification problem. In: 2018 International Interdisciplinary PhD Workshop (IIPhDW), Świnouście, Poland, 2018, pp 117–122, https://doi.org/10.1109/IIPHDW.2018.8388338

  • Najafian B, Sani MSM (2019) a review on object detection and recognition using deep learning techniques. In: 2019 IEEE 6th International Conference on smart instrumentation, measurement and applications (ICSIMA), 2019, pp. 384–389, https://doi.org/10.1109/ICSIMA48156.2019.9079006

  • Nepal U, Eslamiat H (2022) Comparing YOLOv3, YOLOv4 and YOLOv5 for autonomous landing spot detection in faulty UAVs. Sensors (basel) 22(2):464. https://doi.org/10.3390/s22020464. (PMID: 35062425; PMCID: PMC8778480)

    Article  Google Scholar 

  • Peemen M et al (2017) A comparison of FPGA and ASIC implementations of SHA-256. In: 2017 IEEE International Symposium on circuits and systems (ISCAS), Baltimore, MD, 2017, pp 1–4, https://doi.org/10.1109/ISCAS.2017.8050835

  • Qiao J et al (2021) A survey of FPGA-based deep learning: trends and prospects. IEEE Trans Neural Netw Learn Syst 32(3):808–821. https://doi.org/10.1109/TNNLS.2020.2979025

    Article  MathSciNet  Google Scholar 

  • Ramachandran P, Zoph B, Le QV (2017) Swish: a self-gated activation function. arXiv. https://doi.org/10.48550/arXiv.1710.05941

  • Ramos LA, de Souza GB, Marana AN (2015) Shape analysis using multiscale hough transform statistics. In: Progress in pattern recognition, image analysis, computer vision, and applications: 20th Iberoamerican congress, CIARP 2015, Montevideo, Uruguay, 9–12 Nov 2015, Proceedings 20. Springer International Publishing, pp 452–459

    Chapter  Google Scholar 

  • Redmon J, Farhadi A (2017) YOLO9000: better, faster, stronger. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp 6517–6525, https://doi.org/10.1109/CVPR.2017.690.

  • Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, LeCun Y (2014) OverFeat: integrated recognition, localization and detection using convolutional networks. In: 2014 International Conference on Learning Representations (ICLR), Banff, AB, 2014

  • Shi L, Wu H, Li Z, Zhang J (2014) Vehicle license plate recognition based on SIFT feature and SVM classifier. In: International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, 2014

  • Srivastava N, Hinton GE, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15:1929–1958

    MathSciNet  MATH  Google Scholar 

  • Vargas M, Toral SL, Barrero F, Cortés F (2009) A license plate extraction algorithm based on edge statistics and region growing. In: International Conference on Image Analysis and Processing (ICIAP), pp 317–326, 2009

  • Vassiliadis S (2015) FPGAs vs. ASICs: A technical comparison. In: 2015 International Conference on Field-Programmable Technology (ICFPT), Queenstown, 2015, pp 7–14, https://doi.org/10.1109/ICFPT.2015.7393152.

  • Zhai X, Benssali F, Ramalingam S (2010) License plate localisation based on morphological operations. In: 2010 11th International Conference on control automation robotics & vision, Singapore, 2010, pp 1128–1132, https://doi.org/10.1109/ICARCV.2010.5707933

  • Zhang C, Wang J (2009) An approach to license plate detection based on region growing and feature clustering. In: International Conference on computer and information technology, 2009

  • Zhang Y, Qiu M, Ni Y, Wang W (2020) A novel deep learning based number plate detect algorithm under dark lighting conditions. In: 2020 IEEE 20th International Conference on communication technology (ICCT), Nanning, China, 2020, pp 1412–1417, https://doi.org/10.1109/ICCT50939.2020.9295720.

Download references

Acknowledgements

We are thankful to SERB-DST, New Delhi for providing a grant under the TARE scheme. Grant No: SERB/F/11697/2018-19 dated 27 February 2019. We are also thankful to Devi Ahilya University, Indore for providing financial support under Seed Money -2 scheme with file no Dev/Seedmoney2.0/2020-21/664.

Author information

Authors and Affiliations

  1. IET-Devi Ahilya University, Indore, MP, India

    Vaidik Panchal, Himanshu Sankla & Priyanka Sharma

  2. E&TC Engineering Department, IET-Devi Ahilya University, Indore, MP, India

    Vaibhav Neema & Ashish Panchal

  3. Department of Computer Science, Electrical & Space Engineering, Luleå University of Technology, 97187, Luleå, Sweden

    Shailesh Singh Chouhan

Authors
  1. Vaidik Panchal
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Himanshu Sankla
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Priyanka Sharma
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Vaibhav Neema
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Ashish Panchal
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Shailesh Singh Chouhan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Vaibhav Neema.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Panchal, V., Sankla, H., Sharma, P. et al. FPGA implementation of proposed number plate localization algorithm based on YOLOv2 (You Only Look Once). Microsyst Technol 29, 1501–1513 (2023). https://doi.org/10.1007/s00542-023-05506-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00542-023-05506-w

Search

Navigation