Next Article in Journal
Elements Influencing sEMG-Based Gesture Decoding: Muscle Fatigue, Forearm Angle and Acquisition Time
Previous Article in Journal
Connected Vehicles: Technology Review, State of the Art, Challenges and Opportunities
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

A Deep Learning Based Approach for Localization and Recognition of Pakistani Vehicle License Plates

1
Department of Software Engineering, University of Sialkot, Sialkot 51040, Pakistan
2
Department of Computer Science, COMSATS University Islamabad, Abbottabad Campus, Abbottabad 22044, Pakistan
3
Department of Electrical and Computer Engineering, COMSATS University Islamabad, Abbottabad Campus, Abbottabad 22044, Pakistan
4
Department of Software, Sejong University, Seoul 05006, Korea
5
School of Electrical Engineering, Korea University, Seoul 02841, Korea
6
Department of Software Engineering, University of Lahore, Lahore 54000, Pakistan
*
Authors to whom correspondence should be addressed.
These authors contributed equally to this work and are first co-authors.
Sensors 2021, 21(22), 7696; https://doi.org/10.3390/s21227696
Submission received: 3 September 2021 / Revised: 11 November 2021 / Accepted: 16 November 2021 / Published: 19 November 2021
(This article belongs to the Topic Intelligent Transportation Systems)

Abstract

License plate localization is the process of finding the license plate area and drawing a bounding box around it, while recognition is the process of identifying the text within the bounding box. The current state-of-the-art license plate localization and recognition approaches require license plates of standard size, style, fonts, and colors. Unfortunately, in Pakistan, license plates are non-standard and vary in terms of the characteristics mentioned above. This paper presents a deep-learning-based approach to localize and recognize Pakistani license plates with non-uniform and non-standardized sizes, fonts, and styles. We developed a new Pakistani license plate dataset (PLPD) to train and evaluate the proposed model. We conducted extensive experiments to compare the accuracy of the proposed approach with existing techniques. The results show that the proposed method outperformed the other methods to localize and recognize non-standard license plates.
Keywords: CNN; deep learning; license plate; localization; rectification; recognition; RNN CNN; deep learning; license plate; localization; rectification; recognition; RNN

Share and Cite

MDPI and ACS Style

Yousaf, U.; Khan, A.; Ali, H.; Khan, F.G.; Rehman, Z.u.; Shah, S.; Ali, F.; Pack, S.; Ali, S. A Deep Learning Based Approach for Localization and Recognition of Pakistani Vehicle License Plates. Sensors 2021, 21, 7696. https://doi.org/10.3390/s21227696

AMA Style

Yousaf U, Khan A, Ali H, Khan FG, Rehman Zu, Shah S, Ali F, Pack S, Ali S. A Deep Learning Based Approach for Localization and Recognition of Pakistani Vehicle License Plates. Sensors. 2021; 21(22):7696. https://doi.org/10.3390/s21227696

Chicago/Turabian Style

Yousaf, Umair, Ahmad Khan, Hazrat Ali, Fiaz Gul Khan, Zia ur Rehman, Sajid Shah, Farman Ali, Sangheon Pack, and Safdar Ali. 2021. "A Deep Learning Based Approach for Localization and Recognition of Pakistani Vehicle License Plates" Sensors 21, no. 22: 7696. https://doi.org/10.3390/s21227696

APA Style

Yousaf, U., Khan, A., Ali, H., Khan, F. G., Rehman, Z. u., Shah, S., Ali, F., Pack, S., & Ali, S. (2021). A Deep Learning Based Approach for Localization and Recognition of Pakistani Vehicle License Plates. Sensors, 21(22), 7696. https://doi.org/10.3390/s21227696

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop