Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/157158
Title: Car license plate recognition using deep learning
Authors: Tan, Jason Jit Hao
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2022
Publisher: Nanyang Technological University
Source: Tan, J. J. H. (2022). Car license plate recognition using deep learning. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/157158
Abstract: Emerging technologies towards smart vehicles and Intelligent Transportation System (ITS) have revolutionized many aspects of human life. One of the most important applications of the ITS includes Video Surveillance which is commonly used everywhere. By pairing it with Artificial Intelligence (AI), it may be enhanced and further developed into useful applications such as License Plate Recognition. Currently, there are insufficient license plate recognition systems that can be used to identify the car license plates of Singapore. Furthermore, there is a lack of publicly available datasets of Singapore car license plates. This study aims to explore and develop a model using deep learning methods to identify the characters of Singapore car license plates. With the focus on being lightweight and having fast performance, while maintaining sufficient accuracy for functional use. LPRNet fulfils this requirement by implementing a lightweight model which works without preliminary character segmentation. However, it will be compared with other engines such as Tesseract Optical Character Recognition (OCR) to distinguish the differences in speed and performance.
URI: https://hdl.handle.net/10356/157158
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
FYP Final Report JasonTan(U1921545F).pdf
  Restricted Access
2.73 MBAdobe PDFView/Open

Page view(s)

10
Updated on May 20, 2022

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.