License plate detection using deep learning object detection models

Leong, Kar Wan (2024) License plate detection using deep learning object detection models. Master dissertation/thesis, UTAR.

Preview

PDF Download (1474Kb) | Preview

Abstract

Object detection – an extension of image classification task in computer vision can locate any object from any given image input. In the past, this is usually done by traditional hand-crafted feature algorithms i.e., SIFT, SURF, HOG, BRIEF, and ORB. These algorithms have been successful in their field however they do possess some downsides due to their nature. For example, they can be slow in detection speed, not as accurate, and is difficult to develop. Since 2012, deep learning has become an emerging technology that can solve object detection with relatively better performance. However, not many works has been done when it comes to developing a real life application e.g., license plate detection. License plate detection is a challenging task in computer vision because the input image captured can be in different sizes, color, distance, orientation, and lighting condition. This project aims to study and improve license plate detection using deep learning models. As of current year, the model YOLOv4 has achieved 43.5% AP on MS COCO. Meanwhile, EfficientDet-D7 has achieved 55.1 AP on COCO test-dev. This project will use the available offthe-shelves object detection model to train on CCPD license plate dataset. The impact of this project is that it provides informative insights and uncover the potential of the development of real-life applications using recent deep learning object detection models.

Actions (login required)