Super Resolution Method on Vehicle Number-Plate

Date
2020
Research Supervisor
Editor
Journal Title
Volume
Issue
Journal Title
Journal ISSN
Volume Title
Abstract
Nowadays, it’s hard to capture an object with a mid-range phone or camera within a second, mostly when an incident occurs or when you’re trying to track traffic, and someone violates the traffic rules or commit a crime, it is a high chance that you will capture a hazy or blurry image, which might not be enough to identify the crime scene or collect necessary information of the violator. To end this, we created a project using recent deep learning approaches to obtain photorealistic results, which will help users identify necessary information from an object (.i.e, Vehicle number-plate). In our project, we focused on Vehicle number-plate. In Our project, we implemented a method using a generative adversarial network(GAN), name ProGanSR that is progressive both in architecture and training.
Description
Keywords
Citation
Department Name
Electrical and Computer Engineering
Publisher
North South University
Printed Thesis
DOI
ISSN
ISBN