Automated parking lot management for Bengali license plates using hough transformation and image segmentation

Abstract

This paper is on automated parking lot management system for Bengali language based on vehicle number plate recognition. The need for an efficient parking system stems from increased congestion, motor vehicle pollution. The aim of this research is to develop and implement an automatic parking system that will increase convenience and security of the parking lot with minimum human involvement. This is done with the combination of automated license plate recognition and database manipulation. The image is acquired from a live video feed by comparing frames for significant changes. Then it is passed through several steps including some different types of algorithms and methodologies such as Canny Edge Detection, Connected Component Labeling and Hough Transformation to localize the license plate. Subsequently the license plate is progressed through Character Segmentation and Pattern Recognition to extract the data for manipulating and computing using database to manage the parking lot system efficiently. The system was experimented on 20 different license plates and the algorithms worked correctly in all cases with a very good response time.