Automatic car plate number recognition system

• Main Author: Lim, Hui Zhong.
• Other Authors: Ong Keng Sian, Vincent
• Format: Final Year Project
• Language: English
• Published: 2012
• Subjects: DRNTU::Engineering::Electrical and electronic engineering::Control and instrumentation::Control engineering
• Online Access: http://hdl.handle.net/10356/50178
• Institution: Nanyang Technological University

In this report, different methods of license plate detection are considered and studied. These methods would not be implemented in an Automatic Number Plate Recognition (ANPR) system. However, the methods discussed and proposed here are practical solutions for license plate detection and extraction. The Automatic Number Plate Recognition system would identify the position of a vehicle’s license plate. The license plates are identified irrespective of their colour as an edge detector is used to find the left and right edges of the plate and extract the region between them. Low quality images due to severe illumination conditions, viewpoint, vehicle motion, complex background and other factors are some of the usual problems encountered in identifying the car plate region. In order to alleviate these problems, different image enhancement methods are proposed, using intensity variance, edge density and gray level slicing. The aim is to increase contrast of plate-like regions to avoid missing plate location especially in poor quality images. Furthermore, a complex matching filter is designed to detect candidate regions as license plate. As the filtering procedure is simple, this approach can be used for real-time applications. The proposed methods and algorithm would be for the most important part of ANPR system which is the license plate detection and extraction.