Please use this identifier to cite or link to this item:
Title: Number Plate Detection and Recognition using Scale Invariant Feature Transform
Authors: Balendren, P.
Issue Date: 29-Oct-2013
Abstract: A Number plate recognition (NPR) system plays an important role in numerous applications, such as parking accounting systems, traffic law enforcement, road monitoring and security systems. In this research work, a real time method is proposed to detect and recognize the number plates. Computer vision has played a crucial part in the design of this system. The proposed algorithm consists of two major parts: Extraction of plate region and Recognition of plates in the database. Initially, the captured image from the camera is converted into gray scale images. The gray scale images are preprocessed to enrich the edge features after that extracted out the vertical edges of the car image using image enhancement and Sobel operator, and then some morphological operations are used to remove noise in the vertically edged binary images. Characteristic features such as number plate width and height, character height and spacing between are considered for defining structural elements for morphological operations. Connected component analysis is then used to select the band containing number plate from the candidate segmented. Finally the SIFT method is used to extract the local invariant features of the image labels and recognition is done by matching the extracted features with the stored features of the number plate images in the database. This system can be used for parking accounting systems, security systems and search for stolen cars. The performance of the proposed system has been tested on real images. The MATLAB® implementation of this system handles front and rear view of the car images. This system has been trained and tested using the Sri Lankan number plates and the results are effective in detection as well as recognition. 93% of number plates are detected and 88% of them are recognized by the system.
Appears in Collections:Master of Computer Science - 2009

Files in This Item:
File Description SizeFormat 
Final dissertation.doc
  Restricted Access
7.4 MBMicrosoft WordView/Open Request a copy

Items in UCSC Digital Library are protected by copyright, with all rights reserved, unless otherwise indicated.