Please use this identifier to cite or link to this item: https://hdl.handle.net/2440/55770
Type: Report
Title: A scale invariant object detector: An implementation for license plate detection
Author: Gobara, Mohamed
Suter, David
Publisher: Monash University
Issue Date: 2003
Series/Report no.: Technical Report; MECSE-9-2003
School/Discipline: School of Computer Science
Statement of
Responsibility: 
Mohamed Gubara and David Suter
Abstract: In this paper we present a new method for 2D object detection. This method uses the Hough transform as a robust platform for edge detection and extends it in the scale space. This extension enables the Hough transform to detect the scale changes within an image. The method starts with a linear scale-space representation of the image. At each level of this space edges are extracted through a normalized derivative function and accumulated in the Hough space. Higher features are mapped from the Hough space into the spatial space and then tagged with a normalized descriptor. The feature with the maximum descriptor over scale is then selected as the object of interest The new approach is applied to the classical problem of the license plate detection. This problem is characterized by a unique solution that can be easily verified by the human observation.
Rights: © Monash University. The provision of electronic forms, via the web, is only for the purposes of scholarly study - any other use of this material is prohibited.
Appears in Collections:Computer Science publications

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.