Recognition of Ethiopian Car Plate
No Thumbnail Available
Date
2013-04
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Addis Ababa University
Abstract
As time goes, application areas of information and communication technologies are growing dramatically as well. In these days, every potential problem is automated or it is being automated in order to solve or make things better. In the area of transportation systems, a lot of applications have been developed with development of communication and information processing technologies, officially called Intelligent Transportation Systems (ITS). In this work, one of the fundamental elements of ITS called Car Plate Recognition (CPR) is developed for Ethiopian car plates. The proposed system has three major modules: Plate Detection, Character Segmentation and Character Recognition. For plate detection, a gabor filter based method is proposed. In this module, even though, the gabor filter is the core unit that roughly locates possible plate regions, the module also applies a series of other techniques, namely, binarization, morphological closing operation and connected component analysis consecutively on the filter response, to detect the legitimate plate region. For character segmentation process a connected component analysis method is used. But before, the actual segmentation process, the plate image passes through a number of preprocessing tasks that dramatically increase the accuracy of the segmentation outcome. Of these preprocessing tasks plate’s orientation correction and plate’s frame removal are the major ones. For plate’s orientation correction we used a combination of hough transform and shear transform. For plate’s frame elimination we used a series of binary operations. Besides these preprocessing tasks, the module performs further post segmentation operations that are done in the segmentation outcome of the CCA. The main objective of the post segmentation stage is to separate connected character objects (if any exists) with the help of plate structure information. Finally, a correlation based template matching method is used for character recognition. In addition to the correlation value, the recognition process is supported by color analysis techniques and location information of characters. The prototype of the proposed system is developed using MATLABTM and its performance is tested on 350 RGB car images that are taken under different angle, distance, motion and illumination conditions. The developed system results in an accuracy of 63.14% and also it is able to recognize a plate between 2-5 seconds depending on whether post processing operations are needed or not. Keywords: Ethiopian Car Plates, Ethiopian Car Plate Recognition, License Plate Recognition, Plate Detection, Plate Characters Segmentation, Character Recognition, Plate’s Frame Elimination, Ethiopian Car Plate Type Identification
Description
Keywords
Ethiopian Car Plates, Ethiopian Car Plate Recognition, License Plate Recognition, Plate Detection, Plate Characters Segmentation, Character Recognition, Plate’s Frame Elimination, Ethiopian Car Plate Type Identification