International Journal of Applied Information Systems |
Foundation of Computer Science (FCS), NY, USA |
Volume 5 - Number 1 |
Year of Publication: 2013 |
Authors: Khaled M. Almustafa |
10.5120/ijais12-450839 |
Khaled M. Almustafa . On the Automatic Recognition of Saudi License Plate. International Journal of Applied Information Systems. 5, 1 ( January 2013), 34-44. DOI=10.5120/ijais12-450839
In this paper three different algorithms for Automatic License Plate Recognition (ALPR) of the Saudi License Plates are described. All algorithms rely on processing information from lines strategically drawn vertically and horizontally through a character. The first algorithm calculates the number of peaks for each line. A peak is a place in the line where the pixels change from black to white. The second algorithm calculates the pixels density for a specific crossing line in a character. Pixel density is defined as the number of pixels having a specific intensity level to the total number of pixels in a line. The third algorithm calculates the position of the peaks introduced in the first algorithm rather than only their numbers. An algorithm was developed for each method to differentiate between all characters of the license plate. Uniformly distributed pseudo-random noise was added to simulate the performance of these algorithms in the presence of noisy images, also performance of the suggested algorithms were tested due to image rotation. A comparison between these algorithms also presented. These algorithms were proven to work even in some cases in which the characters were extremely degraded by noise.