The Performance Improvement of License Plate Recognition System Using Composite Color and Artificial Hippocampus Algorithm

The goal of this paper is to improve the performance of a system which recognizes the license plate. In this paper, we suggest the system using composite color and an artificial hippocampus algorithm for license plate recognition. Before extraction with image, the system first operates histogram equalization in pre-processing for the equal distribution of intensity value. After the pre-processing, the system extracts the license plate region using color models which are RGB, HSI and YIQ. The extracted region again is extracted to a letter/number region using horizontal and vertical histograms. Therefore, the system recognizes the letter/number of license plate using artificial hippocampus algorithm. Experimental results with input images are reported to demonstrate the accuracy and robustness of the proposed algorithm.