A smart hybrid license plate recognition system based on image processing using neural network and image correlation

In this paper, I propose a novel hybrid approach of license plate recognition system based on Neural Network and Image Correlation for classification of characters. I used image processing for segmentation. The purpose of this study is to develop a more reliable hybrid system than individual one. The license plate number of the vehicles taken from an acceptable distance from it up to 10m. This hybrid system that is composed of transformation to gray level, histogram equalization, thresholding and some novel algorithms in finding the character of license plate number. These novel algorithms were successively integrated in such a way as to complement with morphological image processing methods. However, Image correlation and neural network with LVQ (Learning Vector Quantization) learning methods were used for template matching extracted from license plate number. The novel algorithm makes powerful increase on success rate of template matching. It extracts features (area, centroid i.e.) of object and then uses them to eliminate noise and extract characters. Experimental results show the hybrid system is quite successful in recognizing private Turkish license plates.