Cellular neural network based pre-processing for localization of non standard licence plate

Automatic license plate localization is one of the crucial steps for any intelligent transportation system. This requires a series of complex image processing steps in which edge detection plays major role in case of non standard license plate as the edges give crucial information regarding the location. In order to localize the license plate in real time, the amount of data to be processed must be minimized at the stage where the edges are identified. In this work we proposed Cellular Neural Network based edge detection for real time computation of edges. The performance of the proposed method has been tested in real time under various type of vehicles where number plate is located at different places. Based on the experimental results, we noted that our method shows superior performance in non standard license plate localization.