License plate text localization using DWT and neural network

The license plate text automatic localization is one of the important research subjects in the intelligent transportation system. License plate texts provide highly condensed information about the contents of images. It proposes a license plate text localization method using discrete wavelet transform (DWT) and neural network. Because the DWT coefficients provide important information of text regions, this paper employs those coefficients and several image processing techniques to preliminarily locate candidate license plate text regions. Then the morphological dilation operation and the neural network are employed to raise the precision rate of the location for license plate text. The objective of the research is to increase the recognition rate of license plates and to improve the success rate of license plate locating. According to the experimental results, the proposed method can successfully locate text region from complex environment. It demonstrates the feasibility of this system and achieves 96% of the correct plate location rate.