Design flow for robust license plate localization

Locating the vehicle license plate is a key step in any license plate recognition system. In order to build an efficient real time license plate detection system, important issues like existence of another text block in an image, sensitivity to license plate dimensions and adaptability of algorithm to license plate located anywhere in the image, need to be addressed. In this paper, we propose an algorithm to ensure success in these practical situations. It uses Mexican hat operator for edge detection and Euler number of a binary image for identifying the region of interest. A thorough testing of algorithm is performed on a database with varying test cases in terms of illumination and plate size. The results for license plate detection are encouraging with success rate of 94-99 %.