License plate location based on direction and edge information

License plate recognition systems have been used extensively for many applications. In order to recognize a license plate efficiently, however, the location of the license plate must be detected in the first place. In our method, the car image first is divided into a set of 5×5 non-overlapping block and a local direction is defined for each block. The M×N car image is converted to a direction image and a vertical edges image of size (M×N)/25. It reduces much processing time. The direction and the vertical edges of block are calculated by using Sobel operator. We remove most of the background and noise regions in the direction and vertical edges image by an effective algorithm and segment the plate out from the original car image. Experimental results demonstrate the great robustness and efficiency of the method.