License Plate Characters Segmentation Using Projection and Template Matching

This paper presents a new method for Car License Plate Characters' Segmentation. The proposed approach is not only simple but also more effective than some of the existing method reported earlier. The novelty lies in this case in its treatment which not only unites the projection and template match, but also improves the techniques. The quality of image that be shot in the natural environment is poor generally. Therefore, the license characters may be broken, adhesive or hid partially. Projecting the image to horizontal direction can detects the approximate edge of single license character in the vertical direction. Then design a template on basis of prior knowledge about the license plate, and take similarity measure to match the image segmented by projection. As a result, we can get the template that its similarity is the best. License characters re-segmentation can be implemented by the best similar template standard. Tests have shown that the method has a wide adaptability and robustness. It could get the optimization matching location to segment the characters.