A New Methodology for License Plate Recognition

摘要

License plate localization process is carried out by weight based density map method (WBDM). This new approach is capable of recognizing license plates in different conditions and it relaxes some constraints in the conventional methods like the size and colour of the plate, style of the characters, position of the vehicle environment lighting etc. Compared to existing methods, proposed approach gives 98% of matching ratio in different constraints while recognizing the license plate in 19.86 second. It shows this approach is efficient in both space and time, making it suitable for any real time applications. This method car easily be improved to identify multiple number plates in a single image.