Based on the technology of recognizing images and characters, the vehicle license plate recognition system is a kind of intellgent transportation management system, one of the focused researches on application of pattern recognition. In this article, some new algorithms and methods are introduced in such stages as pre-processing of images, feature extraction ,character classification and recognition. At the same time, some crucial problems of technology were overall discussed, for example, the new algorithm of segmen-tation is used on different color channels to detect the region of vehicle license plate. With color information of original images and templates of corners, to segment the region of license plate from complex background is processed speedily and automatically. And, some effective methods of feature t~xti~wiiui, such as-the one based ~n lm~ge-trTmwI1tI1Ii~ invariant features which keep stable while the picture move, rotate and zoom in or out, the method by calculating the central moment of image, and the others which is focused on the shape of character and features of direction. Experiment result indicates that the minimum-distance- matching algorithm used in the recognition system of character is reliable and efficient. Meanwhile, the current situation of the research project and a practical car license plate recognition system are introduced in detail.
|