PYRAMIDAL APPROACH TO LICENSE PLATE SEGMENTATION

Car identification is a goal in traffic control, transport planning, t ravel time measurement, managing parking lot traffic and so on. Most c ar identification algorithms contain a standalone plate segmentation p rocess followed by a plate contents reading. A pyramidal algorithm for license plate segmentation, looking for textured regions, has been de veloped on a PC based system running Unix. It can be used directly in applications not requiring real time. When input images are relatively small, real-time performance is in fact accomplished by the algorithm . When using large images, porting the algorithm to special digital si gnal processors can easily lead to preserving real-time performance. E xperimental results, for stationary and moving cars in outdoor scenes, showed high accuracy and high scores in detecting the plate. The algo rithm also deals with cases where many character strings are present i n the image, and not only the one corresponding to the plate This is d one by the means of a constrained texture regions classification. (C) 1996 SPIE and IS&T.