Vehicles' License Plate Recognition Based On Digital Image Processing

Research on vehicles' plate license recognition system (LPRS) involves techniques such as digital image processing, computer seeing, pattern recognition and artificial intelligence etc. LPRS plays an important role in intelligent traffic control system, and it can be applied in vehicle management in situations of all levels and all kinds.LPRS consists of three modules in general, those are: license plate locating, character segmentation and character recognition. Algorithms of all modules related to LPRS is deeply studied and analyzed in this paper. And, we finally settle down a series of algorithms used in LPRS based on our research.Deal with license plate locating, color segmentation is applied at first according to the value range of the three elements in HSV color space. And then, mathematics morphological operation is adopted in order to get some continuous areas. At last, these continuous areas' shape and texture features are analyzed so as to gradually filtrate disturbed areas. The method fully considers the difference of the color, shape and texture features between license and background. So we can separate plate area form the nearby areas whose color and texture are different. In character segmentation, we propose a method which is based on projection and pre-known knowledge of the character size and the space between characters in plate. Also, a method is proposed to deal with those characters that are broken or combined together. In single character recognize, we apply improved BP neural networks to carries out the recognition of letters and numbers in the license plate.Since the algorithms adopted in LPRS are very complex commonly, it's very difficult to program using advanced language directly. So we use interface between VC++ and Matlab to realize our algorithms. By using Matlab compiler, we can generate redistributable, stand-alone application that does not require Matlab at run-time. The application can be run even if Matlab is not installed on the end-user's computer. By which way, we are save form the boring programming. So, we are able to concentrate on the study of the algorithms used in LPRS.