Study On License Plate Recognition System Based On Rough Set

1. IntroductionIn recent years, intelligent traffic system is becoming increasingly important with the increase of traffic as well as the development of the economics. The crowded urban traffic needs more advanced and more effective traffic administration and control system. Automatic license plate recognition system, a technology which can be avidly applied to areas such as traffic administration department, speedway, bridge, electron policeman and custom, etc, is therefore a vital component in ITS and promises a bright outlook.Vehicles'License Plate Recognition System is an important application of computer vision and pattern recognition in the intelligent transportation management. The rough sets can analyze and deal with vagueness, disaccord and uncertainty information, discover the connotative rule. Neural network is widely used in pattern recognition for the better generalization ability. So the research on LPRS based on the combination of rough set and neural network is very meaningful and practical.The main important technology of LPRS consists of three modules in general, those are license platelocating, character segmentation and character recognition .License plate locating is the basic and premiss of the last two steps, and directly affects the process of the last two steps. Character segmentation determines the validity of character recognition.Two effective character recognition methods are presented. In the first method, rough set is used to solve the knowledge acquisition and reduction, and neural network is used to solve the pattern recognition. the second, a rough fuzzy neural network classifier is introduced, rough set, neural network and fuzzy logic. It can efficiently improve recognition rate of the LPRS, which combines the robustness and recognition rate of the LPRS.2. Research ContentThis paper has studied a lot of method and theory about vehicle plate characters recognition system , considering the characteristic of our vehicle plate, using Intelligent Intormation Processing Technologies to solve difficulty in vehicle plate characters recognition system. A suit of scheme about vehicle plate characters recognition system was proposed. Main research contents are as follows:(1) Analyzing about the characteristic of our vehicle plate. There are three kinds of objects about vehicle plate characters, there are Chinese characters, letters and number. And this paper only discuss the civil vehicle plate. The Chinese characters of civil vehicle plate contain about"京,津,晋,冀,�'�,辽,吉,黑,沪,苏,浙,皖,闽,赣,鲁,豫,鄂,湘,粤,桂,琼,川,贵,云,藏,陕,甘,�',宁,新,渝"(31), the number contain about"0~9", the letters contain about from"A"to"Z", besides"I"and"O".(2) After discussing the theory of Artificial Neural Network, the method of license plate location base on rough sets and Artificial Neural Network was proposed. In this way that licence plateloating is very effective and accurate through the operation.(3) Skew corrected, character segmentation and normalization are very important before character recognition. Before skew correction it is essential to enhanced the contrast through histogram equalization, so the edge of the image will not disappear after Hough transform. And after that, use Hough transform to correct angle of the image. Character segmentation implement in the character width and projection method Experimental result indicates that this method is very effective.(4) Optimization based on Neural Networks character recognition.The introduction of one of the rough set of characters to indentify categories. The rough fuzzy neural network classifier is introduced,which combines the rough set,neural network and fuzzy logic. It can efficiently improve the robustness and recognition rate of the LPR system.3.ConclusionLicense plate location and vehicle plate characters recognition are key technology of vehicle plate characters recognition system. This paper is mainly about them. Thesis to improve the traditional method of license plate location, the algorithm can be more accurate positioning of the plate, but in dealing with license plate recognition, there are still some questions. At present, the industry has a lot of about License Plate Recognition and positioning of the algorithm, but because of the complexity of these algorithms than the larger, with a combination of rough set to be further studied. In this paper, the character segmentation system partition line preprocessing can be applied to the majority of license plates, but the characters thin partition apply only to a small car license plate, license plate for large cars is not for discussion.