Dissertation > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Information processing (information processing) > Pattern Recognition and devices > Image recognition device

Research on the Auto-Recognition Technology of Vehicle License Plate

Author FangPeiYu
Tutor XuQuanSheng
School Shenyang University of Technology
Course Computer technology
Keywords Vehicle License Plate Vehicle License Plate Location Character Recognition
CLC TP391.41
Type Master's thesis
Year 2007
Downloads 325
Quotes 1
Download Dissertation

The subject of the automatic recognition of vehicle license plate is one of the most important subjects that are improved from the connection of computer vision and pattern recognition. The images inputted to the computer is disposed and analyzed in order to recognize the characters on the number-plate and completed the characters segmentation and recognition. At last the vehicle license plate number is printed in text string according to the order of original images. This technology is the key context of intelligent traffic management system and it is high valuable in practice.In this paper, various of methods in image manipulation are compared and analyzed, then come out the resolutions for localization of the car plate extraction and isolation of the characters and recognition of the characters. The experiences show that the good result has been got with these methods. The methods based on edge map and frequency analysis is used in the process of the localization of the car plate. That is to say, extracting the characteristics of the car plate in the car images after being double-checked up for the edge, and then analyzing and processing until the accurate area of car plate is extracted. The method of vehicle license plate location based on HSV colorful feature is presented, too. The fusion ruler fusing edge detection in gray space and colorful feature in HSV space is researched in this paper in order to improve the location accuracy. When extracting and isolating the characters, many foregone knowledge is utilized. The following steps are adopted sequentially: binary processing and wiping off noise using the bubble-method. A lot of ways for recognition of the characters are adopted in the third step mainly including modal matching tree classifier and neural network. Each method is used single or combined with the others to realize the recognition of the Chinese character letters and Arabic numerals on the number plate.The subject is meaningful according that the number-plate to the vehicle is similar with the ID card to the citizen, so the automatic recognition system of the number-plate characters can be used in any cases that connected with the management of the vehicles.

Related Dissertations
More Dissertations