License plate character segmentation method with combination of dynamic template and pixel points

Abstract

The invention discloses a license plate character segmentation method with the combination of a dynamic template and pixel points and belongs to the technical field of image processing. The method includes the steps that an input license plate image is binarized, so that the width w and the height h of a license plate are acquired, characters and the width and the height of the interval between every two adjacent characters of the license plate template are set on the basis of the character size and the interval size which are speculated in the standard of motor vehicle license plates, the height of the license plate template is h, the width w' is dynamically increased, the initial value of the width w' ranges from w / 3 to 2w / 3, template sliding processing is conducted on the license plate image based on the license plate template, and the number of the non-zero pixel points of the position of each character in the current sliding position and the current character segmentation position are recorded; the width w' is greatly increased, the setting of the aspect ratio of each character and the interval between every two adjacent characters of the license plate template is maintained, and template sliding processing is repeated till the with w' is increased to w; finally, the segmentation position including the largest number of the pixel points is found to serve as the license plate character segmentation position of the license plate image. The method is applied to a license plate identification system and has good robustness and high universality in a complex environment.

Description

Technical field [0001] The invention belongs to the technical field of image processing, and particularly relates to a character segmentation method for license plate images. Background technique [0002] In recent years, my country's highway transportation has developed rapidly, and manual management methods can no longer meet actual needs. The application of microelectronics, communications and computer technology in the transportation field has greatly improved the efficiency of traffic management. License Plate Recognition (LPR) is one of the important components in modern intelligent transportation systems, and it is widely used. It is based on digital image processing, pattern recognition, computer vision and other technologies. It analyzes the vehicle images or video sequences taken by the camera to obtain the license plate number of each vehicle to complete the recognition process. However, the existing license plate recognition methods have disadvantages such as low rec...

AI Technical Summary

Problems solved by technology

[0006] 2. The external environment of the license plate recognition system is complex and changeable

However, this method has poor adaptability to Chinese characters, such as Sichuan, Shaanxi and other Chinese characters with left and right structures, and is greatly affected by character adhesion.

This algorithm does not consider the license plate format of special units in my country. For example, the seventh character of the police car license plate in my country is the Chinese character "Jing", and the seventh character of the coach car license plate is "Learning". Both are Chinese characters with rich texture information and poor connectivity.

Images