A license plate character segmentation method based on dynamic templates combined with pixels

Abstract

The invention discloses a license plate character segmentation method using a dynamic template combined with pixel points, which belongs to the technical field of image processing. The present invention first carries out binarization processing to the input license plate image and obtains its width w and height h, and sets the width and height of the license plate template characters and the interval between characters based on the character size and interval size stipulated in the standard of the motor vehicle number plate, The height of the license plate template is h, the width w' is dynamically increased, and its initial value is w / 3~2w / 3. Based on the license plate template, the license plate image is subjected to template sliding processing, and the non-zero pixels at the positions of each character at the current sliding position are recorded The number of points and the current character segmentation position; gradually increase the width w', keep the width-to-height ratio setting of each character of the license plate template and the interval between characters, and repeat the template sliding process until the width w' increases to w; finally, find the pixel points The segmentation position with the largest number is used as the license plate character segmentation position of the license plate image. The invention is used in a license plate recognition system and has good robustness and versatility in complex environments.

Description

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

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