License Plate Character Segmentation Method Based on Elastic Template Matching Algorithm

Abstract

The invention describes a license plate character segmentation method based on an elastic template matching algorithm, describes an ideal elastic template, can well describe the scale change of the license plate in a video, and expresses the character segmentation problem as an optimization problem. Matching the license plate picture with the ideal template, and obtaining the global optimal match from the license plate picture can effectively deal with various problems in traditional license plate character segmentation. The corresponding position of each character in the license plate image is determined through the prior positions of each character in the template, and is not affected by the projection of special characters, uneven illumination or weather noise. Moreover, the segmentation algorithm can be applied to the binarized projection sequence, and the matching speed is extremely fast without increasing the time for character recognition. The invention has lower requirements on imaging quality and is suitable for real-time recognition of license plate characters.

Description

technical field [0001] The invention belongs to digital image processing technology. Background technique [0002] Motor vehicle number plate recognition is referred to as license plate recognition. License plate recognition refers to the technology that can detect vehicles traveling at high speed on the road and automatically extract the information of the vehicle license plate (including Chinese characters, English letters, Arabic numerals and license plate color) for processing. License plate recognition technology is an important part of modern intelligent transportation system, and its application is very extensive. Based on computer vision processing, digital image processing, pattern recognition and other technologies, it processes and analyzes the vehicle images or video images captured by the camera, and obtains the license plate number of each vehicle, thus completing the recognition process. Among them, the correct segmentation of license plate characters is the ...

AI Technical Summary

Problems solved by technology

[0005] 2. The external environment of the license plate recognition system is complex and changeable

In bad weather conditions such as rainy days, heavy fog, and heavy snow, the license plate recognition system may cause the license plate to be blocked due to bad weather, or the license plate illumination caused by the headlights of the vehicle to drive in the opposite direction may be uneven.

[0006] 3. In the actual application process in highways and cities, it is difficult to ensure that the license plates involved are not defaced. After a few years of use, the license plates will inevitably appear pollution and wear. It is also difficult to ensure that the vehicles are all standard and clean license plates. Therefore, in the actual environment, in the face of damaged and dirty license plates, how to improve the recognition ability of the license plate recognition system is also a practical problem that needs to be solved.

[0007] The above factors have greatly affected the quality of the obtained license plate image, resulting in the actual obtained characters being stuck, defaced, etc.

In the face of the above problems, the traditional segmentation algorithm either judges that the segmentation fails and does not return any information, or returns completely wrong information due to incorrect segmentation due to the use of local error information

Images