Method for identifying license plate in high-definition image

A clear image and technology in the image, applied in the field of license plate recognition, can solve the problems of difficult license plate recognition, wide viewing range, high resolution, etc., and achieve the effect of reducing requirements, good image binarization effect, and fast positioning and recognition

CN101630360BInactive Publication Date: 2012-12-19上海分维智能科技有限公司
4 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Publication Date
2012-12-19
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention relates to a method for identifying a license plate in a high-definition image, which comprises steps of candidate license plate area detection, grayscale image binarization, obliquity correction, character segmentation, character identification and post-processing. Compared with the prior art, the method for identifying the license plate in the high-definition image has the advantages of simultaneous and quick positioning and identification of a plurality of license plates in a complex background with high definition (more than 5,000,000 pixels), good image binarization effect under the condition of non-uniform illumination, variability of license plate obliquity and size in a relatively larger range, and the like, and simultaneously greatly reduces the requirements on the installation of a video camera.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to license plate recognition, in particular to a method for recognizing license plates in high-definition images. Background technique

[0002] In recent years, industrial-grade high-definition cameras with more than one million pixels (1.3 million to 5 million) have begun to be used to capture vehicle images. Because it can provide strong evidence needed for law enforcement, it has begun to be used in the fields of security and intelligent transportation. be promoted.

[0003] The existing license plate recognition methods for standard-definition images (below 450,000 pixels) are difficult to be used for license plate recognition for high-definition images. The reason is that the license plate recognition of high-definition images has high resolution, wide viewing range, complex background, and difficult license plate positioning. There are multiple license plates in the image that need to be recognized at the same time, while t...

Examples

Embodiment

[0037] 1. Candidate license plate area detection

[0038] In the license plate recognition application system, the location of the camera installation and the size of the captured scene determine the size of the license plate in the image. When the camera is installed on the side, the size of the license plate in the same image will also vary greatly. If the license plate recognition algorithm has too strict requirements on the size of the license plate, it will limit the application range of license plate recognition and bring a lot of trouble to the construction and debugging. Setting the height of license plate characters between 15 and 50 pixels can meet the needs of most practical projects.

[0039] In order to detect large and small license plates at the same time, image pyramid decomposition is used to detect license plates of a specific size range in each level of image. Finally, the candidate license plate areas detected by the pyramid images at all levels are mappe...