Gray projection-based license plate character segmentation method
A character segmentation and gray-scale projection technology, applied in the field of computer vision, can solve the problems of increased difficulty in positioning, segmentation, and recognition, loss of color information in the license plate area, and increased difficulty in information utilization, etc., to achieve high efficiency, good recognition, and The effect of high reliability
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Publication Date
- 2017-03-22
- Estimated Expiration
- Not applicable · inactive patent
Smart Images

Figure 1 
Figure 2 
Figure 3
Abstract
Description
Technical field
[0001] The invention relates to the field of computer vision, in particular to a method for segmentation of license plate characters based on gray-scale projection. Background technique
[0002] With the development of modern transportation, people pay more and more attention to the automatic recognition of vehicle license plates. It is one of the important research topics in the field of intelligent transportation in recent years by computer vision and pattern recognition technology. The automatic vehicle license plate recognition system can be used for vehicle management in road toll stations, parking lots, intersections, etc. It plays an important role in promoting road traffic and parking lot vehicle management.
[0003] License plate recognition technology includes three basic links: license plate location, character segmentation, and character recognition. License plate location is the premise of character segmentation and character recognition, and license pl...
Examples
Embodiment Construction
[0056] Taking the gray-scale projection license plate recognition method based on the character segmentation algorithm as an example, the present invention will be further described in detail with reference to the accompanying drawings.
[0057] S1. Remove the license plate frame of the input license plate area image;
[0058] For license plate images, there are two types of license plate images after positioning, one is a license plate with a frame, and the other is a license plate without a frame. After we rotate the license plate candidate area to the level, the license plate can be accurately positioned, that is, the license plate frame is removed. Statistical analysis of the test data shows that there are two types of borders of the license plate candidate area after positioning and rotation, one is the border of the license plate itself, and the other is the white background around the license plate as the candidate license plate area. At this time, the white background can ...