License plate location method based on ternary image

A license plate positioning and image technology, applied in the field of image processing, can solve the problems of license plate initial character segmentation errors, Chinese characters that cannot be correctly recognized, and license plate omissions, etc.

Active Publication Date: 2011-06-15
张忠义
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] To sum up, the main problems of traditional license plate location are: 1. The license plate location based on the license plate features may cause the license plate to be missed when it is disturbed; ; 3. After positioning, the boundaries between the left and right ends of the license plate candidate area may be "fuzzy", which may lead to incorrect segmentation of the first character of the license plate, and Chinese characters cannot be correctly recognized
But so far, there is no projection and segmentation method based on ternaryization, and there is no method to reverse the license plate location based on segmentation

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • License plate location method based on ternary image
  • License plate location method based on ternary image
  • License plate location method based on ternary image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0129] According to the technical solution, the implementation of the present invention is clear enough.

[0130] In order to better understand the implementation of image accelerated traversal, take the large span value of 20 and the small span value of 2, and now illustrate the process of image accelerated traversal with an example:

[0131] (1) When the interlaced attribute is false

[0132] The initial value of the small loop is 1, and the final value of the small loop is 2. According to the image acceleration traversal, the following execution sequence can be obtained

[0133] 1, 21, 41, ..., 3, 23, 43, ..., 19, 39, 59, ..., 2, 22, 42, ..., 4, 44, 64, ..., 20, 40, 60, ...

[0134] (2) When the interlaced property is true

[0135] The initial value of the small loop is 1, and the final value of the small loop is 1. According to the image acceleration traversal, the following execution order can be obtained

[0136] 1, 21, 41, ..., 3, 23, 43, ..., 19, 39, 59, ...

[013...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a license plate location method based on a ternary image, belongs to the field of image processing and in particular relates to license plate location during license plate recognition. The method is a pioneer for license plate location according to partition reverse by partitioning five characters comprised in a single-layer license plate and a double-layer license plate tobe license plate location basis including color width, location candidate point marker, a stopping marker, an upper circle, a lower circle, a stopping type color depth, image preprocessing and image transverse. The license plate location by partition reverse has advantages that: a character pitch can be detected at the first time to eliminate counterfeit license plates without locating the license plates by mistake; moreover, by the license plate location in the absence of dependency of license plate characteristics, the so-called influence on the license plate characteristics from the image can be ignored, and all license plates can be located.

Description

technical field [0001] The invention belongs to the field of image processing and relates to license plate positioning in the process of license plate recognition. Background technique [0002] License plate recognition is mainly divided into three steps: license plate location, character segmentation and character recognition. At present, those skilled in the art generally believe that license plate location is the most critical step in license plate recognition technology, which determines the effect of character segmentation and character recognition, and is the main factor affecting the recognition rate of the entire license plate recognition. [0003] License plate positioning is generally based on license plate features, such as texture, corners, edges, colors, etc. The main problem of license plate location based on a single license plate feature is that the image background is complex or the image is affected by uneven illumination, which is prone to location omissi...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/36
Inventor 张忠义
Owner 张忠义
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products