Evaluation method of fuzzy degree of license plate image
A license plate image and evaluation method technology, applied in the field of image processing, can solve problems such as low resolution of acquisition equipment, different license plate images, blurred license plate images, etc.
Active Publication Date: 2019-11-05
NANJING UNIV OF POSTS & TELECOMM
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, due to the diurnal changes in natural light, the influence of bad weather such as rain, snow and fog, the movement of the vehicle itself, and the low resolution of the acquisition device itself, the license plate images collected by the surveillance camera often become blurred, and different license plate Images will have different levels of blur
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0031] The present invention will be further described below in conjunction with accompanying drawing.
[0032] refer to figure 1 and figure 2 , the invention provides a method for evaluating the fuzziness of a blurred license plate image, comprising:
[0033] S1. Design the fuzzy license plate image fuzzy level calibration criterion, and establish a training library and a testing library with labels according to the criterion;
[0034] S2. Based on the discriminative dictionary learning model guided by logistic regression, the reconstruction error vector of the license plate image block is designed, and the evaluation feature of the license plate fuzzy level is designed, and an evaluation model is established based on this feature;
[0035] Further, the step S1 is specifically:
[0036] S11. Since there is no public fuzzy license plate image data set for verifying and evaluating the algorithm, it is necessary to collect fuzzy license plate images from actual surveillance ...
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
Login to View More Abstract
The present invention provides a fuzzy license plate image fuzziness evaluation method. The fuzzy license plate image fuzziness evaluation is taken as a classification problem, and the fuzzy license plate image fuzziness is classified into two classification: relative fuzziness and severe fuzziness. The method comprises: designing a fuzzy license plate image fuzziness grade calibration standard based on the identification capacity of human eyes for the license plate image, and establishing a training database and a test database with labels according to the standard; designing the license plate fuzziness grade evaluation features based on the reconstruction error vector of the license plate image block through the distinguishing dictionary learning model led by the logistic regression; and finally, establishing an evaluation model based on the designed features.
Description
technical field [0001] The invention relates to image quality evaluation in the field of image processing, in particular to a method for evaluating the fuzziness of a blurred license plate image. Background technique: [0002] License plate images are an important source of information in surveillance videos, and license plate recognition is the most effective and convenient means to extract information from license plate images. However, due to the diurnal changes in natural light, the influence of bad weather such as rain, snow and fog, the movement of the vehicle itself, and the low resolution of the acquisition device itself, the license plate images collected by the surveillance camera often become blurred, and different license plate Images will have different levels of blur. [0003] In order to obtain the best recognition results, different preprocessing and recognition methods should be used for license plate images with different blur levels. Therefore, it is nec...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00
CPCG06T7/0002G06T2207/10016G06T2207/20021G06T2207/20081G06T2207/30168G06T2207/30232
Inventor 刘峰李超群干宗良窦逸辛
Owner NANJING UNIV OF POSTS & TELECOMM