Unlock instant, AI-driven research and patent intelligence for your innovation.
Comprehensive Evaluation Method of License Plate Image Quality
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A license plate image and comprehensive evaluation technology, applied in the field of image processing, can solve the problems of insufficient pertinence, insufficient utilization of degraded characteristics, and evaluation results that cannot meet expectations, etc.
Active Publication Date: 2018-09-25
NANJING UNIV OF POSTS & TELECOMM
View PDF7 Cites 1 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0003] License plate image quality assessment belongs to blind source quality assessment, which usually adopts general image quality evaluation standards. The characteristics of the specific object of license plate are not fully utilized, and the common degradation characteristics of special scenes such as video surveillance are not targeted enough. The evaluation results are often up to less than expected
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0100] refer to figure 1 , a comprehensive evaluation method for license plate image quality, including:
[0101] S1. Establish a sample library of clearly identifiable license plate images and fuzzy unrecognizable license plate images, and train to obtain the hyperplane equation parameters with the strongest ability to distinguish their frequency features and color features, which will provide for the classification of the frequency features and color features of target license plate images in the future. parameter.
[0102] S2, refer to figure 2 , this embodiment uses a common method to input a recognizable license plate image that has been stretched by nearest neighbor interpolation, and the result after edge detection is as follows image 3 As shown, it can be clearly seen that there are a large number of adjacent grids of the same size in the edge image. Through further calculation, the grid side length is used to calculate the actual spatial resolution of the target l...
Embodiment 2
[0113] This implementation example is basically similar to Embodiment 1, the difference lies in:
[0114] S2, refer to Image 6 , this embodiment uses a fast method to input an unrecognizable license plate image with a high degree of blur, and the result after edge detection is as follows Figure 7 As shown, there is no obvious grid phenomenon, so it is judged that its actual spatial resolution is the input spatial resolution;
[0115] S3, its normalized DCT transform such as Figure 8 , the high-frequency components are obviously insufficient;
[0116] S4, use the fast method here, skip the step of calibrating the corner points of the license plate, and do not change the target license plate image;
[0117] S5. Vertically project the grayscale image of the target license plate image and perform one-dimensional median filtering, such as Figure 9 , it can be clearly found that the vertical projection characteristic peak-valley alternation phenomenon is not obvious;
[011...
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 comprehensive evaluation method widely applicable to license plate image quality in different scenarios, from the spatial resolution, frequency characteristics, peak-valley alternation characteristics of the actual license plate image produced by vertical projection of gray scale, and the deviation between color and standard color The four aspects of features comprehensively analyze the quality of license plate images, which basically covers the ability to distinguish various types of low-quality license plate images in harsh situations such as surveillance scenes. This solution provides two evaluation methods, normal and fast. The normal method requires the user to manually calibrate the four corners of the license plate in the image, while the fast method requires the area of the license plate to account for half or more of the license plate image area. This scheme can be used to judge whether the license plate image reaches the recognizable standard and analyze the reasons for the low quality of the license plate image that cannot meet the recognizable standard.
Description
technical field [0001] The invention relates to image quality evaluation in the field of image processing, in particular to blind source image quality evaluation. Background technique [0002] License plate information is one of the most important information in the field of video surveillance, and often becomes the key factor in case detection. Common license plate recognition, license plate reconstruction and other tasks often need to classify batches of license plate images according to different qualities, which consumes a lot of time. In addition, whether the quality of a license plate image is up to the standard and analyzing the reasons for the low quality of the image that does not meet the standard has become a problem that needs to be solved urgently in the license plate reconstruction. [0003] License plate image quality assessment belongs to blind source quality assessment, which usually adopts general image quality evaluation standards. The characteristics of ...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to View More 
Login to View More