Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Evaluation method and device for face image quality

A face image and evaluation method technology, which is applied in the fields of image processing and biometrics, can solve the problems that the quality score does not conform to the intuitive evaluation of face images, depict the clarity of images, etc., and achieve the effect of accurate and reliable evaluation results

Active Publication Date: 2022-02-08
BEIJING EYECOOL TECH CO LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, both solutions have the same problem: the final quality score may not conform to people's intuitive evaluation of face images, and it is difficult to accurately describe the clarity of the image

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
  • Evaluation method and device for face image quality
  • Evaluation method and device for face image quality
  • Evaluation method and device for face image quality

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0064] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will describe in detail with reference to the drawings and specific embodiments.

[0065] On the one hand, an embodiment of the present invention provides a method for evaluating the quality of a face image, such as Figures 1 to 7 shown, including:

[0066] Step S1: Obtain the face image to be evaluated;

[0067] In this step, various methods known to those skilled in the art in the prior art can be used to obtain the face image to be evaluated, such as the AdaBoost face detection algorithm using Haar features.

[0068] Step S2: performing normalization processing on the face images to be evaluated to obtain the first face image;

[0069] In this step, the face image to be evaluated is normalized and adjusted to a uniform size to obtain the first face image, for example, 128*128.

[0070] Step S3: Evaluate the first face image I by...

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 discloses a method and a device for evaluating the quality of a human face image, belonging to the fields of image processing and biometric identification. The evaluation method of described human face image quality comprises obtaining the human face image to be evaluated; The human face image to be evaluated is carried out normalization processing, obtains the first human face image; Utilizes blind / no reference image spatial quality evaluation The algorithm evaluates the first human face image to obtain a first quality score representing the quality of the human face image to be evaluated; corrects the first quality score according to the brightness value and the fuzzy value to obtain a characterization The second quality score of the quality of the human face image to be evaluated, wherein the fuzzy value is one or more of the grayscale fuzzy value in the space domain, the fuzzy value in the frequency domain and the texture fuzzy value in the space domain; according to the The second quality score evaluates the quality of the face image to be evaluated. The invention not only conforms to people's way of evaluating images, but also can ensure that the evaluation results are more accurate and reliable.

Description

technical field [0001] The invention relates to the technical fields of image processing and biometric identification, in particular to a method and device for evaluating the quality of human face images. Background technique [0002] With the popularization of digital imaging devices such as smart phones and digital cameras and the rapid development of Internet services, images have become an important medium of communication. People are exposed to a large number of images every day. Problems such as distortion will seriously affect people's visual senses. [0003] In the biometric system, some studies have pointed out that most of the matching errors are caused by low-quality input images, and high-quality images will improve the accuracy of recognition. In particular, in the face recognition system, if the quality of the face image captured by the front-end camera is poor, too many recognition failures will be caused when the back-end recognition is performed, resulting ...

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 Patents(China)
IPC IPC(8): G06T7/00
CPCG06T7/0002G06T2207/30168G06T2207/30201
Inventor 刘守宪孔勇
Owner BEIJING EYECOOL TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com