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

Construction method and application of face quality evaluation model

A quality assessment and construction method technology, applied in the field of face quality assessment model construction, can solve problems such as inability to accurately assess face quality, and achieve the effects of improving generalization performance, reducing memory usage, and improving learning effects

Pending Publication Date: 2021-09-24
HUAZHONG UNIV OF SCI & TECH
View PDF1 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the above defects or improvement needs of the prior art, the present invention provides a construction method and application of a human face quality evaluation model to solve the technical problem that the prior art cannot comprehensively and accurately evaluate the human face quality

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
  • Construction method and application of face quality evaluation model
  • Construction method and application of face quality evaluation model
  • Construction method and application of face quality evaluation model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] A method for constructing a face quality assessment model, such as figure 1 shown, including the following steps:

[0052] S1. Build a face quality assessment model; the face quality assessment model includes a cascaded feature extraction network and a multi-task layer; the feature extraction network is used to extract low-level features of the input image; the multi-task layer includes multiple parallel task branches, using It is used to predict the face image attributes of the input image; each face image attribute corresponds to a task branch; the task branch is used to learn the low-level features to obtain the high-level features corresponding to the face image attributes, and for the high-level features to perform regression or classification to predict face image attributes; among them, face image attributes include continuous numerical attributes and discrete numerical attributes; continuous numerical attributes include: ambiguity, illumination intensity, and he...

Embodiment 2

[0094] A face quality assessment method, such as Figure 4 shown, including the following steps:

[0095] 1), the image to be tested is input into the face quality evaluation model constructed by the construction method of the face quality evaluation model described in embodiment 1, and the predicted value or predicted category of each face image attribute of the image to be tested is obtained ; Wherein, face image attributes include continuous numerical attributes and discrete numerical attributes; continuous numerical attributes include: ambiguity, light intensity and head posture; head posture includes yaw angle, pitch angle and roll angle; discrete numerical attributes include: Facial expression status and glasses wearing status;

[0096] 2), obtain the quality evaluation result of each face image attribute according to the predicted value or the prediction category of each face image attribute obtained;

[0097] It should be noted that the fuzziness is a value between 0...

Embodiment 3

[0113] A machine-readable storage medium, the machine-readable storage medium stores machine-executable instructions, and when the machine-executable instructions are called and executed by a processor, the machine-executable instructions cause the processor to implement the following: The construction method of any human face quality assessment model described in embodiment 1 and / or the human face quality assessment method as described in embodiment 2.

[0114] The relevant technical solutions are the same as those in Embodiment 1 and Embodiment 2, and will not be repeated here.

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 construction method and application of a face quality evaluation model. The construction method comprises the following steps: S1, constructing the face quality evaluation model; and S2, inputting a pre-collected training set into the face quality evaluation model, and training the face quality evaluation model by minimizing a weighted sum of differences between a prediction attribute and a real attribute of each face image attribute as a target. The constructed face quality evaluation model comprises a cascaded feature extraction network and a multi-task layer, the multi-task layer comprises a plurality of parallel task branches, and each face image attribute corresponds to one task branch, so that parallel learning is carried out on various related deep learning tasks; relevance among tasks can be considered in the learning process, parameters are shared, and a better generalization effect can be achieved; different face image attributes of the image are perceived through each task branch, detail information of each face image attribute evaluation index can be obtained, and the face quality can be comprehensively and accurately evaluated.

Description

technical field [0001] The invention belongs to the field of human face image processing of computer vision, and more specifically relates to a construction method and application of a human face quality evaluation model. Background technique [0002] In the era of big data, the importance of information security is self-evident, and face information is even more related to the safety of personal life and property. With the widespread application of deep learning in the field of computer vision, tasks such as face recognition, expression recognition, head pose estimation, and eye tracking have emerged. Taking face recognition as an example, although innovative algorithms have already The accuracy of face recognition has been greatly improved, but there are still limitations in practical applications. The quality of face images fundamentally determines the accuracy of face recognition. For self-service ID photo shooting, airports, railway stations and other security inspecti...

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): G06T7/00G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06T7/0012G06N3/04G06N3/08G06T2207/30168G06T2207/30201G06F18/2451G06F18/2415
Inventor 韩守东马迪李英豪王法权
Owner HUAZHONG UNIV OF SCI & TECH
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