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

Face key point detection method and system based on sparse key point calibration

A technology of face key points and detection methods, which is applied in the field of face detection to achieve the effects of improving detection accuracy, improving stability, and reducing dependencies

Active Publication Date: 2020-02-21
HANGZHOU QUWEI SCI & TECH
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This brings great challenges to the current face key point detection method based on the face frame.

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
  • Face key point detection method and system based on sparse key point calibration
  • Face key point detection method and system based on sparse key point calibration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] Such as figure 1 As shown, this embodiment proposes a face key point detection method based on sparse key point calibration, including:

[0045] S1. Calculate the average face of dense key points under the input size of the detection model;

[0046] Face key point detection includes face key point detection, positioning or face alignment, which refers to locating the key areas of the face for a given face image, including eyebrows, eyes, nose, mouth, and facial contours. The present invention uses a deep learning method to detect key points, and the specific detection method is not limited here.

[0047] Before using the detection model for key point detection, it is necessary to train and generate the corresponding detection model. The production of training samples is based on the average face as a standard, and a certain proportion of disturbance enhancement is performed to ensure the consistency of the distribution of training samples and predicted samples. Gener...

Embodiment 2

[0063] Such as figure 2 As shown, this embodiment proposes a face key point detection system based on sparse key point calibration, including:

[0064] The mean face calculation module is used to calculate the mean face of dense key points under the input size of the detection model;

[0065] Face key point detection includes face key point detection, positioning or face alignment, which refers to locating the key areas of the face for a given face image, including eyebrows, eyes, nose, mouth, and facial contours. The present invention uses a deep learning method to detect key points, and the specific detection method is not limited here.

[0066] Before using the detection model for key point detection, it is necessary to train and generate the corresponding detection model. Production of training samples The mean face is used as a standard to generate a certain percentage of disturbance enhancements to ensure the consistency of the distribution of training samples and pre...

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 face key point detection method and system based on sparse key point calibration. The detection method comprises the following steps: S1, calculating a mean value face of dense key points under the input size of a detection model; S2, detecting sparse key points of the face image by using an existing face detector; S3, calculating an affine transformation matrix based onthe mean human face and the sparse key points of the human face image; S4, performing affine transformation on the face image to an input image of the mean face size based on the affine transformationmatrix; and S5, detecting key points of the face image based on the detection model, and restoring the coordinates of the key points through inverse affine transformation to obtain dense key points in the original face image. According to the invention, the sparse key points are detected, the input image is obtained through affine transformation, the position of the face is closer to the proportion of the face, and the detection precision of the face key points is improved. Meanwhile, the dependence of key point detection on the face frame is reduced, and the stability is improved.

Description

technical field [0001] The invention relates to the field of human face detection, in particular to a human face key point detection method and system based on sparse key point calibration. Background technique [0002] With the development of deep learning technology, algorithms represented by neural networks have made unprecedented breakthroughs in many fields. Among them, as a classic problem in computer vision, face key point detection, whether it is based on deep learning or traditional methods, has a common shortcoming-over-reliance on face frames. In the existing methods, a detection algorithm often only performs better for the face frame used in training, and when another face frame is used, the detection accuracy of face key points will decrease. Even if the same standard face frame is used, the instability of the detector will cause the instability of the face frame, which will also cause great interference to the detection of key points of the face. The main perf...

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): G06K9/00G06K9/62
CPCG06V40/161G06F18/2136G06F18/214
Inventor 戴侃侃李云夕熊永春杨金江
Owner HANGZHOU QUWEI 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