Acquisition method and detection method of living body face detection head posture regression device

A head posture and face detection technology, applied in the field of image recognition, can solve the problems of non-interactive, unpublished regressor for posture regression, poor anti-attack ability, etc., to improve the accuracy and scientificity, and increase the success rate , the effect of improving speed and accuracy

Inactive Publication Date: 2019-12-03
HUAIBEI NORMAL UNIVERSITY
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Moreover, most face detection schemes are based on direct extraction of face image information, without interactivity, and poor anti-attack capabilities, such as photos, videos, and model camouflage, which put forward requirements for live face detection. There are mature human face detection me

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
  • Acquisition method and detection method of living body face detection head posture regression device
  • Acquisition method and detection method of living body face detection head posture regression device
  • Acquisition method and detection method of living body face detection head posture regression device

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0046] Example one

[0047] according to figure 1 , 2 As shown, this embodiment proposes a method for acquiring a head posture regressor for live face detection, including the following steps:

[0048] A. Acquire 2D face model data, 3D face model data, and iris data, and then screen out the acquired 2D face model data, 3D face model data, and iris data to remove the 2D face model data , The low resolution and repeated data in the face 3D model data, remove the damaged data in the iris data;

[0049] B. Select a certain number of feature points in the face two-dimensional model data, and then select the same feature points in the face three-dimensional model data, and map the feature points, and then form the face three-dimensional model data with composite standardization, and then Perform normalization processing on the face three-dimensional model data with compound standardization, and use the distance and direction axis of the two pupils in the face three-dimensional model data ...

Example Embodiment

[0061] Example two

[0062] according to image 3 As shown, this embodiment of a method for detecting a living body face based on a head posture regressor includes the following steps:

[0063] H. Obtain the image of the head posture made by the user according to the instructions issued by the terminal, including two-dimensional images and three-dimensional images, and then use the iris data collected by the iris collection device;

[0064] I. According to the two-dimensional image, three-dimensional image and iris data, the face frame is obtained through the adaboost algorithm;

[0065] G. Locate the coordinates of the face feature points in the face frame by using a supervised gradient descent method;

[0066] K. Perform centralization and normalization of the facial feature points;

[0067] L. According to the processed feature point data, the head angle is obtained through the head posture regressor; when it is judged that the obtained head angle value is within the preset threshold,...

Example Embodiment

[0081] Example three

[0082] according to Figure 4 As shown, the method for detecting a human face in this embodiment includes the following steps:

[0083] M. Obtain the two-dimensional and three-dimensional images of facial expressions made by the user according to terminal instructions, and the iris data collected by the iris collection device;

[0084] N. According to the two-dimensional image, three-dimensional image and iris data, obtain a face frame through an adaboost algorithm;

[0085] O. Locate the coordinates of the face feature points in the face frame by using a supervised gradient descent method;

[0086] P. Perform linear transformation on the located feature points; when it is judged that the feature information value of the feature points after linear transformation is within the preset feature threshold range, the recognition is successful.

[0087] The beneficial effects of the present invention are: by constructing a high-precision head posture regressor, and by a...

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 an acquisition method and detection method of living body face detection head posture regression device, and the method comprises the steps: obtaining face data, and forming face three-dimensional model data with composite standardization; obtaining a training sample set; acquiring a corresponding Euler angle and a rotation matrix containing a corresponding relationship between each two-dimensional coordinate plane and the corresponding Euler angle by using the acquired two-dimensional coordinate plane set formed by the two-dimensional coordinates of the feature points;obtaining a head posture regression device. According to the invention, a high-precision head posture regression device is constructed. Corresponding earlier-stage processing is carried out on the human face two-dimensional model data, the human face three-dimensional model data and the iris data. The invention has the following beneficial effects: human faces are effectively recognized, therebymaking data more accurate and robust; and the success rate of face living body detection is improved.

Description

technical field [0001] The invention relates to image recognition technology, in particular to an acquisition method and a detection method of a head pose regressor for detection of living human faces. Background technique [0002] With the advent of the era of big data, the problem of personal information security has become increasingly severe, and face recognition and detection technology based on image processing has been widely used. However, the current face detection technology is aimed at a small number of face images. With the deepening of the concept of big data, image big data processing will put forward higher requirements for face detection technology. Moreover, most face detection schemes are based on direct extraction of face image information, without interactivity, and poor anti-attack capabilities, such as photos, videos, and model camouflage, which put forward requirements for live face detection. There are mature human face detection methods, and the reg...

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
IPC IPC(8): G06K9/00G06K9/32G06K9/62G06T3/60
CPCG06T3/60G06V20/64G06V40/166G06V40/168G06V40/18G06V40/45G06V10/25G06F18/285G06F18/214
Inventor 张琪
Owner HUAIBEI NORMAL UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap