Generation of attitude detection model, attitude detection method, device, equipment and medium

A technology for detecting models and attitudes, applied in the field of image processing, can solve problems such as detection failure, and achieve the effect of improving representativeness and accuracy

Active Publication Date: 2019-12-24
BEIJING BYTEDANCE NETWORK TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the process of implementing the present disclosure, the inventor found that the existing technology has the following defects: if a person flips up and down with a photo of a legitimate user, it is easy to detect by nodding or shaking the head, resulting in the failure of liveness detection

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
  • Generation of attitude detection model, attitude detection method, device, equipment and medium
  • Generation of attitude detection model, attitude detection method, device, equipment and medium
  • Generation of attitude detection model, attitude detection method, device, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] figure 1 It is a flow chart of a method for generating a posture detection model provided by Embodiment 1 of the present disclosure. This embodiment is applicable to the situation of generating a model for posture detection. This method can be executed by a device for generating a posture detection model. The device can be implemented in the form of software and / or hardware, and the device can be configured in electronic equipment, such as a typical computer. Such as figure 1 As shown, the method specifically includes the following steps:

[0067] S110. Acquire at least one set of pose-consistent sample sets, wherein the pose-consistent sample set includes: an original face image, at least one pose-transformed face image that satisfies a pose difference condition with the original face image, the The pose-transformed face image is generated by transforming the original face image.

[0068] Specifically, the pose consistent sample set refers to a set including at leas...

Embodiment 2

[0096] figure 2 It is a flow chart of a pose detection method provided in Embodiment 2 of the present disclosure. This embodiment is applicable to the detection of human face poses. The method can be executed by a pose detection device, which can use software and / or hardware Realized in a manner, the device can be configured in electronic equipment, such as a typical computer. Such as figure 2 As shown, the method specifically includes the following steps:

[0097] S210, acquiring a plurality of continuous video frames including user face images in the video.

[0098] Generally speaking, video is formed by a series of static video frames played continuously at a very fast speed. Thus, the video can be split into a series of video frames, and each video frame can be used as an image. In the embodiment of the present disclosure, the video frame is an image including a user's face image. When performing liveness detection, a video including the user's face is recorded, so ...

Embodiment 3

[0110] image 3 It is a schematic structural diagram of an apparatus for generating a gesture detection model provided by an embodiment of the present disclosure. This embodiment is applicable to the situation of generating a model for gesture detection. The device can be implemented in software and / or hardware, and the device can be configured in electronic equipment. Such as image 3 As shown, the device may include: an attitude consistency sample set acquisition module 310 , an attitude parameter setting module 320 and an attitude detection model generation module 330 .

[0111] The attitude consistency sample set acquisition module 310 is used to acquire at least one set of attitude consistency sample sets, wherein the attitude consistency sample set includes: an original human face image, at least A pose-transformed face image, the pose-transformed face image is generated by transforming the original face image;

[0112] A posture parameter setting module 320, configur...

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 present disclosure discloses an attitude detection model generation, attitude detection method, device, equipment and medium. The method includes: acquiring at least one set of pose consistency samples, wherein the pose consistency sample set includes: an original face image, at least one pose-transformed face image that satisfies a pose difference condition with the original face image, The posture-transformed face image is generated by transforming the original face image; the posture parameters of each face image included in each group of the posture-consistent sample sets are set to the same standard posture parameter value; the at least one set of The attitude consistency sample set is used to train the standard detection model to form the attitude detection model. The embodiments of the present disclosure can avoid the situation of misjudging the user's gesture by using a photo, and improve the accuracy of the user's gesture recognition.

Description

technical field [0001] Embodiments of the present disclosure relate to image processing technologies, and in particular, relate to generation of an attitude detection model, an attitude detection method, device, device, and medium. Background technique [0002] When people are engaged in various activities, they often need to carry out identity authentication, so as to ensure the security of information. With the development of computers and networks, the popularity of networked electronic devices has made the identity authentication work more efficient. Usually, identity authentication needs to determine that the subject is a living body. [0003] At present, liveness judgment is often required in financial systems and face recognition systems. In this process, the user is generally required to complete basic facial movements. For example, nodding and / or shaking the head. The existing technology mainly determines whether the user is a live user by detecting the changes i...

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): G06K9/00G06N20/00
CPCG06V40/161G06V40/171G06V40/20
Inventor 王旭张惜今
Owner BEIJING BYTEDANCE NETWORK TECH CO LTD
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