Supercharge Your Innovation With Domain-Expert AI Agents!

Human face key point detection method, device, computer device and storage medium

A technology of face key points and detection methods, applied in the fields of computer equipment and storage media, devices, and face key point detection methods, can solve the problems of high time complexity, high resource requirements, large network models and hierarchical models, etc.

Active Publication Date: 2019-02-22
BIGO TECH PTE LTD
View PDF12 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the network model and hierarchical model are single. In order to be able to handle different faces, the network model and hierarchical model are large in size, resulting in a large amount of calculation and high time complexity, resulting in high resource requirements and difficult to apply to mobile terminals. In resource-constrained computing devices

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
  • Human face key point detection method, device, computer device and storage medium
  • Human face key point detection method, device, computer device and storage medium
  • Human face key point detection method, device, computer device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0110] figure 1 It is a flow chart of a face key point detection method provided by Embodiment 1 of the present invention. This embodiment is applicable to scenarios where face key point detection is performed in real time in applications such as live broadcast and short video that mainly focus on user interaction. The method can be performed by a human face key point detection device, which can be implemented by software and / or hardware, and can be configured in a computer device that is relatively scarce in resources, and the computer device can be a mobile phone, a tablet computer, a A mobile terminal such as a wearable device (such as a smart watch, smart glasses, etc.), or the computer device may be a non-mobile terminal such as a smart TV. The method specifically includes the following steps:

[0111] S110. Acquire image data including a human face.

[0112] In a specific implementation, for video scenes such as live broadcast and short video, when playing video data, ...

Embodiment 2

[0131] figure 2 It is a flow chart of a face key point detection method provided by Embodiment 2 of the present invention. This embodiment is based on the foregoing embodiments, and further adds processing operations of a three-level network. The method specifically includes the following steps:

[0132] S201. Acquire image data including a human face.

[0133] Such as image 3 As shown, the embodiment of the present invention may include a global model of a human face and a partial model of facial features.

[0134]Furthermore, the global model includes a face key point detection model 310 and a position correction model 320 , and the facial features local model includes a facial feature key point detection model 330 .

[0135] The face key point detection model 310, the position correction model 320 and the facial features key point detection model 330 form a three-layer cascade network.

[0136] S202. Extract a first human face image including the human face from the i...

Embodiment 3

[0217] Figure 5 A schematic structural diagram of a human face key point detection device provided in Embodiment 3 of the present invention, the device may specifically include the following modules:

[0218] An image data acquisition module 510, configured to acquire image data comprising a human face;

[0219] The first human face key point detection module 520 is used to detect the first human face key point of the human face in the image data;

[0220] A face type identification module 530, configured to identify the face type of the face according to the first key points of the face;

[0221] A position correction module 540, configured to perform position correction on the first face key point with reference to the face type;

[0222] A facial features image extraction module 550, configured to extract a facial features image containing facial features from the image data based on the first face key point after position correction;

[0223] The second human face key ...

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 embodiment of the invention discloses a face key point detection method, a device, a computer device and a storage medium. Detecting a first human face key point of the human face in the image data; Identifying a face type of the face according to the first face key point; Performing position correction on the first human face key point with reference to the human face type; Extracting a five-feature image including five features from the image data based on a first face key point after position correction; Detecting a second human face key point of the human face in the facial image. By distinguishing the face types and modifying the first key points of different face types with different branch classifications, the localization operation is simplified, the computation amount is reduced, and the real-time detection of the face key points is ensured in the computer equipment with scarce resources, such as mobile terminals, and the localization accuracy of the face key points is also improved.

Description

technical field [0001] Embodiments of the present invention relate to biometric processing technologies, and in particular, to a face key point detection method, device, computer equipment, and storage medium. Background technique [0002] For applications that mainly focus on user interaction, such as live broadcast and short video, it is often necessary to detect key points of the face, locate the key points of the face, such as the contour of the face, and the contour of the facial features, for face beautification, facial features, etc. Sticker special effects, face deformation and face changing, etc. [0003] In order to improve the user experience, such as making the beautification more refined and the special effects of facial features stickers more stable, etc., it is necessary to detect the key points of the face accurately enough. Point detection requires that the speed of face key point detection is fast enough. [0004] At present, the schemes to improve the ac...

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): G06K9/00G06V10/764
CPCG06V40/172G06V40/161G06V40/168G06V40/165G06V10/242G06V10/82G06V10/764G06F18/00
Inventor 周卫
Owner BIGO TECH PTE LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com