Face image processing method and device, equipment and medium

A face image and processing method technology, applied in the field of face image processing, can solve problems such as jitter, frame loss, and inconspicuous facial micro-motion capture, etc., to achieve the effect of removing jitter

Active Publication Date: 2020-04-24
北京蜜莱坞网络科技有限公司
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is likely to cause frequent frame loss, the micro-motion capture of the face is not obvious, and there will be jitter when adding special effects to the face

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 image processing method and device, equipment and medium
  • Face image processing method and device, equipment and medium
  • Face image processing method and device, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] figure 1 It is a flow chart of a face image processing method provided by Embodiment 1 of the present invention. This embodiment is applicable to the processing of a face image, and the method can be executed by a face image processing device. Typically, the method It can be used to identify the shaking of key points of the anchor's face in a live broadcast scene, and the device can be implemented by software and / or hardware. see figure 1 , the method specifically includes the following steps:

[0026] Step 110, determining the key point distances and optical flow change values ​​of different target face images in the face image sequence.

[0027] Wherein, the face image sequence is the face images collected in real time at different times. First determine the position of the face frame of each face image, and then determine the key points of the face in the face frame. Specifically, the key points of a human face may include key points of areas such as a human face...

Embodiment 2

[0046] figure 2 It is a flow chart of a face image processing method provided by Embodiment 2 of the present invention. This embodiment further refines step 120 on the basis of the above embodiments. see figure 2 , the embodiments of the present invention specifically include:

[0047]Step 210, determining key point distances and optical flow change values ​​of different target face images in the face image sequence.

[0048] Step 220 : Determine the optical flow change thresholds for different parts of the face according to the degree and frequency of changes of different parts of the face.

[0049] Usually, different parts of the face correspond to different degree of change and frequency of change. For example, the degree of change and frequency of change of the mouth are larger than those of other parts. Therefore, when using the optical flow change value to judge whether the key points of the face shake, it is necessary to set the optical flow change threshold of dif...

Embodiment 3

[0055] image 3 It is a schematic structural diagram of a face image processing device provided in Embodiment 3 of the present invention. see image 3 , the device may specifically include a calculation module 310 , a shake judgment module 320 and a key point determination module 330 .

[0056] Wherein, the calculation module 310 is used to determine the key point distance and the optical flow change value of different target face images in the face image sequence;

[0057] Shake judging module 320, for determining whether the key points of the face shake according to the key point distance and the optical flow change value;

[0058] The key point determination module 330 is used to select a frame of target human face images from the sequence of human face images, and use the key points in the frame of target human face images as the keys of all target human face images in the sequence of human face images points for animating the target face image.

[0059] Further, the d...

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 image processing method and device, equipment and a medium. The method comprises the following steps: determining key point distances and optical flow change values of different target face images in a face image sequence; according to the key point distance and the optical flow change value, determining whether the human face key point shakes or not; and if so, selecting a frame of target face image from the face image sequence, and taking key points in the frame of target face image as key points of all target face images in the face image sequence to add animation to the target face image. According to the technical scheme, when human face jitter is detected, key points of a frame of target face image are selected from a face image sequence, animation is added to a face based on the key points of the frame of target face image, the shaking problem of the face key points is solved, position stability and movement smoothness of a face key point result are achieved, and the face animation special effect is better served.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of image processing, and in particular, to a face image processing method, device, device, and medium. Background technique [0002] At present, animation special effects related to live broadcast or short video anchors are generally based on key points of human faces. In order to ensure the practical appreciation of animation special effects, how to achieve smooth movement of key points and prevent shaking is very important for the presentation of animation special effects under the condition of ensuring accurate key point positioning. [0003] In the prior art, the position of the key point is determined by detecting the position change of the key point of the human face, and the image frame is directly discarded when the position movement is relatively small. This method is likely to cause frequent frame loss, the micro-motion capture of the face is not obvious, and jitter will occu...

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): G06T13/00G06T7/33
CPCG06T13/00G06T7/33
Inventor 邓天璧
Owner 北京蜜莱坞网络科技有限公司
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