Unlock instant, AI-driven research and patent intelligence for your innovation.

A live video method and device for realizing multi-dimensional dynamic display of cosmetics

A dynamic display and live video technology, applied in the field of live video, can solve the problems of not being able to know the makeup effect of cosmetics, single dimension of makeup effect display, and increasing the difficulty of cosmetics

Active Publication Date: 2022-05-31
湖南雷尔传媒有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, there is still a problem in using the live broadcast display method to sell cosmetics with goods: only the anchor’s own makeup effect is displayed on the live broadcast screen, and there is no display picture of the makeup effect of faces with other types of faces. It is possible to know the makeup effect of the cosmetics on the face of the host, but not the makeup effect of the cosmetics on the faces of different users. This makes the display dimension of the makeup effect very single, and also makes users decide whether to buy cosmetics. There are fewer reference examples, which increases the difficulty for users to choose the cosmetics that suit them

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
  • A live video method and device for realizing multi-dimensional dynamic display of cosmetics
  • A live video method and device for realizing multi-dimensional dynamic display of cosmetics
  • A live video method and device for realizing multi-dimensional dynamic display of cosmetics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0087] The facial model selected and the variation of the key point feature group calculated in step 300 are input to the makeup effect.

[0089] The model face image or video of the rendering is compared with the face image or the face image of the makeup effect that the anchor actually takes.

[0093] The value of each point in the image integral graph is the sum of all pixel values ​​in the upper left corner of the point in the original image. Specifically, point

[0097]

[0099] The weak classifier is trained by minimizing the detection error rate, and the weak classification corresponding to the minimum error function is obtained.

[0107] Based on the deformable part model, some key points can be located more accurately, and based on the active appearance model, the

[0108] The first is to use the deformable part model to perform coarse localization of key points with lower accuracy on the face. in one embodiment

[0115]

[0118] The space compression is specifically: se...

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 live video method for multi-dimensional dynamic display of cosmetics. Firstly, the face features before makeup are extracted from the face image before makeup uploaded by the anchor, and are matched with the facial features of the facial model to obtain the matching relationship of facial features. Then extract the post-makeup facial features from the post-makeup facial image uploaded by the anchor, calculate the facial feature change amount reflecting the makeup effect according to the pre-makeup facial features and post-makeup facial features, and then based on the facial feature matching relationship and facial feature change amount Generate the facial feature changes after makeup of the facial model, and render the corresponding facial model according to the facial feature variation after makeup to generate a virtual facial image or video of the facial model after makeup, and then display the virtual facial image or video after makeup on the anchor in real time Upload a live-streamed makeup face image or video. The method can intuitively play the effects of cosmetics applied to different facial models during the live broadcast process, which is beneficial for users to choose suitable cosmetics.

Description

A video live broadcast method and device for realizing multi-dimensional dynamic display of cosmetics technical field The present invention relates to a kind of live video technical field, particularly a kind of video that realizes the multi-dimensional dynamic display of cosmetics. Method and device for live broadcast. Background technique [0002] At present, the social mode of live broadcast by short online video is becoming more and more popular. With the gradual development of Internet construction, More and more human activities are realized with the help of the Internet, and live online through short video software such as Douyin and Kuaishou. Course sharing and item display. Among them, the use of live broadcast display to carry out cosmetics sales with goods is very popular. During the process, the anchor will generally use cosmetics to make up to show the effect of the cosmetics on the facial appearance. This includes making the eyes appear larger, the sha...

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): H04N21/2187H04N21/431H04N21/4415G06K9/62G06V40/16
CPCH04N21/2187H04N21/4318H04N21/4415G06V40/171G06V10/267G06V10/758G06F18/24
Inventor 刘谋容王国强王慧仙
Owner 湖南雷尔传媒有限公司