Method for processing face in instant video and electronic device
A technology of face processing and electronic equipment, applied in the field of image processing, can solve problems such as poor user experience, inability to adjust the proportion of the user's face, and inability to meet the aesthetic requirements of the user's face, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0092] An embodiment of the present invention provides a method for processing a face in an instant video, refer to figure 1 As shown, the method includes:
[0093] 101. Obtain the proportion of the reference face.
[0094] Specifically, the process includes:
[0095] obtain a reference face; and
[0096] According to the reference face, obtain the proportion of the reference face.
[0097] The ratio of the reference face includes at least one of a length-width ratio, a facial feature ratio, and a ratio between facial features.
[0098] Among other things, the process can include:
[0099] Get the scale of the stored reference face.
[0100] Wherein, obtaining the reference face may include:
[0101] Obtain multiple feature points of the face in the current instant video frame;
[0102] According to multiple feature points, the face in the face picture with the greatest similarity to the face is obtained as the reference face; or
[0103] Obtain the face in the face pi...
Embodiment 2
[0119] An embodiment of the present invention provides a method for processing a face in an instant video. In the embodiment of the present invention, the aspect ratio of the face in the instant video is adjusted according to the aspect ratio of the reference face. figure 2 As shown, the method includes:
[0120] 201. Obtain a reference face.
[0121] Specifically, the process may include:
[0122] a. Obtain multiple feature points of the face in the current instant video frame;
[0123] Detect the human face in the current instant video frame, and obtain multiple feature points that can be used to describe the human face according to the detection result. The multiple feature points used to describe the human face can include multiple feature point parameters of the peripheral contour of the human face and Multiple feature points of the facial features of the human face. The facial features of the human face may include eyebrows, eyes, nose, mouth, and ears. In addition, t...
Embodiment 3
[0171] An embodiment of the present invention provides a method for processing a face in an instant video. In the embodiment of the present invention, according to the aspect ratio of the reference face and / or the ratio of facial features and / or the ratio between facial features, The aspect ratio and / or the facial features ratio and / or the ratio between the facial features of the human face are adjusted, refer to image 3 As shown, the method includes:
[0172] 301. Obtain a reference face.
[0173] Specifically, this step is the same as step 201 in the second embodiment, and will not be repeated here.
[0174] 302. Obtain a ratio of the reference face according to the reference face.
[0175] The ratio of the reference face includes at least one of a length-width ratio, a facial feature ratio, and a ratio between facial features.
[0176] Obtain at least one of the aspect ratio, the ratio of facial features, and the ratio between the facial features of the reference face cal...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com