Expression-based video generation method, apparatus and device, and storage medium
A video and expression technology, applied in the field of image processing, can solve the problem of not being able to automatically capture wonderful moment videos.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0037] Embodiment 1 of the present invention provides an expression-based video generation method, such as figure 1 As shown, the method includes:
[0038] S1. Store the video to be synthesized within a preset period of time and detect in real time whether the video to be synthesized contains an interesting expression image;
[0039] Wherein, the preset time period may be a default time period of the system, such as 20 minutes, or may be a time period preset by the user according to needs. Taking 20 minutes as an example, during the video shooting process, this step can temporarily store the video to be synthesized within 20 minutes, and automatically detect whether each frame image in the video to be synthesized contains funny expression images through the face detector.
[0040] Wherein, the funny emoticon image can be set according to the image requirements of the generated target video or the user's preferences. Preferably, the funny emoticon images include: smiley emoti...
Embodiment 2
[0046] Embodiment 2 of the present invention provides an expression-based video generation method, such as figure 2 As shown, the method includes:
[0047] S201. Store the video to be synthesized within a preset period of time and detect in real time whether the video to be synthesized contains funny expression images;
[0048] S202. When it is detected that the video to be synthesized contains a funny expression image, score the funny expression image according to a preset scoring rule to obtain a score value, and judge whether the score value is greater than a preset value;
[0049] In a specific implementation manner, the funny emoticon image is a smiley image of a specified group of people, and the preset scoring rule is a scoring rule formed by the smiling degree and image quality of the smiling face image. The score value of the funny emoticon image is the sum of the weights of the first score item obtained from the composition factor of the degree of laughter and the ...
Embodiment 3
[0063] Embodiment 3 of the present invention provides an expression-based video generation method, such as image 3 As shown, the method includes:
[0064] S301. Allocate temporary storage space for storing videos to be synthesized.
[0065] The size of the temporary storage space can be set according to the storage space of the video to be synthesized during the preset time period is larger than that.
[0066] S302. Store the video to be synthesized within a preset period of time and detect in real time whether the video to be synthesized contains funny facial expressions;
[0067] Exemplarily, the funny emoticon image is a baby smiling face image, and the detecting whether the video to be synthesized contains an interesting emoticon image includes:
[0068] S11, detecting the face image of the baby;
[0069] Specifically, in this step, the image in the video stream may be automatically detected by a face detector; and it is judged whether there is a baby face in the curre...
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