Expression recognition method, device and equipment for character in video and storage medium
A technology in expression recognition and video, applied in character and pattern recognition, acquisition/recognition of facial features, instruments, etc., can solve problems such as inability to stream media data tagging
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0118] see figure 1 , an embodiment of the present invention provides a method for recognizing facial expressions of characters in a video, which can be executed by a device for recognizing facial expressions of characters in a video (hereinafter referred to as an facial expression recognition device), in particular, executed by at least one processor in the facial expression recognition device , to at least implement the following steps:
[0119] S101. Acquire multiple first images from a video to be processed.
[0120] In this embodiment, the video to be processed is a video with a character image, which may be a video recorded with a real person, or an animation streaming media with a character image, which is not specifically limited in the present invention. Among them, the expressions of characters in animation streaming media are often more exaggerated than those of real people, so they are easier to be recognized.
[0121] The first image is a specific frame on the v...
Embodiment 2
[0210] see figure 2 , the second embodiment of the present invention provides an expression recognition device for characters in a video, which includes:
[0211] The first image acquisition module 201 is configured to acquire a plurality of first images from the video to be processed;
[0212] a grayscale module 202, configured to grayscale the first image to obtain a second image;
[0213] The face detection module 203 is used to obtain the face area on the second image through the face detection model;
[0214] A frontal face screening module 204, configured to filter out a third image containing a frontal face from a plurality of second images according to the face area;
[0215] The face recognition module 205 is used to obtain the character information corresponding to the face area of the third image through the face recognition module 205;
[0216] The expression recognition module 206 is configured to acquire expression information corresponding to the person in...
Embodiment 3
[0258] The third embodiment of the present invention provides a device for facial expression recognition of characters in a video, including a processor, a memory, and a computer program stored in the memory, and the computer program can be executed by the processor to implement the above-mentioned embodiment The facial expression recognition method of the characters in the video.
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