Video conference user identification method and device, equipment and storage medium
The invention discloses a video conference user identification method and device, equipment and a storage medium, and the method comprises the steps: determining the view finding range of a participant user in a video through face recognition, obtaining the face score of each user in the video based...
Saved in:
| Main Authors | , |
|---|---|
| Format | Patent |
| Language | Chinese English |
| Published |
04.08.2023
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Summary: | The invention discloses a video conference user identification method and device, equipment and a storage medium, and the method comprises the steps: determining the view finding range of a participant user in a video through face recognition, obtaining the face score of each user in the video based on mouth shape recognition and motion recognition, and determining the user with the highest speaking probability in a video image, and improving the user experience. According to the method and the device, the user is identified, and the viewing frame of the user is marked as the current spokesman, so that other users can more conveniently and quickly position the speaking user, and the technical problem of low user experience caused by lack of a method for accurately identifying the spokesman when multiple persons participate in the conference in the same terminal picture at present is solved.
本申请公开了一种视频会议用户识别方法、装置、设备及存储介质，采用人脸识别确定视频中的参会用户的取景范围，基于口型识别以及动作识别得到视频中各用户人脸的得分，从而确定在一个视频画面中发言概率最高的用户，并标记该用户的取景框为当前发言人，使得其 |
|---|---|
| Bibliography: | Application Number: CN202310648928 |