Single-person close-up real-time recognition and automatic screenshot method for large-scale live broadcast scenes

Abstract

The invention discloses a single-person close-up real-time recognition and automatic screenshot method for large-scale live broadcast scenes, specifically as follows: obtain the current video frame image of the live video in real time, and detect whether there is a human face in the video frame image; if the video frame image If there is a face in the frame image, the face detection module is used to obtain the face area, and then the face area is comprehensively evaluated for face size, clarity, position and angle, and then the optimal face is selected, and the optimal face is selected. The current video frame image of the face is saved as a screenshot; finally, the optimal face image is sent to the face recognition module for recognition, and the recognition result is output. The invention can be applied to identify and take screenshots of single-person close-ups in the video in large-scale live broadcast scenarios, and automatically save the screenshots when the screenshot indicators are met; at the same time, the screenshot indicators can not only obtain screenshots with better quality, but also avoid face recognition. A large number of repeated face snapshots bring about a large amount of back-end server and computing workload.

Description

Technical field: [0001] The invention relates to a method for real-time identification and automatic screenshot of a single person close-up for large-scale live broadcast scenes, and belongs to the technical field of video image processing technology. Background technique: [0002] On various live broadcast platforms, such as regular conference live broadcast or football live broadcast or large-scale party live broadcast, it is necessary to take screenshots under certain circumstances, and perform face recognition on the characters in the pictures, so as to facilitate the introduction of pictures and texts. People must be detected if a screenshot is needed. The key technology is face detection, while traditional face detection is usually performed in real time, so a large number of repeated snapshots of different faces of the same object will be generated during the detection process, and the quality In addition, if all snapshots are saved for face recognition, it will bring...

AI Technical Summary

Problems solved by technology

People must be detected if screenshots are needed. The key technology is face detection, and traditional face detection is usually detected in real time, so a large number of repeated different face snapshots of the same object will be generated during the detection process, and the quality In addition, if all snapshots are saved for face recognition, it will bring the disadvantages of large storage capacity and poor face recognition effect. Therefore, in order to solve this problem, the present invention proposes an image quality evaluation method, which can only satisfy Screenshots are required to save and identify

Images