Method and system for character face transformation in real-time video screen

Abstract

The invention provides a method and system for transforming a figure face in an instant video picture. The method comprises the following steps: receiving a face transformation instruction which is submitted by a first user in an instant video call, wherein the face transformation instruction comprises first face information and second face information which are used for realizing face image position transformation; in response to the face transformation instruction, dynamically identifying a first face image pointed by the first face information and a second face image pointed by the second face information in real time which are to be pushed to an instant video call picture of at least one user participating in the instant video call, and interchanging positions of the first face image and the second face image in each frame of picture by taking a video frame as a unit; and pushing video frames of which the face images have been interchanged to corresponding users participating in the instant video call in a mode of video streams. By adoption of the method provided by the invention, the face images of target figures can be effectively identified, and the figure face transformation in instant videos can be rapidly implemented.

Description

technical field [0001] The present invention relates to digital image processing technology, in particular, the present invention relates to a method and system for transforming faces of people in real-time video images. Background technique [0002] In daily life, people often like to exchange face images of characters in some pictures, and then share them on social networks to increase fun and entertainment. The current image processing is based on static images, and cannot process videos in real time, let alone human-computer interaction. [0003] At the same time, in the current real-time video chat or webcast, there is an operation of modifying the face of a character. It's just that this kind of operation is relatively static and fixed in form, and it cannot perform a dynamic recognition, tracking and processing of the character's face. Furthermore, due to the lack of a good recognition mechanism in the existing technology, the speed of recognizing the face of a pers...

AI Technical Summary

Problems solved by technology

It's just that this kind of operation is relatively static, and the form is relatively fixed, and it cannot perform a dynamic recognition, tracking and processing of the character's face.

Furthermore, due to the lack of a good recognition mechanism in the existing technology, the speed of recognizing the face of a person in response to an operation instruction is slow, and it is difficult to accurately identify the target object in the real-time video and acquire the face of the target object and transform

Images