Method and device for face deformation in video stream, electronic equipment and computer readable medium

Abstract

The invention provides a method for face deformation in a video stream, and the method comprises the steps: carrying out the face deformation of each frame in a plurality of frames of images in the video stream, wherein the method of the face deformation of any frame of image comprises the steps: determining a plurality of initial points on a face in a current frame of image through employing a preset first algorithm; according to the initial point and / or the key point in the related frame image, adjusting the position of the initial point in the current frame image through smoothing processing, the initial point subjected to smoothing processing serving as the key point; adopting a preset second algorithm, carrying out triangulation according to the key points, and obtaining multiple triangles with the key points as vertexes; and according to the type of the face deformation to be performed, moving at least part of the key points by adopting a corresponding moving rule, and on the premise that the texture in the triangle is not changed, calculating the pixel value of each pixel point in the triangle with the moving vertex. The invention further provides a device for face deformation in the video stream, electronic equipment and a computer readable medium.

Description

technical field [0001] The embodiments of the present disclosure relate to the technical field of image processing, and in particular, to a method and device for deforming a human face in a video stream, an electronic device, and a computer-readable medium. Background technique [0002] In many cases, people hope to process the human face in the image to change its appearance, for example, to make the human face look more beautiful (beautification), or to achieve certain film and television special effects, etc. In the processing of the face in the image, the face deformation (face shaping) that changes all or part of the structural shape and position of the face is an important category, such as big eyes, reduced nose, thin face, eyebrows, etc. . [0003] Most of the existing face deformation technologies have shortcomings such as small deformation range, limited functions, slow operation speed, and poor deformation effect. In particular, when deforming faces in multiple ...

AI Technical Summary

Problems solved by technology

[0003] Most of the existing face deformation technologies have shortcomings such as small deformation range, limited functions, slow operation speed, and poor deformation effect.

In particular, when deforming faces in multiple frames of images in a video stream, it is often difficult to ensure the consistency of multi-frame image processing effects because the faces in the video stream may move (including overall displacement and orientation changes) , resulting in abrupt effects such as jitter and discontinuity in the video stream

Images