Face beautifying method and device, electronic equipment and storage medium

Abstract

The invention discloses a face beautifying method and device, electronic equipment and a storage medium, and relates to the technical field of computer vision. The specific implementation scheme comprises the following steps of extracting a first preset number of key points from a current face image, and expanding a second preset number of key points from the current face image; extracting each preset key point from a triangulation template with a preset function, and extracting a target key point corresponding to each preset key point from a key point set formed by a first preset number of key points and a second preset number of key points; extracting each preset triangulation grid from the triangulation template based on each preset key point, and constructing a target triangulation grid corresponding to each preset triangulation grid in the current face image based on each target key point; and beautifying a preset function of the current face image on each target triangulation grid. According to the embodiment of the invention, a personalized beautifying effect can be achieved, and the processing speed can be increased.

Description

technical field [0001] The present application relates to the technical field of image processing, and further relates to computer vision technology, especially a face beautification method, device, electronic equipment and storage medium. Background technique [0002] Currently, many short video and live video applications are widely used by more and more users. Among these applications, interactive applications related to face beautification account for a large proportion. Such as face shaping, face beauty makeup, face whitening and microdermabrasion, etc. [0003] In the existing short video and live video applications, beautification functions such as face shaping, face beautification, and face whitening and microdermabrasion are realized by different technical means. For example, when implementing the shaping function, the pixel shader is usually used to pass in the control points to pull the pixels; the disadvantage of this method is that the deformation range of the...

AI Technical Summary

Problems solved by technology

For example, when implementing the shaping function, the pixel shader is usually used to pass in the control points to pull the pixels; the disadvantage of this method is that the deformation range of the face shaping is small, and due to the limitation of using a large number of control points, in The running speed of the mobile terminal is relatively slow; when implementing the beauty function, a set of global triangulation templates is usually used, and then the texture of the material is pasted on the face; the disadvantage of this method is that it cannot implement different functions for different beauty functions. Customized triangulation, so that different beauty functions cannot have their own characteristics; when implementing the whitening and microdermabrasion function, the face area and non-face area in the image are usually segmented by the face segmentation algorithm, Then perform edge-preserving filtering on the face area output by the face segmentation algorithm; the disadvantage of this method is that it will introduce more calculations, resulting in slower speed on the mobile terminal or difficulty in running on low-end machines

Images