Face detection model training method, face key point detection method and device

Abstract

The embodiment of the invention discloses a face detection model training method, a face key point detection method, a device, a device and a storage medium. Performing three-dimensional reconstruction on the training face image based on a preset three-dimensional face model to obtain a training three-dimensional face model; Generating a training UV coordinate map including three-dimensional coordinates of the training three-dimensional face model according to the training three-dimensional face model; The training face image and the training UV coordinate diagram are used for training the semantic segmentation network, so that that face detection model is obtain, As that embodiment of the invention doe not need to manually label the train face image and the training UV coordinate map, Thepresent invention solves the problem that the training data need to be manually estimated and labeled, which leads to inaccurate training data and inaccurate coordinates of the key points of the faceoutput by the CNN, and improves the performance of the face detection model and the accuracy of the key points detection of the face.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of data processing, and in particular to a training method of a human face detection model, a detection method of human face key points, a training device of a human face detection model, and a detection of human face key points Devices, equipment and storage media. Background technique [0002] With the development of Internet technology, various video applications appear, through which people can communicate more intuitively. [0003] In the process of live streaming or recording short videos, users usually need to perform some special effects processing on the video, such as adding special effects such as beautification and stickers to the faces in the video. The addition of the above special effects depends on the eyes, mouth, Key points such as the nose, therefore, the accuracy of detecting the key points of the face is especially important for the processing of special effect...

AI Technical Summary

Problems solved by technology

[0005] Embodiments of the present invention provide a training method for a human face detection model, a method for detecting key points of a human face, a training device for a human face detection model, a detection device, equipment and a storage medium for key points of a human face, To solve the problem of inaccurate face key point detection in existing face key point detection methods, in order to improve the accuracy of face key point detection

Images