3D face image generating method, device and electronic device based on occlusion image

Abstract

A 3D face image generating method, device and electronic device based on occlusion image are provided in the invention. The method includes identifying target human face image in picture, judging whetthat rotation angle of the target human face is greater than a preset threshold value or not;; identifying feature point information in the target face image by a pre-trained regression model when the rotation angle is greater than a preset threshold value, the first feature point information including first visible feature point information and first invisible feature point information; the first feature point information is inputted to a pre-trained convolution neural network model to obtain a three-dimensional face image corresponding to the target face image. By using the method, the device and the electronic device, not only the problem of difficult generation of the three-dimensional face image due to the recognition and positioning of the feature points caused by the invisibility of the feature points due to the self-occlusion is solved, but also the effect of the generation of the three-dimensional face image is further improved, and the matching degree is improved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a method, device and electronic equipment for generating a three-dimensional face image based on an occlusion image. Background technique [0002] 3D face reconstruction has been widely used in medical, education, entertainment and other fields. Most of the existing 3D facial image generation methods are based on the detection of 2D facial feature points and 3D facial shape modeling. However, in the process of implementing the present invention, the inventors found that for two-dimensional face images with a large rotation posture, especially after the deflection direction exceeds 60 degrees, nearly half of the face area is self-occluded, and the texture feature information of the occluded area is completely Missing, leading to the failure of feature point detection, and the mismatch between the 3D face image and the 2D face. [0003] In addition, more and more...

AI Technical Summary

Problems solved by technology

However, in the process of implementing the present invention, the inventors found that for two-dimensional face images with a large rotation posture, especially after the deflection direction exceeds 60 degrees, nearly half of the face area is self-occluded, and the texture feature information of the occluded area is completely Missing, resulting in failure of feature point detection, and mismatch between 3D face image and 2D face

[0003] In addition, portable electronic devices are increasingly using 3D face reconstruction technology for entertainment purposes. The acquisition of 2D face images is mainly through the camera of the electronic device, and the reconstruction effect of the 3D face image in the later stage depends partly on the acquisition of the previous camera device. The quality of the image, and the quality of the obtained image partly depends on the effect of the shake processing during shooting. The current portable electronic equipment mainly uses software to perform anti-shake processing, and the hardware has not been improved in a targeted manner.

Images