Face brightness calculation method, device and equipment and storage medium

Abstract

The invention relates to the technical field of image data processing, and discloses a face brightness calculation method, apparatus and device, and a storage medium. The method comprises the steps ofextracting a head region from an image; extracting a face region from the head region, wherein the face area comprises a marked left mouth corner key point, a marked right mouth corner key point, a marked left forehead key point, a marked right forehead key point, a marked left cheek key point, a marked right cheek key point, a marked left upper jaw key point and a marked right upper jaw key point; judging the face orientation according to the midpoint of the face area, the left mouth corner key point and the right mouth corner key point; when the face orientation is a front face, extractinga hexagonal area defined by the left forehead key point, the right forehead key point, the left cheek key point, the right cheek key point, the left upper jaw key point and the right upper jaw key point from the face area; calculating the average brightness of the hexagonal area, wherein the accuracy of face brightness calculation can be improved.

Description

technical field [0001] The present invention relates to the technical field of image data processing, in particular to a face brightness calculation method, device, equipment and storage medium. Background technique [0002] At present, the video conferencing terminal system usually adjusts the exposure by means of intelligent adjustment, so as to ensure the brightness experience of the face in the scene. This method usually needs to rely on the real-time brightness of the face in the scene. However, the mainstream solution for calculating the brightness of the face in the video conferencing terminal industry has certain shortcomings: after the face is detected, because the general face detection algorithm can only give For the rectangular area where the face is located, when calculating the brightness of the face, background information will be mixed in near the four vertices of the rectangle, resulting in inaccurate calculation of the brightness of the face. Contents of ...

AI Technical Summary

Problems solved by technology

This method usually needs to rely on the real-time brightness of the face in the scene. However, the mainstream solution for calculating the brightness of the face in the video conferencing terminal industry has certain shortcomings: after the face is detected, because the general face detection algorithm can only give In the rectangular area where the face is located, when calculating the brightness of the face, background information will be mixed in near the four vertices of the rectangle, resulting in inaccurate calculation of the brightness of the face

Images