Human face key point labeling method and device

Abstract

The embodiment of the invention discloses a human face key point labeling method and device. The method comprises the following steps: acquiring human face images acquired by a plurality of image acquisition devices in the same acquisition period; detecting image position information corresponding to each face key point in the target face from each face image; based on image position information corresponding to face key points in a target face in each face image and a preset key point labeling rule, determining labeling position information of each face key point of the target face in each face image, wherein the preset key point labeling rule comprises a rule for labeling based on image position information corresponding to face key points in the target face image, and / or a rule for labeling based on image position information corresponding to face key points which are obtained by traversing in each face image and meet a specified position condition; the target face image is a face image meeting a specified screening rule in the face images, so that the accuracy of a position recognition result of the face key points is improved.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a method and device for marking key points of a human face. Background technique [0002] Face recognition technology is widely used in technical fields such as security, personnel identity detection and personnel tracking. In the relevant face recognition technology, it is generally necessary to first detect the image position information of the key points of the face in each part of the face from the collected images containing the face, and then, based on the image of the key points of the face position information, and carry out subsequent task steps. For example, identity verification of personnel, or identification of fatigue driving behavior of personnel, etc. steps. [0003] It can be seen from the above process that it is very important to accurately identify the image position information of the key points of the face in each part of the face contained in th...

AI Technical Summary

Problems solved by technology

However, in some scenarios, the above-mentioned process is prone to position recognition errors. For example, when a person closes his eyes forcefully, wrinkles are likely to appear around the eyes. At this time, it is easy to recognize the end of the eyebrow as the corner of the eye, resulting in an error in the position recognition of the key points of the face.

Images