Method and device for determining human face deflection angle, computer equipment and medium

Abstract

The invention discloses a method for determining a human face deflection angle. The method comprises the following steps: acquiring a human face image; recognizing human face feature information in the human face image, wherein the human face feature information at least comprises a left pupil coordinate, a right pupil coordinate, a nose tip point coordinate and a lip midpoint coordinate; determining a deflection angle of a human face in the human face image according to a geometrical relationship between the human face feature information and a reference value corresponding to a reference human face image, with the deflection angle including at least one of a first deflection angle and a second deflection angle, the first deflection angle being an angle at which the human face deflects ina horizontal direction, and the second deflection angle being an angle at which the human face deflects in the horizontal direction; wherein the second deflection angle is the deflection angle of thehuman face around the vertical direction. The invention further discloses a device for determining the human face deflection angle, computer equipment and a computer readable storage medium. According to the invention, the efficiency of recognizing the human face deflection angle in the human face image is improved.

Description

technical field [0001] The present application relates to the technical field of face recognition, and in particular to a method for determining a face deflection angle, a device for determining a face deflection angle, computer equipment, and a computer-readable storage medium. Background technique [0002] In the current face detection and recognition, the user's front face image is used as a benchmark, and the deflection angle of the face equivalent to the front face (such as deflection up and down, deflection to left and right, etc.) can be used as a dimension to judge the quality of the face image . The general approach is to use a large number of labeled face pictures and angle deflection information to feed the deep learning neural network to train a model that can recognize the face deflection angle. But doing so is costly and not conducive to implementation on devices with fewer hardware resources. [0003] The above content is only used to assist in understanding...

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the present application is to provide a method for determining the deflection angle of a human face, a device for determining the deflection angle of a human face, computer equipment, and a computer-readable storage medium, aiming at solving the problem of inefficiency in identifying the deflection angle of a human face in a human face image The problem

Images