A face frame selection method in face key point detection module

Abstract

The invention relates to the field of human face key point detection, and discloses a method for selecting a human face frame in a human face key point detection module, including obtaining a human face detection model and a key point model; Face frame coordinates and the real face frame coordinates of N pictures to obtain the face frame coordinate scaling ratio; use the face frame coordinate scaling ratio to the face frame coordinates of each picture in the test data set output by the trained face detection model Perform optimization to obtain the optimized face frame coordinates of each picture in the test data set; perform coordinate transformation on the optimized face frame coordinates to obtain new face frame coordinates, and cut out from the original image according to the new face frame coordinates Face frame, input the cropped face frame into the trained key point model to obtain key point coordinates. The present invention can effectively solve the problem that the accuracy of key points decreases due to inconsistent selection standards of human face frames in human face detection and key point detection modules.

Description

technical field [0001] The invention relates to the field of human face key point detection, in particular to a face frame selection method in a human face key point detection module. Background technique [0002] Face key point detection is a key step in the field of face recognition and analysis. It is the premise and breakthrough of automatic face recognition, expression analysis, 3D face reconstruction, 3D animation and other face-related problems. In the face recognition system, face detection and face key point detection belong to a cascade system, that is, face key point detection needs to use the face frame output by the face detection module. The face frame used in the face detection module generally only contains the face. In most cases, it cannot be guaranteed that the key points of the face and cheeks are in the face frame, but in the key point module, it is necessary to ensure that all the key points of the face are included in the face frame. In this way, the ...

AI Technical Summary

Problems solved by technology

There are differences between the two face frame selection strategies, which leads to the problem of decreased accuracy of key points due to inconsistent face frame selection standards

In the existing face recognition system, less attention is paid to the accuracy loss caused by the inconsistency between the face frame provided by the face detector and the face frame required by the key points of the face, but its accuracy will directly affect the subsequent feature extraction and expression recognition. Accuracy of facial recognition technology

Images