Face box selection method in face key point detection module

Abstract

The invention relates to the field of face key point detection, and discloses a face box selection method in a face key point detection module, which comprises the steps of obtaining a face detectionmodel and a key point model; obtaining a face box coordinate scaling ratio according to the face box coordinates of N pictures and the real face box coordinates of N pictures obtained by the face detection model; optimizing the face box coordinates of each picture in a test data set output by the trained face detection model by using the face box coordinate scaling ratio to obtain the optimized face box coordinates of each picture in the test data set; and performing coordinate conversion on the optimized face box coordinates to obtain new face box coordinates, cutting out a face box from theoriginal picture according to the new face box coordinates, and inputting the cut-out face box into the trained key point model to obtain key point coordinates. According to the method, the problem ofkey point precision reduction caused by inconsistent face box selection standards in the face detection module and the key point detection module can be effectively solved.

Description

Technical field [0001] The present invention relates to the field of detecting facial key points, particularly to a face detection module faces in the key block selection method. Background technique [0002] Face detection is the key step in face recognition and analysis of key fields, automatic face recognition, facial expression analysis, 3D face reconstruction and 3D animation, and other issues related to the human face of the premise and farmers. In the face recognition system, face detection and face detection key belongs to a cascade system, i.e. the face detection requires the use of key face detection module outputs a face frame. In the face frame Face detection module used generally only contain a face you can not be the guarantor face cheek key point in most cases in the face box, but the key point in the module requires a guarantor face all the key points contained in the human face frame, so as to ensure the accuracy of detection of the key points. Two human face box...

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