End-to-end unconstrained human face key point detection method

A technology of face key points and detection methods, applied in the field of face recognition, can solve problems such as occlusion of faces, huge amount of information, inability to deal with large angles at the same time, and achieve the effect of improving time efficiency

Active Publication Date: 2017-12-19
GUANGZHOU YUNCONG INFORMATION TECH CO LTD
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these methods have always had a common problem: they cannot handle faces with large angles and severe occlusions at the same time. To solve this problem, 3D models or multi-angle models are usually introduced for key point detection. This method needs to be carried out through the model. Multi-angle calculation detection, huge amount of information, low efficiency

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • End-to-end unconstrained human face key point detection method
  • End-to-end unconstrained human face key point detection method
  • End-to-end unconstrained human face key point detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The present invention will be further described below in conjunction with embodiment:

[0020] An end-to-end unconstrained face keypoint detection method, including the following steps:

[0021] Step 1, determine several key points on the whole face in advance on the face picture, and collect the coordinate information y=(a of each key point 0 , b 0 ,...,a i , b i ,...,a n , b n ), where y is the coordinate information of the key point, (a i , b i ) is the coordinate information of the i-th key point;

[0022] Step 2. For facial pictures from different angles or facial pictures wearing accessories, the preset key points may be obscured, so it is necessary to determine the key point visibility information z=(z 0 ,...,z i ,...,z n ), and define when the keypoint is visible z i The value of and z when the key point is invisible i value of z i is the visibility information of the i-th key point, in this embodiment, when the key point is visible, z i = 1; when ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an end-to-end unconstrained human face key point detection method, which belongs to the technical field of human face recognition. The method provided by the invention comprises the steps that a number of key points of a face are pre-determined; the visibility information of the key points is determined; multitasking training is carried out to predict the coordinate and visibility of the key points. An end-to-end training scheme is realized without additional information such as a 3D human face. Multi-human-face pose prediction of a multi-angle key point detection scheme is prevented. According to the invention, the time efficiency is improved; a human face with change of any angle can be processed; and a human face with any degree of occlusion can be processed.

Description

technical field [0001] The invention belongs to the technical field of face recognition, and in particular relates to an end-to-end unconstrained face key point detection method. Background technique [0002] Face alignment aims to locate some key positions in the face, such as the coordinate information of the corners of the eyes, the corners of the mouth, and the tip of the nose. Since the problem arises, various methods have been proposed one after another. However, these methods have always had a common problem: they cannot handle faces with large angles and severe occlusions at the same time. To solve this problem, 3D models or multi-angle models are usually introduced for key point detection. This method needs to be carried out through the model. Multi-angle calculation and detection has a huge amount of information and low efficiency. Contents of the invention [0003] In view of the above-mentioned defects of the prior art, the technical problem to be solved by t...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & AuthorityApplications(China)
IPC IPC(8): G06K9/00
CPCG06V40/161
Inventor肖春林周曦
OwnerGUANGZHOU YUNCONG INFORMATION TECH CO LTD