Method and device for locating facial feature points

A face feature and feature point technology, applied in the field of image processing, can solve the problem of large face shape error, and achieve the effect of reducing error and improving similarity

Active Publication Date: 2017-06-27
LENOVO (BEIJING) LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problem of large error between the face shape formed by the feature points in the shape model obtained in the prior art and the face shape in the target image, the embodiment of the present invention provides a method and device for locating face feature points

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
  • Method and device for locating facial feature points
  • Method and device for locating facial feature points
  • Method and device for locating facial feature points

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] The embodiment of the present invention provides a method for locating facial feature points, the method is based on the ASM algorithm, see figure 1 , the method includes:

[0045] Step 101: Obtain an image to be tested.

[0046] Step 102: In the image to be tested, perform initial positioning of the average shape model to obtain the initial positions of the feature points describing the organs of the human face in the image to be tested.

[0047] Step 103: Determine the type of the organ model describing the set organ of the face.

[0048] Optionally, the type can be classified according to one or more of facial expression, face orientation, thickness, opening and closing, and occlusion type.

[0049] Step 104: Based on the determined type of organ model, search for feature points in the image to be tested, and adjust the initial positions of the feature points of the face organs in the image to be tested.

[0050]The embodiment of the present invention adjusts the ...

Embodiment 2

[0052] The embodiment of the present invention provides a method for locating facial feature points, the method is based on the ASM algorithm, see figure 2 , the method includes:

[0053] Step 201: Obtain an image to be tested.

[0054] Step 202: In the image to be tested, perform initial positioning of the average shape model to obtain the initial positions of the feature points describing the organs of the human face in the image to be tested.

[0055] In this embodiment, the average shape model is a general model used when locating facial feature points, and the average shape model is the result obtained after averaging the feature points of all faces, regardless of the differences between individual faces sex.

[0056] In a specific implementation, when performing initial positioning, the position of the eye can be determined first in the image to be tested, that is, the position of the feature points describing the eye in the image to be tested can be determined, and t...

Embodiment 3

[0082] An embodiment of the present invention provides a device for locating facial feature points, see image 3 , the device consists of:

[0083] A first acquisition module 301, configured to acquire an image to be tested;

[0084] The second acquisition module 302 is used to perform initial positioning of the average shape model in the image to be tested, and obtain the initial positions of feature points describing the organs of the human face in the image to be tested;

[0085] A determining module 303, configured to determine the type of an organ model describing a set organ of a human face;

[0086] The adjustment module 304 is configured to search for feature points of the image to be tested based on the determined type of organ model, and adjust the initial positions of the feature points of the face organs in the image to be tested.

[0087] Optionally, the type can be classified according to one or more of facial expression, face orientation, thickness, opening an...

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 a facial feature point positioning method and device, and belongs to the technical field of image processing. The method includes the steps of obtaining an image to be detected, conducting initial positioning on an average shape model in the image to be detected so as to obtain initial positions of feature points for describing the organs of a face in the image to be detected, determining the types of organ models for describing the set organs of the face, conducting feature point search on the image to be detected on the basis of the organ models of the determined types, and regulating the initial positions of the feature points of the organs of the face in the image to be detected. According to the facial feature point positioning method and device, for different types of the set organs of the face in the image to be detected, the initial positions of the feature points of the organs of the face in the image to be detected are regulated on the basis of the organ shape models of different types, similarity between the feature points of the face and the image to be detected is improved, and errors between the face shape formed by the feature points of the face in the obtained image to be detected and the face shape in the image to be detected are reduced.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method and device for locating facial feature points. Background technique [0002] The facial feature point location method based on the ASM (Active Shape Model) algorithm is currently the mainstream technology for extracting facial feature points from videos and images, and has the advantages of fast speed and high precision. [0003] The face feature point localization method based on the ASM algorithm usually comprises at present: first establishes the average shape model for several face images, the average shape model is made up of a series of feature points, and all feature points are combined to form the face shape; then establish The gray-scale model near each feature point in the shape model, the gray-scale model of each feature point includes the gray-scale characteristics of the feature point; finally, the gray-scale model is used to search for the best pos...

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 & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/66
Inventor 赵丛
Owner LENOVO (BEIJING) LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap