Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Accurate positioning method of human face characteristic points

A technology of precise positioning and facial features, applied in the field of precise positioning of facial feature points and face recognition, it can solve the problem of inaccurate positioning of feature points, and achieve the effect of improving positioning accuracy, positioning accuracy and positioning accuracy.

Inactive Publication Date: 2009-10-28
PEKING UNIV
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the problem of inaccurate positioning of feature points in the prior art, and propose a method for precise positioning of feature points of human faces

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
  • Accurate positioning method of human face characteristic points
  • Accurate positioning method of human face characteristic points
  • Accurate positioning method of human face characteristic points

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The present invention will be further described below through specific embodiments in conjunction with the accompanying drawings.

[0045] Embodiments of the present invention include the following steps:

[0046] a. Select the grayscale image of 9 face images, take the right corner of the mouth in the image as a feature point, take this feature point as the center, and intercept a circular analysis window of the same size, such as Figure 6 shown;

[0047] b. Divide each analysis window into 4 equal parts to obtain 4 analysis areas, each analysis area contains feature points;

[0048] c. For each analysis area on each analysis window, do the following:

[0049] Perform 3 LBP processes on the analysis area to obtain 3 LBP maps. In each LBP process, the distances between the central point and surrounding points are 1, 2, and 3 pixels respectively;

[0050] Obtain respective histograms from the 3 LBP diagrams;

[0051] Adding the 3 histograms to obtain the histogram s...

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 accurate positioning method of human face characteristic point, pertaining to the technical field of digital image processing. The method comprises the steps of: intercepting an analysis window from an existing human face image; equally dividing the analysis window by taking the characteristic point as the center and obtaining analysis areas; conducting R times of LBP processing on each analysis area (the distances between the center point and the peripheral points for the processing are respectively 1 pixel, 2 pixels to R pixels.) and obtaining R LBP graphs, thus obtaining all the histograms; taking the summation of the R histograms as the histogram of the analysis area; taking the average value of the histograms of all analysis areas as the characteristic histograms of the analysis areas; intercepting an analysis window from the graph to be analyzed based on each pixel and dividing the analysis window into analysis areas in the same way; conducting Line LBP processing on the analysis areas and obtaining the LBP graphs, thus obtaining the histograms, and calculating the chi-square distances between the histograms and the characteristic histograms of the analysis areas; summing the chi-square distances; and taking the pixel point when the sum is minimum as the characteristic point. The method can be applied to the accurate positioning of the human face characteristic points in the processing of the human face image.

Description

technical field [0001] The invention relates to face recognition, in particular to a method for accurately locating feature points of a face. It belongs to the technical field of digital image processing. Background technique [0002] In the current automatic face recognition system, the feature point positioning technology is relatively weak. Researchers in the field of face detection often do not care about the accuracy of feature point positioning, and only give the approximate location information of the face. Most researchers who do recognition algorithms assume that the positions of feature points are given when doing recognition experiments, for example, the positions of two eyes are given. However, the precise positioning of feature points is far from being a problem that can be solved by existing technologies, especially when the imaging conditions are relatively harsh and the expression changes are relatively large, the key point positioning is more difficult. 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 & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/64
Inventor 祝世虎封举富
Owner PEKING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com