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

Man face image identifying method based on man face geometric size normalization

A face image and geometric size technology, applied in the field of image processing, can solve problems such as distance instability, instability, and affecting the recognition rate of face recognition, so as to achieve good normalization effect, increase recognition rate, and improve face recognition. The effect of visual effects

Inactive Publication Date: 2007-10-24
TSINGHUA UNIV
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] (5) Differences in face images caused by illumination
[0008] In the general face recognition algorithm, there is no normalization processing of the standard geometric size of the face image, and the normalization processing of the geometric size will not only affect the recognition rate of face recognition, but also affect the number of people in the face database. face visual effects
The existing face geometric size normalization method is mainly based on the distance between the two eyes, however, the distance between the two eyes of the face is unstable, especially in the horizontally rotated face image, this Instability is more prominent

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
  • Man face image identifying method based on man face geometric size normalization
  • Man face image identifying method based on man face geometric size normalization
  • Man face image identifying method based on man face geometric size normalization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The embodiments of the face image recognition method based on the normalization of face geometric dimensions proposed by the present invention are described in detail with reference to the accompanying drawings, and the method includes the following steps:

[0044] 1) Determine the coordinate position (x) of a point A on the left eyeball on the input face image (as shown in Figure 1). 1 , y 1 ), the coordinate position of a point B on the right eyeball (x 2 , y 2 ), and draw a straight line L through the points A and B 1 , and determine the mandibular point C 0 Coordinate (x 0 , y 0 ).

[0045] In this step, the coordinate positions of the points A and B on the left and right eyeballs can be realized by two methods. One method is to use the mouse to directly determine the coordinate positions of the points A and B on the left and right eyeballs on the face image, and the other method It uses an algorithm that combines integral projection and feature space analysi...

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 relates to a human face image recognizing method based on the geometric size normalization of a human face, belonging to image processing technical field, and comprising the steps of: determining the coordinates of the left and right eyeballs on an input human face image, and according to the coordinates, rotating the image to the horizontal position to obtain a new human face image 2, then determining the coordinates of left and right eyeballs and mandible of the new human face image 2, specifying the numeric value of normalized geometric size of a human face, zooming in or out the new human face 2 to obtain another human face image 3 meeting the standard distance; according to the coordinates of left and right eyeballs and mandible of the human face image 3, cutting the human face image 3 to obtaina standard normalized human face image; forming training-set, known and to-be- recognized human face images into human face images of normalized geometric size and extracting human face characteristics, and in a known human face database, adopting the methods of calculating similarity and sequencing according to the similarity to recognize the human face. The invention obviously improves the visual effect of a human face and makes a higher increase in the recognizing ratio.

Description

technical field [0001] The invention belongs to the technical field of image processing, and particularly relates to a method for improving a face recognition rate. Background technique [0002] Face recognition involves many disciplines, including image processing, computer vision, pattern recognition, etc. It is also closely related to the research results of physiology and biology on the structure of the human brain. The recognized difficulties in face recognition are: [0003] (1) Face changes caused by age; [0004] (2) Face diversity caused by posture; [0005] (3) Plastic deformation of the face caused by expressions; [0006] (4) The multiplicity of face patterns caused by factors such as glasses and makeup; [0007] (5) Differences of face images caused by illumination. [0008] In general face recognition algorithms, there is no normalization of the standard geometric size of the face image, and the normalization of the geometric size will not only affect the ...

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): G06K9/00
Inventor 苏光大孟凯杜成王俊艳
Owner TSINGHUA 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