Two-dimension human face image recognizing method

A face image and recognition method technology, which is applied in the field of pattern recognition and computer vision, can solve problems such as time-consuming, time-consuming, and inability to overcome the influence of illumination changes on images, and achieve the effect of increased speed and high recognition rate

Active Publication Date: 2008-04-09
TSINGHUA UNIV
View PDF0 Cites 64 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, because it needs to optimize the shape and texture at the same time, it is time-consuming and easy to fall into the local minimum, and the initial feature point position needs to be obtained manually, which cannot m

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
  • Two-dimension human face image recognizing method
  • Two-dimension human face image recognizing method
  • Two-dimension human face image recognizing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] The face database in the present embodiment is taken from the three-dimensional face data of 200 Europeans, and each face data includes about 100,000 vertices, and the coordinates (x, y, z) and texture (R, G, B) Known.

[0044] The two-dimensional face image recognition method in this embodiment includes: building a three-dimensional face deformation model, three-dimensional reconstruction of the face image, generating a virtual image of posture and illumination changes, design of a change-limited classifier, and face image recognition.

[0045] As shown in Figure 1, the corresponding steps are specifically introduced below:

[0046] Step 101: Establish a 3D face deformation model based on a known 3D face database.

[0047] The specific process includes:

[0048] Step 101a: Obtain raw data such as coordinates (x, y, z) and textures (R, G, B) of vertices of all faces in the database, and perform quantization processing on the raw data.

[0049] A variety of methods ca...

Embodiment 2

[0166] In this embodiment, two face databases are taken as examples to illustrate the process of two-dimensional face image recognition in the present invention.

[0167] Face database 1 is a subset of the CMU PIE face database, which contains 67 facial images, each with 8 poses. Use a frontal face image for registration. The database is a two-dimensional image database used for data input in the registration phase.

[0168] The second face database is a 3D face database from 488 Chinese people, which is obtained by a 3D scanner. After preprocessing, a 3D deformation model of a face can be established according to Step 101 of Embodiment 1. The specific implementation of the following process is divided into three stages: training, registration, and recognition, as shown in Figure 6, Figure 7 and Figure 8. The specific process is introduced as follows:

[0169] Step 201: training phase.

[0170] For the input frontal face, the face area is automatically detected first.

[0...

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 method of two-dimensional face image recognition, pertaining to the field of pattern recognition and computer vision. The method includes that: building a three-dimensional face deformation model according to the known three-dimensional face database; inputting a two-dimensional face image to register, and rebuilding in three dimension the registered two-dimensional face image using the three-dimensional face deformation model to obtain the three-dimensional rebuilt result of the registered two-dimensional face image; by constructing an illumination model, generating a virtual image with the changing posture and illumination in the three-dimensional rebuilt result; designing a change limitation classifier using the virtual image; inputting the two-dimensional face image to be recognized, implementing feature extraction and compression processing, then inputting the features processed by extraction and compression processing to the change limitation classifier, outputting the classified result, and finally realizing the face image recognition. The method in the invention realizes the full automation of the recognition procedure, enhances the recognition accuracy, and largely improves the recognition speed.

Description

technical field [0001] The invention relates to the fields of pattern recognition and computer vision, in particular to a method for recognizing two-dimensional human face images. Background technique [0002] Although research on face recognition has continued for decades, it remains a challenging problem in the field of pattern recognition to this day. There are still a series of difficult problems in the face recognition method. For example, when the face posture, expression and ambient lighting (PIE, Pose Illumination Expression) change greatly, the recognition rate will drop sharply. How to solve the problem of face recognition under different postures, lighting and expression conditions is still a hot spot of current research. [0003] For the face recognition problem of pose and illumination changes, if the traditional method is used, it is necessary to obtain enough face training images for learning under different poses and illumination conditions. However, in many...

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
IPC IPC(8): G06K9/00G06K9/62
Inventor 丁晓青方驰薛峰丁镠刘长松彭良瑞
Owner TSINGHUA UNIV
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