Multi-view angle human face recognizing method based on non-linear tensor resolution and view angle manifold

A face recognition and tensor decomposition technology, applied in the field of multi-view face recognition, can solve problems such as the inability to establish a face surface model, the inability to accurately describe the linear and nonlinear changes in the face space, and the inability to achieve factor separation. The effect of avoiding the full search process, fast recognition speed and accurate identity coefficient

Inactive Publication Date: 2009-05-20
XIDIAN UNIV
View PDF0 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for complex face images with multi-factor changes, this method cannot establish a unified face surface model, so it cannot separate various factors that affect face generation, nor can it accurately describe the linear and nonlinear aspects of face space. linear change

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
  • Multi-view angle human face recognizing method based on non-linear tensor resolution and view angle manifold
  • Multi-view angle human face recognizing method based on non-linear tensor resolution and view angle manifold
  • Multi-view angle human face recognizing method based on non-linear tensor resolution and view angle manifold

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0045] Example 1, the specific steps are as follows:

[0046] Step 1, image normalization.

[0047] First, the face images under each viewing angle are calibrated according to the positions of the eyes and nose, and then geometrically normalized to align the face images.

[0048] Step 2, divide the database.

[0049] For the normalized face images, the leave-one-out method is used to divide the multi-view face image data set, and the face images from one set of viewpoints are selected as the test sample set, and the face images from other viewpoints are used as the training sample set.

[0050] Step 3, tensor decomposition of multi-view face data.

[0051] (3a) Select the training set of face images, the images contain the changes of identity and perspective, and the face image of the kth person under the perspective v is expressed as where k=1,...,K and v=1,...,N;

[0052] (3b) Use high-order singular value decomposition to decompose the tensor Y according to the followi...

example 2

[0082] Example 2, the specific steps are as follows:

[0083] Step 1, image normalization.

[0084] First, the face images under each viewing angle are calibrated according to the positions of the eyes and nose, and then geometrically normalized to align the face images.

[0085] Step 2, divide the database.

[0086] For the normalized face images, the multi-view face image dataset is divided by the leave-one-out method, and the face images from one set of viewpoints are selected as the test sample set, and the face images from other viewpoints are used as the training sample set;

[0087] Step 3, build a concept-driven perspective manifold.

[0088] A two-dimensional point set uniformly distributed on a semicircle is used to represent the perspective coordinates of a face image rotated from left to right out of plane, and the two-dimensional point set is used to form a concept-driven face perspective manifold V, such as image 3 shown, x is a coordinate point on the manifo...

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 for identifying multi-view human face based on nonlinear tensor resolution and view manifold, which comprises the following steps: normalizing the size of the multi-view human face; dividing multi-view human face images into a test set and a training set by adopting a method of leaving one out; arraying the human face images in the training set into a form of tensor along the direction of identity, view and pixel information change, resolving tensor data by using high-order singular values to obtain a coefficient matrix of identity, view and pixel factors of the human face images; using a data-concept driving mode to array and interpolate view coefficients to obtain the view manifold of human face; according to the rotating objective sequence of the human face, generating the view manifold through a concept driving mode; using the nonlinear tensor resolution to map the view manifold to a data space of the multi-view human face, obtaining a modular matrix of identity coefficient, and establishing a model of the multi-view human face; and adopting an iterative algorithm based on EM-like to solve a model parameter, and achieving identification by the parameter meeting the minimum reconstructed error criterion. The method has the advantages of high accuracy and high speed, and can be used for complex human face retrieval and identification under different view angles in the field of biological characteristic identification.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition and computer vision, and in particular relates to a multi-view face recognition method, which can be used for face retrieval and recognition under different viewpoints in the field of biometric identification. Background technique [0002] Biometrics will be one of the most important technological revolutions in the security and IT industries in the next few years. Modern research shows that human iris, fingerprint and palm shape can be used for identification. Compared with other biometric recognition technologies or systems, face recognition systems have the advantages of high recognition accuracy, convenience, friendliness, and naturalness. Therefore, face recognition is a non-invasive identification method that is easily accepted by people. The face image is affected by the interaction of various factors such as scene structure and character state, and the obtained face image has...

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): G06K9/00G06K9/62
Inventor 高新波田春娜李洁张颖刘振兴邓成肖冰牛振兴温静王秀美
Owner XIDIAN 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