Multi-mode face identification method

A face recognition, multi-modal technology, applied in the field of face recognition, can solve the problems of whether the face has appeared in the work, the new face cannot be stored in memory, and it is difficult to take into account the impact of the overall differential recognition accuracy of the face.

Inactive Publication Date: 2015-04-29
天津瑞为拓新科技发展有限公司
View PDF0 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In fact, face patterns often have non-rigid deformations (such as smiles and frowns), and it is difficult to take into account the impact of overall differences and local variations on recognition accuracy by simply using a global feature matching method or a local feature matching method....

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-mode face identification method
  • Multi-mode face identification method
  • Multi-mode face identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] A certain face recognition, detection of the original image, wavelet classification image, extraction of global spectral features, drawing into a spectral image, when extracting global spectral features, the formula of two-dimensional Fourier transform is: I ( u , v ) = F [ f ( x , y ) ] = ∫ - ∞ + ∞ ∫ - ∞ + ∞ f ( x , y ) e - 2 πj ( ux + ...

Embodiment 2

[0036] In embodiment 1, the value of d is less than the preset value T, then the global spectral feature is matched, the local geometric feature is matched, the face is segmented, the eyebrow parts and their binary images are extracted, and the Hu invariant moments of the image are used to describe For the eyebrow part, the process of calculating the 7 invariant moments of Hu is as follows: calculate the centroid of the image, find the required center distance, and find the required normalized center distance, where the centroid calculation formula is: i ‾ = m 10 / m 00 j ‾ = m...

Embodiment 3

[0048] In embodiment 2, if the value of d is less than the empirical value D, it is considered that the two eyebrow regions match, and the face is recognized.

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 multi-mode face identification method which comprises the following three steps: firstly, performing global spectrum face matching on a to-be-matched face and faces in a database; secondly, if the matching is failed, judging that two face modes are not matched, and if the matching is successful, performing geometric characteristic matching and judging whether the two face modes are matched or not; finally, transmitting face data without global spectrum face matching and geometric characteristic matching into a new face memory database in the database. According to the method, overall difference of different faces is distinguished by a global spectrum face matching method, and local tiny difference of the faces are distinguished in combination with local geometric characteristic matching, so that the face identification performance is improved; for newly acquired faces, if the newly acquired faces are not matched with the faces in the original database, the newly acquired faces are stored in the new face memory database module of the database, so that original images can be quickly called from the new face memory database module during re-matching.

Description

technical field [0001] The invention relates to a face recognition method, in particular to a multi-mode face recognition method combining global feature matching and local feature matching. Background technique [0002] There are many methods of face recognition, which can be roughly divided into two categories: matching based on global features and matching based on local features. Global feature matching methods include PCA, 2DPCA, LDA, spectral face, etc., and local feature matching methods include geometric features, wavelet features, and LBP features. In fact, face patterns often have non-rigid deformations (such as smiles and frowns), and it is difficult to take into account the impact of overall differences and local variations on recognition accuracy by simply using a global feature matching method or a local feature matching method. New faces that do not match the faces in the database cannot be memorized and stored, which brings trouble to the work of investigati...

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
CPCG06V40/161G06V40/171
Inventor 孙伟
Owner 天津瑞为拓新科技发展有限公司
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