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

Face low-level feature constructing method

A technology of low-level features and construction methods, which is applied in the direction of instruments, character and pattern recognition, computer components, etc., and can solve problems such as inability to respond to faces of different quality

Inactive Publication Date: 2016-05-18
SHANDONG UNIV OF TECH
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the construction of this image is simply the average superposition of images, and the energy map obtained by construction cannot reflect the influence of faces of different qualities or different degrees of importance.

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
  • Face low-level feature constructing method
  • Face low-level feature constructing method
  • Face low-level feature constructing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] Figure 1~5 It is the best embodiment of the present invention, below in conjunction with attached Figure 1~5 The present invention will be further described.

[0043] Refer to attached Figure 1~5 : A method for constructing the underlying features of a human face. First, read in the reference face and multi-pose face images in the face database; secondly, locate the coordinates of the binocular positions of the reference face and the multi-pose face; Calculate the left and right sway angle of the face based on the position coordinates of the eyes before and after the posture change; fourthly, calculate the weight value of the face that has swayed according to the obtained sway angle; finally, use the calculated weight of the face that has swayed value to construct a weighted underlying feature image of the face.

[0044] 1. Read reference face and multi-pose face images

[0045] to combine figure 2 , which fully illustrates the calculation steps and effectivene...

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 provides a face low-level feature constructing method and belongs to the technical field of mode identification and feature extraction. The face low-level feature constructing method is characterized by comprising the following steps of: 1.1, reading a reference face image and multi-attitude face images with changing attitudes from a face database; 1.2, positioning double-eye position coordinates of the reference face and the multi-attitude faces, and determining left-right swinging angles of the multi-attitude faces; 1.3, according to the obtained left-right swinging angles, calculating weighted values of the faces having swinging changes; and 1.4, according to the obtained weighted values, calculating a new face low-level feature image. By adopting the new face low-level feature constructing method, different influences of different faces are more accurately reflected, the new low-level features are better fused with comprehensive information of the plurality of face images, the storage space is saved, the complexity of calculation is lowered, the noise interference in a single image is weakened, and a new feature simple to calculate and significant in effect is provided for later deep feature extraction and classified identification.

Description

technical field [0001] The invention discloses a new method for constructing the underlying feature of human face, which belongs to the technical field of pattern recognition and feature extraction. Background technique [0002] Extracting good features has always been the essence of pattern recognition. According to the different ways of feature generation, image features are divided into two categories: natural features and artificial features. Artificial features are features constructed through calculations, such as histograms, spectrograms, chain codes, etc.; natural features are inherent features of the image itself, which can be directly obtained through the human visual perception system, such as image edges, textures, shapes, points, line etc. In face recognition, by measuring the face, a description of the face can be obtained, that is, a point in the measurement space is used to represent a face. [0003] At present, the research on algebraic feature extraction...

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): G06K9/00
CPCG06V40/168
Inventor 邹国锋傅桂霞姜殿波张存山高明亮
Owner SHANDONG UNIV OF TECH
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