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

Picture facial contour feature extraction method based on logarithmic difference

A technology of contour feature and extraction method, applied in the field of face recognition

Inactive Publication Date: 2015-03-25
SUN YAT SEN UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] In order to solve the above defects in the prior art, the present invention provides a logarithmic difference-based face profile feature extraction method, which has the characteristics of stable numerical calculation and strong adaptability, especially when the illumination of the picture changes drastically, or the In the case of other complex changes, the image processing effect is still very good

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
  • Picture facial contour feature extraction method based on logarithmic difference
  • Picture facial contour feature extraction method based on logarithmic difference
  • Picture facial contour feature extraction method based on logarithmic difference

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] In order to solve the problem that the face feature extraction method provided by the prior art is unstable in numerical calculation and the recognition effect of the extracted face features is poor, the present invention provides a method for extracting face contour features of a picture based on logarithmic difference, and the technical solution as follows:

[0054] A method for extracting facial contour features of a picture based on logarithmic difference, the method extracts a differential boundary map of picture pixels, and performs arctan transformation to obtain facial contour features, as follows:

[0055] S1. Adjust the gray value interval of the picture to [1,256], set the current pixel to be processed as (x, y), and divide the neighborhood N with this pixel as the center (x,y) , when the pixel point (x, y) is located at the boundary of the picture, use the mirror reflection continuation method to extend the neighborhood of the pixel point (x, y), and the gra...

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 picture facial contour feather extraction method based on the logarithmic difference. According to the method, facial contour features are obtained by extracting difference boundary diagrams of all picture pixel points and carrying out conversion. Compared with the prior art, the method has the advantages that numeric calculation is stable, and adaptability is high, and still has the good picture processing effect on the condition that picture illumination changes greatly, or other complex changes exist. Meanwhile, the weight is introduced for adjusting the difference boundary diagrams of subneighborhoods, and the recognition rate of the extracted facial contour feature is more stable during recognition.

Description

technical field [0001] The present invention relates to the field of face recognition, and more specifically, to a method for extracting face contour features from a picture based on logarithmic difference. Background technique [0002] In the prior art, when recognizing a face picture, if the face picture is affected by light, the Lambert model is generally selected to process the face picture. The principle of the Lambert model is as follows: decompose the pixel value f(x,y) of an m×n-dimensional face picture pixel into a product of an illumination component S and a reflectance component ρ: [0003] f(x,y)=ρ(x,y)S(x,y), 1≤x≤m, 1≤y≤n. [0004] Among them, the reflectance component ρ contains the contour features of the face, so ρ needs to be decomposed. It is generally believed that the illumination component S changes slowly and satisfies the following formula: [0005] S(x-i△x,y-i△y)≈S(x,y) [0006] Among them, △x and △y represent a small amount of translation, that i...

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): G06K9/00
CPCG06V40/169G06V10/752
Inventor 赖兆荣戴道清
Owner SUN YAT SEN 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