Unlock instant, AI-driven research and patent intelligence for your innovation.

A feature extraction method of image face contour based on logarithmic difference

A technology of contour feature and extraction method, which is applied in the field of face recognition to achieve the effects of stable recognition rate, strong adaptability, and stable numerical calculation

Inactive Publication Date: 2017-08-11
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
  • A feature extraction method of image face contour based on logarithmic difference
  • A feature extraction method of image face contour based on logarithmic difference
  • A feature extraction method of image face contour 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 method for extracting face contour features of a picture based on logarithmic difference. The method obtains the face contour features by extracting the difference boundary map of all pixels in the picture. Compared with the prior art, the method has stable numerical operation , strong adaptability, especially in the case of drastic lighting changes or other complex changes in the picture, the processing effect on the picture is still very good; at the same time, the weight is introduced to adjust the difference boundary map of the sub-neighborhood, so The recognition rate of the extracted face contour features is more stable when it is recognized.

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-iΔx,y-iΔy)≈S(x,y) [0006] Among them, Δx and Δy 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 Patents(China)
IPC IPC(8): G06K9/00
CPCG06V40/169G06V10/752
Inventor 赖兆荣戴道清
Owner SUN YAT SEN UNIV