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

Canthus and pupil location method based on VPP and improved SUSAN

A positioning method and pupil technology, applied in the field of image processing, can solve problems such as inability to give correct positioning and difficulty in positioning eyes, and achieve the effect of improving precision and high accuracy.

Inactive Publication Date: 2005-10-26
SHANGHAI JIAO TONG UNIV
View PDF0 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But in most cases, due to the influence of complex background and lighting, it is very difficult to locate the eyes only relying on grayscale and edges
[0003] After searching the prior art documents, it was found that Rein-Lien Hsu et al. (Rein-Lien Hsu, Mohamed Abdel-Mottaleb, Anil K. Jain Face Detection In Color images IEEETRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL 24, NO.5.MAY 2002) gave the distribution of each component of the eye area in the YCbCr color space through the statistics of a large number of samples, and roughly positioned the position of the human eye according to the distribution of these components, but for different lighting, race and face posture , this method still cannot give the correct positioning

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
  • Canthus and pupil location method based on VPP and improved SUSAN
  • Canthus and pupil location method based on VPP and improved SUSAN
  • Canthus and pupil location method based on VPP and improved SUSAN

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The technical solution of the present invention will be further described in detail below in conjunction with specific embodiments.

[0027] The human face image database captured by the eye image used in the embodiment. Whole invention realization process is as follows:

[0028] 1. The smoothing processing of eye region image, uses median filter to carry out smooth denoising among the present invention, can further remove the noise in the image by this step, can greatly improve the precision of canthus and pupil location. The original image and the smoothed image such as figure 1 shown.

[0029] 2. Calculate the VPF of each column of the smoothed image, that is, calculate the variance of each column, such as figure 2 shown.

[0030] 3. Compute the derivative of the VPF from the previous step. like image 3 shown. At the same time draw the pupil circle, such as Figure 4 shown.

[0031] 4. Apply the improved SUSAN operator on the eye area to find some candidat...

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

A method based on VPF and improved SVSAN for locating the canthi and pupil in order to recognize human face, sex, expression, age, etc includes such steps as determining the horizontal coordinate of pupil center according to the maximum of VPF, determining the left and right boundaries of pupil (the diameter and radius of pupil) according to the positions of the maximal and minimal first-order derivative of VPF, matching the circle with template to obtain the circle center of pupil, and determining the positions of canthi according to improved SUSCAN operator.

Description

technical field [0001] The invention relates to a positioning method of pupils and eye corners based on VPF (variance projection function) and improved SUSAN (minimum single-valued segment attraction kernel) applied to face recognition, eyeball posture estimation and expression recognition, and relates to the field of image processing. Background technique [0002] Face feature point detection is a key technology in applications such as face recognition, expression recognition, and gender recognition. The accuracy of feature point location directly affects the accuracy of recognition, and eye features are particularly important in face features. Therefore, accurately locating the position of the eyes can greatly improve the accuracy of recognition. The positioning of the current eye position is mainly based on the analysis of image grayscale and image edge. But in most cases, due to the complex background and lighting effects, it is a very difficult job to locate the eyes o...

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): A61B5/1171
Inventor 杜春华杨杰郑忠龙戈新良李冯
Owner SHANGHAI JIAO TONG 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