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

A Facial Age Estimation Method Based on Correlated Gaussian Process Regression

A Gaussian process regression and face technology, applied in the field of computer vision and human-computer interaction, can solve problems such as general accuracy and inability to cover differences

Inactive Publication Date: 2019-06-21
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage is that the accuracy of the estimation is general, because there are some differences in the mapping relationship between each individual's facial features and the real age, and only one general model cannot cover all the above differences.

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 Facial Age Estimation Method Based on Correlated Gaussian Process Regression
  • A Facial Age Estimation Method Based on Correlated Gaussian Process Regression
  • A Facial Age Estimation Method Based on Correlated Gaussian Process Regression

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0107] Implementation language: Matlab, C / C++

[0108] Hardware platform: Intel core2E7400+4G DDR RAM

[0109] Software platform: Matlab2012a, VisualStdio2010

[0110] Adopt the method of the present invention, at first utilize Facetracker tool kit to extract the feature point of facial image on VisualStdio2010 platform, and record the feature point position corresponding to each image. Then use C++ or matlab programming to implement the algorithm according to the patent content, extract facial features and establish a two-layer regression relationship from facial features to age. Finally, according to the learned regression relationship, use the above code to estimate the corresponding age of the sample to be estimated.

[0111] The test databases of this patent are FG-NET and Morph 2 face databases respectively. There are a total of 1002 age-tagged color face images in the FG-NET library. All the images come from 82 people, about 12 images per person, and the face images...

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 present invention proposes a facial age estimation method based on correlation Gaussian process regression. The method first extracts the shape features of the facial image, and extracts the appearance features from the normalized light and shape normalized images; then, establishes a gender-differentiated Gaussian process from facial features to the target age according to the calibrated ages corresponding to all images Regression model, and solve the regression parameters; finally, when the facial age image to be estimated is given, the facial shape and appearance features are extracted and the corresponding age is estimated by using the learned Gaussian process regression model.

Description

technical field [0001] The invention belongs to the field of computer vision technology, relates to facial age estimation technology, and is mainly applied to the fields of age-based login control, age-differentiated advertisement, and age-related human-computer interaction technology. Background technique [0002] Facial age estimation technology refers to the technology of automatically estimating the age of the human body after analyzing the facial features of the human face through computer algorithms. Usually, a computer collects a face image (photo) through a camera, extracts and analyzes facial features, and automatically estimates the age corresponding to the image. Since this technology has very wide applications in age-related human interaction, age-based login control, and age-differentiated advertising, it has attracted extensive interest and attention from scholars in the field of computer vision. The existing facial age estimation algorithms can be divided int...

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
CPCG06V40/168
Inventor 潘力立王正宁郑亚莉
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA