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

Face image age evaluation method based on convolutional neural network

A technology of convolutional neural network and face image, which is applied in computing, computer components, instruments, etc., can solve problems such as errors in recognition results, and achieve the effect of improving accuracy

Active Publication Date: 2017-03-15
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF3 Cites 34 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This leads to large errors in the recognition results of traditional age recognition technologies.

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 image age evaluation method based on convolutional neural network
  • Face image age evaluation method based on convolutional neural network
  • Face image age evaluation method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] Preferred embodiments of the present invention are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention, and are not intended to limit the protection scope of the present invention.

[0055] The face image age estimation method based on the convolutional neural network of the present invention mainly makes each real age correspond to an apparent age distribution by modeling the randomness of the apparent age of the face, and then realizes that each real age corresponds to the age distribution based on Multiple apparent age labels weighted by Gaussian distribution, and the method of convolutional neural network is used to train the age estimation model.

[0056] The present invention includes model training and age judgment two parts;

[0057] Model training:

[0058] In step A1, the original samples of face images of differ...

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 discloses a face image age evaluation method based on the convolutional neural network (CNN). According to the traditional age identification technology, a training sample only corresponds to one age label, so relationships among adjacent ages are neglected. According to the method based on the convolutional neural network, each sample corresponds to multiple age labels, so an age estimation model acquired through training can be more precise. The method comprises steps that firstly, face detection, face key point detection, face alignment and image cutting for inputted images are carried out; secondly, modeling for an age aging process is carried out, and probability of each apparent age is calculated and is stored to form an age distribution table; thirdly, the aligned face images are utilized in combination with the age distribution table and a target function to train the CNN network; lastly, the trained CNN network can be utilized to carry out age estimation on the inputted face images.

Description

technical field [0001] The invention relates to the field of image recognition, in particular to a method for estimating the age of a face image based on a convolutional neural network. Background technique [0002] In traditional age recognition techniques, there is often a one-to-one relationship between samples and age labels during training, that is, one sample corresponds to only one age label. Such a training process assumes that samples of different ages are independent of each other, thus ignoring the relationship between adjacent ages. [0003] In fact, the aging process of people is affected by various factors, such as genes, living environment, working environment, etc. The aging rate of each person is different, which will make some people of the same age look younger and some look older . On the other hand, the process of human aging is also a slow process, and people of similar ages look very similar in age. It can be seen from this that a person's apparent ...

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
CPCG06V40/178G06V40/161G06V40/168
Inventor 万军李子青雷震谭资昌
Owner INST OF AUTOMATION CHINESE ACAD OF SCI
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