Age estimation method based on deep learning

A deep learning and image technology, applied in the field of computer vision, can solve problems such as low-resolution face images, achieve fast running time, ensure sample diversity, and small depth models

Inactive Publication Date: 2018-01-16
SICHUAN CHANGHONG ELECTRIC CO LTD
View PDF4 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention proposes a lightweight deep learning model, the purpose of which is to improve the low time-consuming problem of the existing algorithm recognition rate, especially suitable for the age estimation problem of low-resolution and occluded face images

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
  • Age estimation method based on deep learning
  • Age estimation method based on deep learning
  • Age estimation method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present invention is an age estimation method based on deep learning, including the establishment of a database in the early stage, model design and training, and later testing. The specific implementation methods are as follows:

[0023] (1) Establish a face age estimation database. The face database established by the present invention contains 600,000 face images, and each image has gender and age labels. The range of age labels is 0-61, where label 61 indicates people over 60 years old. The images are from the Internet and self-collected images, and some are from videos. The present invention organizes sample patterns such as figure 1 shown. Collect samples of various ages on the Internet, mainly from marriage and love websites and parenting websites, then train the model, classify the newly downloaded data with the model, and then manually recalibrate the pictures with large age estimates, update the training library, and retrain the model, so Repeatedly up...

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 an age estimation method based on deep learning. The age estimation method based on deep learning comprises steps of (1) constructing an age database, (2) performing pre-processing on images of the constructed age database, (3) performing unification and normalization on sizes of aligned images to obtain images with a size being 64*64, (4) taking the obtained images and corresponding labels as inputs of a deep model, using a CNN convolution deep network to train an age estimation model, (5) inputting an age estimation model into a tested image to obtain similarity values of tested images on various kinds of labels, (6) multiplying the obtained corresponding label with the obtained similarity value and then adding obtained corresponding label and the obtained similarity value to obtain a final age estimation result. The age estimation method based on deep learning can obtain a smaller deep model and is fast in operation time and high in an age estimation identification rate. The database comprises massive samples of children and senior people and can effectively identify age of a special group.

Description

technical field [0001] The invention relates to an age estimation method, in particular to an age estimation model design method based on deep learning, which belongs to the field of computer vision. Background technique [0002] As a branch of computer vision, age estimation techniques have received more and more attention in recent years. The so-called age estimation is based on face images, extracting image age features, using computer vision technology for related processing and analysis, and judging the age of face images. Through the accurate age prediction of face images, people's living habits and styles can be changed, which has very important practical significance. In terms of daily life, age prediction results can be used to provide precise services for people of different ages, and quickly mark young children and the elderly in crowded areas to facilitate the management of special groups. More and more mobile entertainment software has also added age estimatio...

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): G06K9/00G06N3/04G06N3/08
Inventor 曹艳艳王昆
Owner SICHUAN CHANGHONG ELECTRIC CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap