Ajou University repository

Age and gender estimation using deep residual learning network
  • Lee, Seok Hee ;
  • Hosseini, Sepidehsadat ;
  • Kwon, Hyuk Jin ;
  • Moon, Jaewon ;
  • Koo, Hyung Il ;
  • Cho, Nam Ik
Citations

SCOPUS

0

Citation Export

Publication Year
2018-05-30
Journal
2018 International Workshop on Advanced Image Technology, IWAIT 2018
Publisher
Institute of Electrical and Electronics Engineers Inc.
Citation
2018 International Workshop on Advanced Image Technology, IWAIT 2018, pp.1-3
Keyword
Age estimationDeep learningGender estimationImage processingMachine learningResidual learning
Mesh Keyword
Age estimationEstimation methodsGender estimationsInput imageLearning methodsLearning modelsLearning networkResidual learning
All Science Classification Codes (ASJC)
Computer Networks and CommunicationsComputer Vision and Pattern RecognitionMedia Technology
Abstract
In this paper, we propose a deep residual learning model for age and gender estimation. Our method detects faces in input images, and then the age and gender of each face are estimated. The estimation method consists of three deep neural networks where we adopt residual learning methods. We train the model with IMDB-WIKI database [4]. However, since the database has only a small number of face images under the age of 20, we augment the set by collecting the images on the Internet. Experimental results show that the proposed model with residual learning yields improved performance.
Language
eng
URI
https://aurora.ajou.ac.kr/handle/2018.oak/36301
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85048817247&origin=inward
DOI
https://doi.org/10.1109/iwait.2018.8369763
Journal URL
http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=8365178
Type
Conference
Show full item record

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

 KOO, HYUNG IL Image
KOO, HYUNG IL구형일
Department of Electrical and Computer Engineering
Read More

Total Views & Downloads

File Download

  • There are no files associated with this item.