Age and Gender Recognition on Imbalanced Dataset of Face Images with Deep Learning

Dmitry Yudin, Maksim Shchendrygin, Alexandr Dolzhenko

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The paper describes usage of deep neural networks based on ResNet and Xception architectures for recognition of age and gender of imbalanced dataset of face images. Described dataset collection process from open sources. Training sample contains more than 210000 images. Testing sample have more 1700 special selected face images with different ages and genders. Training data has imbalanced number of images per class. Accuracy for gender classification and mean absolute error for age estimation are used to analyze results quality. Age recognition is described as classification task with 101 classes. Gender recognition is solved as classification task with two categories. Paper contains analysis of different approaches to data balancing and their influence to recognition results. The computing experiment was carried out on a graphics processor using NVidia CUDA technology. The average recognition time per image is estimated for different deep neural networks. Obtained results can be used in software for public space monitoring, collection of visiting statistics etc.

Original languageEnglish
Title of host publicationProceedings of the 4th International Scientific Conference on Intelligent Information Technologies for Industry, IITI 2019
EditorsSergey Kovalev, Andrey Sukhanov, Valery Tarassov, Vaclav Snasel
PublisherSpringer
Pages30-40
Number of pages11
ISBN (Print)9783030500962
DOIs
Publication statusPublished - 2020
Externally publishedYes
Event4th International Scientific Conference on Intelligent Information Technologies for Industry, IITI 2019 - Ostrava-Prague, Czech Republic
Duration: 2 Dec 20197 Dec 2019

Publication series

NameAdvances in Intelligent Systems and Computing
Volume1156 AISC
ISSN (Print)2194-5357
ISSN (Electronic)2194-5365

Conference

Conference4th International Scientific Conference on Intelligent Information Technologies for Industry, IITI 2019
Country/TerritoryCzech Republic
CityOstrava-Prague
Period2/12/197/12/19

Keywords

  • Age recognition
  • Classification
  • Deep neural network
  • Face image
  • Gender recognition
  • Imbalanced dataset

Fingerprint

Dive into the research topics of 'Age and Gender Recognition on Imbalanced Dataset of Face Images with Deep Learning'. Together they form a unique fingerprint.

Cite this