Gender Classification Using Gaze Distributions for Privacy-Protection of Training Samples

• INOUE Michiko

  鳥取大学大学院工学研究科

• NISHIYAMA Masashi

  鳥取大学大学院工学研究科

• IWAI Yoshio

  鳥取大学大学院工学研究科

Bibliographic Information

Other Title

• プライバシーが保護された訓練画像に対する視線位置分布を用いた性別認識

Abstract

We propose a method for classifying gender using training samples after applying privacy-protection. Recently, training samples containing individuals require to protect their privacy. Head regions of training sample are usually manipulated for privacy-protection. However, the accuracy of gender classification is degraded when directly using the protected training samples. Here, we aim to use the human visual capability that people can correctly recognize males and females though the head regions are manipulated. We use gaze distributions of observers who view stimulus images for the preprocessing of gender classifier. Experimental results show that our method improved the accuracy of gender classification after manipulating the training samples by masking, pixelation and blur for privacy-protection.

Journal

• Journal of the Japan Society for Precision Engineering

  Journal of the Japan Society for Precision Engineering 85 (12), 1094-1101, 2019-12-05

  The Japan Society for Precision Engineering

Keywords

• Gender classification
• training samples
• gaze distributions
• privacy-protection

Details

• CRID: 1390846609777786880
• NII Article ID: 130007757435
• DOI: 10.2493/jjspe.85.1094
• ISSN: 1882675X
• ISSN: 09120289
• Web Site: https://www.jstage.jst.go.jp/article/jjspe/85/12/85_1094/_pdf
• Text Lang: ja
• Data Source:
  • JaLC
  • Crossref
  • CiNii Articles
  • KAKEN
• Abstract License Flag: Disallowed