“A Feature Selection Technique with Genetic Algorithm to Reduce the Visibility of Gradient-based Image Features”

Akira Suzuki, Shingo Ando, Masashi Morimoto, Hideki Koike, Shunichi Yonemura, Katsuyoshi Tanabe

Research output: Contribution to journalArticle

Abstract

This paper proposes a feature selection technique with genetic algorithm that reduces the risk of data leaks by reducing the visibility of gradient-based image features. Gradient-based image features, which are used in image classification, are capable of wide application and offer high classification accuracy. However, people can picture the original image in their minds easily from the features when used in high resolution because they are represent appearance. This creates privacy concerns when they are applied to face image recognition. To overcome this problem, we introduce a feature selection technique that uses the genetic algorithm to reduce the visibility of gradient-based image features without sacrificing the recognition rate significantly. To evaluate the performance of the proposed technology, we make an experimental feature selection system that incorporates gender classification software. An experiment shows that the proposed technology can well reduce the visibility of gradient-based image features without sacrificing the recognition rate.

Original languageEnglish
Pages (from-to)448-458
Number of pages11
JournalJournal of the Institute of Image Electronics Engineers of Japan
Volume40
Issue number3
DOIs
Publication statusPublished - 2011
Externally publishedYes

Fingerprint

Visibility
Feature extraction
Genetic algorithms
Image recognition
Image classification
Experiments

Keywords

  • feature selection
  • genetic algorithm
  • image feature
  • visibility of feature

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Electrical and Electronic Engineering

Cite this

“A Feature Selection Technique with Genetic Algorithm to Reduce the Visibility of Gradient-based Image Features”. / Suzuki, Akira; Ando, Shingo; Morimoto, Masashi; Koike, Hideki; Yonemura, Shunichi; Tanabe, Katsuyoshi.

In: Journal of the Institute of Image Electronics Engineers of Japan, Vol. 40, No. 3, 2011, p. 448-458.

Research output: Contribution to journalArticle

@article{d9a66aa56c58424dad62c9b8d2f181b1,
title = "“A Feature Selection Technique with Genetic Algorithm to Reduce the Visibility of Gradient-based Image Features”",
abstract = "This paper proposes a feature selection technique with genetic algorithm that reduces the risk of data leaks by reducing the visibility of gradient-based image features. Gradient-based image features, which are used in image classification, are capable of wide application and offer high classification accuracy. However, people can picture the original image in their minds easily from the features when used in high resolution because they are represent appearance. This creates privacy concerns when they are applied to face image recognition. To overcome this problem, we introduce a feature selection technique that uses the genetic algorithm to reduce the visibility of gradient-based image features without sacrificing the recognition rate significantly. To evaluate the performance of the proposed technology, we make an experimental feature selection system that incorporates gender classification software. An experiment shows that the proposed technology can well reduce the visibility of gradient-based image features without sacrificing the recognition rate.",
keywords = "feature selection, genetic algorithm, image feature, visibility of feature",
author = "Akira Suzuki and Shingo Ando and Masashi Morimoto and Hideki Koike and Shunichi Yonemura and Katsuyoshi Tanabe",
year = "2011",
doi = "10.11371/iieej.40.448",
language = "English",
volume = "40",
pages = "448--458",
journal = "Journal of the Institute of Image Electronics Engineers of Japan",
issn = "0285-9831",
publisher = "Institute of Image Electronics Engineers of Japan",
number = "3",

}

TY - JOUR

T1 - “A Feature Selection Technique with Genetic Algorithm to Reduce the Visibility of Gradient-based Image Features”

AU - Suzuki, Akira

AU - Ando, Shingo

AU - Morimoto, Masashi

AU - Koike, Hideki

AU - Yonemura, Shunichi

AU - Tanabe, Katsuyoshi

PY - 2011

Y1 - 2011

N2 - This paper proposes a feature selection technique with genetic algorithm that reduces the risk of data leaks by reducing the visibility of gradient-based image features. Gradient-based image features, which are used in image classification, are capable of wide application and offer high classification accuracy. However, people can picture the original image in their minds easily from the features when used in high resolution because they are represent appearance. This creates privacy concerns when they are applied to face image recognition. To overcome this problem, we introduce a feature selection technique that uses the genetic algorithm to reduce the visibility of gradient-based image features without sacrificing the recognition rate significantly. To evaluate the performance of the proposed technology, we make an experimental feature selection system that incorporates gender classification software. An experiment shows that the proposed technology can well reduce the visibility of gradient-based image features without sacrificing the recognition rate.

AB - This paper proposes a feature selection technique with genetic algorithm that reduces the risk of data leaks by reducing the visibility of gradient-based image features. Gradient-based image features, which are used in image classification, are capable of wide application and offer high classification accuracy. However, people can picture the original image in their minds easily from the features when used in high resolution because they are represent appearance. This creates privacy concerns when they are applied to face image recognition. To overcome this problem, we introduce a feature selection technique that uses the genetic algorithm to reduce the visibility of gradient-based image features without sacrificing the recognition rate significantly. To evaluate the performance of the proposed technology, we make an experimental feature selection system that incorporates gender classification software. An experiment shows that the proposed technology can well reduce the visibility of gradient-based image features without sacrificing the recognition rate.

KW - feature selection

KW - genetic algorithm

KW - image feature

KW - visibility of feature

UR - http://www.scopus.com/inward/record.url?scp=85024745273&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85024745273&partnerID=8YFLogxK

U2 - 10.11371/iieej.40.448

DO - 10.11371/iieej.40.448

M3 - Article

VL - 40

SP - 448

EP - 458

JO - Journal of the Institute of Image Electronics Engineers of Japan

JF - Journal of the Institute of Image Electronics Engineers of Japan

SN - 0285-9831

IS - 3

ER -