Mixed features for face detection in thermal image

Chao Ma, Ngo Thanh Trung, Hideaki Uchiyama, Hajime Nagahara, Atsushi Shimada, Rin-Ichiro Taniguchi

研究成果: 著書/レポートタイプへの貢献会議での発言

1 引用 (Scopus)

抄録

An infrared (IR) camera captures the temperature distribution of an object as an IR image. Because facial temperature is almost constant, an IR camera has the potential to be used in detecting facial regions in IR images. However, in detecting faces, a simple temperature thresholding does not always work reliably. The standard face detection algorithm used is AdaBoost with local features, such as Haar-like, MB-LBP, and HOG features in the visible images. However, there are few studies using these local features in IR image analysis. In this paper, we propose an AdaBoost-based training method to mix these local features for face detection in thermal images. In an experiment, we captured a dataset from 20 participants, comprising 14 males and 6 females, with 10 variations in camera distance, 21 poses, and participants with and without glasses. Using leave-one-out cross-validation, we show that the proposed mixed features have an advantage over all the regular local features.

元の言語英語
ホスト出版物のタイトルThirteenth International Conference on Quality Control by Artificial Vision 2017
編集者Atsushi Yamashita, Hajime Nagahara, Kazunori Umeda
出版者SPIE
ISBN(電子版)9781510611214
DOI
出版物ステータス出版済み - 1 1 2017
イベント13th International Conference on Quality Control by Artificial Vision, QCAV 2017 - Tokyo, 日本
継続期間: 5 14 20175 16 2017

出版物シリーズ

名前Proceedings of SPIE - The International Society for Optical Engineering
10338
ISSN(印刷物)0277-786X
ISSN(電子版)1996-756X

その他

その他13th International Conference on Quality Control by Artificial Vision, QCAV 2017
日本
Tokyo
期間5/14/175/16/17

Fingerprint

Face Detection
Local Features
Face recognition
Infrared Image
Infrared radiation
Infrared Camera
AdaBoost
cameras
Adaptive boosting
Cameras
Thresholding
Temperature Distribution
image analysis
Image Analysis
Cross-validation
temperature distribution
education
Camera
Image analysis
Face

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

これを引用

Ma, C., Trung, N. T., Uchiyama, H., Nagahara, H., Shimada, A., & Taniguchi, R-I. (2017). Mixed features for face detection in thermal image. : A. Yamashita, H. Nagahara, & K. Umeda (版), Thirteenth International Conference on Quality Control by Artificial Vision 2017 [1033805] (Proceedings of SPIE - The International Society for Optical Engineering; 巻数 10338). SPIE. https://doi.org/10.1117/12.2266836

Mixed features for face detection in thermal image. / Ma, Chao; Trung, Ngo Thanh; Uchiyama, Hideaki; Nagahara, Hajime; Shimada, Atsushi; Taniguchi, Rin-Ichiro.

Thirteenth International Conference on Quality Control by Artificial Vision 2017. 版 / Atsushi Yamashita; Hajime Nagahara; Kazunori Umeda. SPIE, 2017. 1033805 (Proceedings of SPIE - The International Society for Optical Engineering; 巻 10338).

研究成果: 著書/レポートタイプへの貢献会議での発言

Ma, C, Trung, NT, Uchiyama, H, Nagahara, H, Shimada, A & Taniguchi, R-I 2017, Mixed features for face detection in thermal image. : A Yamashita, H Nagahara & K Umeda (版), Thirteenth International Conference on Quality Control by Artificial Vision 2017., 1033805, Proceedings of SPIE - The International Society for Optical Engineering, 巻. 10338, SPIE, 13th International Conference on Quality Control by Artificial Vision, QCAV 2017, Tokyo, 日本, 5/14/17. https://doi.org/10.1117/12.2266836
Ma C, Trung NT, Uchiyama H, Nagahara H, Shimada A, Taniguchi R-I. Mixed features for face detection in thermal image. : Yamashita A, Nagahara H, Umeda K, 編集者, Thirteenth International Conference on Quality Control by Artificial Vision 2017. SPIE. 2017. 1033805. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.2266836
Ma, Chao ; Trung, Ngo Thanh ; Uchiyama, Hideaki ; Nagahara, Hajime ; Shimada, Atsushi ; Taniguchi, Rin-Ichiro. / Mixed features for face detection in thermal image. Thirteenth International Conference on Quality Control by Artificial Vision 2017. 編集者 / Atsushi Yamashita ; Hajime Nagahara ; Kazunori Umeda. SPIE, 2017. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{97b69471e5054934b2a79522894cb7a5,
title = "Mixed features for face detection in thermal image",
abstract = "An infrared (IR) camera captures the temperature distribution of an object as an IR image. Because facial temperature is almost constant, an IR camera has the potential to be used in detecting facial regions in IR images. However, in detecting faces, a simple temperature thresholding does not always work reliably. The standard face detection algorithm used is AdaBoost with local features, such as Haar-like, MB-LBP, and HOG features in the visible images. However, there are few studies using these local features in IR image analysis. In this paper, we propose an AdaBoost-based training method to mix these local features for face detection in thermal images. In an experiment, we captured a dataset from 20 participants, comprising 14 males and 6 females, with 10 variations in camera distance, 21 poses, and participants with and without glasses. Using leave-one-out cross-validation, we show that the proposed mixed features have an advantage over all the regular local features.",
author = "Chao Ma and Trung, {Ngo Thanh} and Hideaki Uchiyama and Hajime Nagahara and Atsushi Shimada and Rin-Ichiro Taniguchi",
year = "2017",
month = "1",
day = "1",
doi = "10.1117/12.2266836",
language = "English",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Atsushi Yamashita and Hajime Nagahara and Kazunori Umeda",
booktitle = "Thirteenth International Conference on Quality Control by Artificial Vision 2017",
address = "United States",

}

TY - GEN

T1 - Mixed features for face detection in thermal image

AU - Ma, Chao

AU - Trung, Ngo Thanh

AU - Uchiyama, Hideaki

AU - Nagahara, Hajime

AU - Shimada, Atsushi

AU - Taniguchi, Rin-Ichiro

PY - 2017/1/1

Y1 - 2017/1/1

N2 - An infrared (IR) camera captures the temperature distribution of an object as an IR image. Because facial temperature is almost constant, an IR camera has the potential to be used in detecting facial regions in IR images. However, in detecting faces, a simple temperature thresholding does not always work reliably. The standard face detection algorithm used is AdaBoost with local features, such as Haar-like, MB-LBP, and HOG features in the visible images. However, there are few studies using these local features in IR image analysis. In this paper, we propose an AdaBoost-based training method to mix these local features for face detection in thermal images. In an experiment, we captured a dataset from 20 participants, comprising 14 males and 6 females, with 10 variations in camera distance, 21 poses, and participants with and without glasses. Using leave-one-out cross-validation, we show that the proposed mixed features have an advantage over all the regular local features.

AB - An infrared (IR) camera captures the temperature distribution of an object as an IR image. Because facial temperature is almost constant, an IR camera has the potential to be used in detecting facial regions in IR images. However, in detecting faces, a simple temperature thresholding does not always work reliably. The standard face detection algorithm used is AdaBoost with local features, such as Haar-like, MB-LBP, and HOG features in the visible images. However, there are few studies using these local features in IR image analysis. In this paper, we propose an AdaBoost-based training method to mix these local features for face detection in thermal images. In an experiment, we captured a dataset from 20 participants, comprising 14 males and 6 females, with 10 variations in camera distance, 21 poses, and participants with and without glasses. Using leave-one-out cross-validation, we show that the proposed mixed features have an advantage over all the regular local features.

UR - http://www.scopus.com/inward/record.url?scp=85020312468&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85020312468&partnerID=8YFLogxK

U2 - 10.1117/12.2266836

DO - 10.1117/12.2266836

M3 - Conference contribution

AN - SCOPUS:85020312468

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Thirteenth International Conference on Quality Control by Artificial Vision 2017

A2 - Yamashita, Atsushi

A2 - Nagahara, Hajime

A2 - Umeda, Kazunori

PB - SPIE

ER -