Face Identification for an in-vehicle Surveillance System Using Near Infrared Camera

Minsong Ki, Bora Cho, Taejun Jeon, Yeongwoo Choi, Hyeran Byun

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Face identification is an essential topic in surveillance system research. Surveillance systems have many unconstrained conditions, e.g., brightness, occlusion, and user state variations. In this paper, we propose a multi-SVM based face recognition method using a near-infrared camera. Our method has a face identification scenario optimized for an in-vehicle surveillance system, which comprises two steps: (i) registering a driver and (ii) recognizing whether the driver is a registered. We perform feature extraction and recognition for each facial landmark. In the case of extreme exposure to light, we convert normal face images into simulated light overexposed images for learning. Thus, face classifiers for normal and extreme illumination conditions are simultaneously generated. We also create a new face dataset and evaluate our method with both our new and PolyU NIR datasets. Experimental results show that we achieve significantly higher recognition accuracy than existing methods.

Original languageEnglish
Title of host publicationProceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538692943
DOIs
Publication statusPublished - 2019 Feb 11
Event15th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2018 - Auckland, New Zealand
Duration: 2018 Nov 272018 Nov 30

Publication series

NameProceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance

Conference

Conference15th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2018
CountryNew Zealand
CityAuckland
Period18/11/2718/11/30

Fingerprint

Cameras
Infrared radiation
Face recognition
Feature extraction
Luminance
Classifiers
Lighting

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture
  • Media Technology

Cite this

Ki, M., Cho, B., Jeon, T., Choi, Y., & Byun, H. (2019). Face Identification for an in-vehicle Surveillance System Using Near Infrared Camera. In Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance [8639472] (Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AVSS.2018.8639472
Ki, Minsong ; Cho, Bora ; Jeon, Taejun ; Choi, Yeongwoo ; Byun, Hyeran. / Face Identification for an in-vehicle Surveillance System Using Near Infrared Camera. Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance. Institute of Electrical and Electronics Engineers Inc., 2019. (Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance).
@inproceedings{1337135a374f4a398f41df00c239e413,
title = "Face Identification for an in-vehicle Surveillance System Using Near Infrared Camera",
abstract = "Face identification is an essential topic in surveillance system research. Surveillance systems have many unconstrained conditions, e.g., brightness, occlusion, and user state variations. In this paper, we propose a multi-SVM based face recognition method using a near-infrared camera. Our method has a face identification scenario optimized for an in-vehicle surveillance system, which comprises two steps: (i) registering a driver and (ii) recognizing whether the driver is a registered. We perform feature extraction and recognition for each facial landmark. In the case of extreme exposure to light, we convert normal face images into simulated light overexposed images for learning. Thus, face classifiers for normal and extreme illumination conditions are simultaneously generated. We also create a new face dataset and evaluate our method with both our new and PolyU NIR datasets. Experimental results show that we achieve significantly higher recognition accuracy than existing methods.",
author = "Minsong Ki and Bora Cho and Taejun Jeon and Yeongwoo Choi and Hyeran Byun",
year = "2019",
month = "2",
day = "11",
doi = "10.1109/AVSS.2018.8639472",
language = "English",
series = "Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance",
address = "United States",

}

Ki, M, Cho, B, Jeon, T, Choi, Y & Byun, H 2019, Face Identification for an in-vehicle Surveillance System Using Near Infrared Camera. in Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance., 8639472, Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance, Institute of Electrical and Electronics Engineers Inc., 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2018, Auckland, New Zealand, 18/11/27. https://doi.org/10.1109/AVSS.2018.8639472

Face Identification for an in-vehicle Surveillance System Using Near Infrared Camera. / Ki, Minsong; Cho, Bora; Jeon, Taejun; Choi, Yeongwoo; Byun, Hyeran.

Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance. Institute of Electrical and Electronics Engineers Inc., 2019. 8639472 (Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Face Identification for an in-vehicle Surveillance System Using Near Infrared Camera

AU - Ki, Minsong

AU - Cho, Bora

AU - Jeon, Taejun

AU - Choi, Yeongwoo

AU - Byun, Hyeran

PY - 2019/2/11

Y1 - 2019/2/11

N2 - Face identification is an essential topic in surveillance system research. Surveillance systems have many unconstrained conditions, e.g., brightness, occlusion, and user state variations. In this paper, we propose a multi-SVM based face recognition method using a near-infrared camera. Our method has a face identification scenario optimized for an in-vehicle surveillance system, which comprises two steps: (i) registering a driver and (ii) recognizing whether the driver is a registered. We perform feature extraction and recognition for each facial landmark. In the case of extreme exposure to light, we convert normal face images into simulated light overexposed images for learning. Thus, face classifiers for normal and extreme illumination conditions are simultaneously generated. We also create a new face dataset and evaluate our method with both our new and PolyU NIR datasets. Experimental results show that we achieve significantly higher recognition accuracy than existing methods.

AB - Face identification is an essential topic in surveillance system research. Surveillance systems have many unconstrained conditions, e.g., brightness, occlusion, and user state variations. In this paper, we propose a multi-SVM based face recognition method using a near-infrared camera. Our method has a face identification scenario optimized for an in-vehicle surveillance system, which comprises two steps: (i) registering a driver and (ii) recognizing whether the driver is a registered. We perform feature extraction and recognition for each facial landmark. In the case of extreme exposure to light, we convert normal face images into simulated light overexposed images for learning. Thus, face classifiers for normal and extreme illumination conditions are simultaneously generated. We also create a new face dataset and evaluate our method with both our new and PolyU NIR datasets. Experimental results show that we achieve significantly higher recognition accuracy than existing methods.

UR - http://www.scopus.com/inward/record.url?scp=85063295542&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063295542&partnerID=8YFLogxK

U2 - 10.1109/AVSS.2018.8639472

DO - 10.1109/AVSS.2018.8639472

M3 - Conference contribution

T3 - Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance

BT - Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Ki M, Cho B, Jeon T, Choi Y, Byun H. Face Identification for an in-vehicle Surveillance System Using Near Infrared Camera. In Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance. Institute of Electrical and Electronics Engineers Inc. 2019. 8639472. (Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance). https://doi.org/10.1109/AVSS.2018.8639472