Quality labeled faces in the wild (QLFW): A database for studying face recognition in real-world environments

Lina Karam, Tong Zhu

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

7 Citations (Scopus)

Abstract

The varying quality of face images is an important challenge that limits the effectiveness of face recognition technology when applied in real-world applications. Existing face image databases do not consider the effect of distortions that commonly occur in real-world environments. This database (QLFW) represents an initial attempt to provide a set of labeled face images spanning the wide range of quality, from no perceived impairment to strong perceived impairment for face detection and face recognition applications. Types of impairment include JPEG2000 compression, JPEG compression, additive white noise, Gaussian blur and contrast change. Subjective experiments are conducted to assess the perceived visual quality of faces under different levels and types of distortions and also to assess the human recognition performance under the considered distortions. One goal of this work is to enable automated performance evaluation of face recognition technologies in the presence of different types and levels of visual distortions. This will consequently enable the development of face recognition systems that can operate reliably on real-world visual content in the presence of real-world visual distortions. Another goal is to enable the development and assessment of visual quality metrics for face images and for face detection and recognition applications.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
PublisherSPIE
Volume9394
ISBN (Print)9781628414844
DOIs
StatePublished - 2015
EventHuman Vision and Electronic Imaging XX - San Francisco, United States
Duration: Feb 9 2015Feb 12 2015

Other

OtherHuman Vision and Electronic Imaging XX
CountryUnited States
CitySan Francisco
Period2/9/152/12/15

Fingerprint

Face recognition
Face Recognition
Face
impairment
Face Detection
Compression
JPEG2000
Image Database
Gaussian White Noise
Real-world Applications
white noise
White noise
Performance Evaluation
Vision
Metric
evaluation
Range of data
Experiment
Experiments

Keywords

  • Database
  • Face recognition
  • Visual quality

ASJC Scopus subject areas

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

Cite this

Karam, L., & Zhu, T. (2015). Quality labeled faces in the wild (QLFW): A database for studying face recognition in real-world environments. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 9394). [93940B] SPIE. https://doi.org/10.1117/12.2080393

Quality labeled faces in the wild (QLFW) : A database for studying face recognition in real-world environments. / Karam, Lina; Zhu, Tong.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 9394 SPIE, 2015. 93940B.

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

Karam, L & Zhu, T 2015, Quality labeled faces in the wild (QLFW): A database for studying face recognition in real-world environments. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 9394, 93940B, SPIE, Human Vision and Electronic Imaging XX, San Francisco, United States, 2/9/15. https://doi.org/10.1117/12.2080393
Karam L, Zhu T. Quality labeled faces in the wild (QLFW): A database for studying face recognition in real-world environments. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 9394. SPIE. 2015. 93940B https://doi.org/10.1117/12.2080393
Karam, Lina ; Zhu, Tong. / Quality labeled faces in the wild (QLFW) : A database for studying face recognition in real-world environments. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 9394 SPIE, 2015.
@inproceedings{e1d55c81d4084a6cb340e8ccc28f220c,
title = "Quality labeled faces in the wild (QLFW): A database for studying face recognition in real-world environments",
abstract = "The varying quality of face images is an important challenge that limits the effectiveness of face recognition technology when applied in real-world applications. Existing face image databases do not consider the effect of distortions that commonly occur in real-world environments. This database (QLFW) represents an initial attempt to provide a set of labeled face images spanning the wide range of quality, from no perceived impairment to strong perceived impairment for face detection and face recognition applications. Types of impairment include JPEG2000 compression, JPEG compression, additive white noise, Gaussian blur and contrast change. Subjective experiments are conducted to assess the perceived visual quality of faces under different levels and types of distortions and also to assess the human recognition performance under the considered distortions. One goal of this work is to enable automated performance evaluation of face recognition technologies in the presence of different types and levels of visual distortions. This will consequently enable the development of face recognition systems that can operate reliably on real-world visual content in the presence of real-world visual distortions. Another goal is to enable the development and assessment of visual quality metrics for face images and for face detection and recognition applications.",
keywords = "Database, Face recognition, Visual quality",
author = "Lina Karam and Tong Zhu",
year = "2015",
doi = "10.1117/12.2080393",
language = "English (US)",
isbn = "9781628414844",
volume = "9394",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",

}

TY - GEN

T1 - Quality labeled faces in the wild (QLFW)

T2 - A database for studying face recognition in real-world environments

AU - Karam, Lina

AU - Zhu, Tong

PY - 2015

Y1 - 2015

N2 - The varying quality of face images is an important challenge that limits the effectiveness of face recognition technology when applied in real-world applications. Existing face image databases do not consider the effect of distortions that commonly occur in real-world environments. This database (QLFW) represents an initial attempt to provide a set of labeled face images spanning the wide range of quality, from no perceived impairment to strong perceived impairment for face detection and face recognition applications. Types of impairment include JPEG2000 compression, JPEG compression, additive white noise, Gaussian blur and contrast change. Subjective experiments are conducted to assess the perceived visual quality of faces under different levels and types of distortions and also to assess the human recognition performance under the considered distortions. One goal of this work is to enable automated performance evaluation of face recognition technologies in the presence of different types and levels of visual distortions. This will consequently enable the development of face recognition systems that can operate reliably on real-world visual content in the presence of real-world visual distortions. Another goal is to enable the development and assessment of visual quality metrics for face images and for face detection and recognition applications.

AB - The varying quality of face images is an important challenge that limits the effectiveness of face recognition technology when applied in real-world applications. Existing face image databases do not consider the effect of distortions that commonly occur in real-world environments. This database (QLFW) represents an initial attempt to provide a set of labeled face images spanning the wide range of quality, from no perceived impairment to strong perceived impairment for face detection and face recognition applications. Types of impairment include JPEG2000 compression, JPEG compression, additive white noise, Gaussian blur and contrast change. Subjective experiments are conducted to assess the perceived visual quality of faces under different levels and types of distortions and also to assess the human recognition performance under the considered distortions. One goal of this work is to enable automated performance evaluation of face recognition technologies in the presence of different types and levels of visual distortions. This will consequently enable the development of face recognition systems that can operate reliably on real-world visual content in the presence of real-world visual distortions. Another goal is to enable the development and assessment of visual quality metrics for face images and for face detection and recognition applications.

KW - Database

KW - Face recognition

KW - Visual quality

UR - http://www.scopus.com/inward/record.url?scp=84928494406&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84928494406&partnerID=8YFLogxK

U2 - 10.1117/12.2080393

DO - 10.1117/12.2080393

M3 - Conference contribution

AN - SCOPUS:84928494406

SN - 9781628414844

VL - 9394

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

PB - SPIE

ER -