Likelihood Ratio Based Mixed Resolution Facial Comparison

Y. Peng; Lieuwe Jan Spreeuwers; Raymond N.J. Veldhuis

doi:10.1109/IWBF.2015.7110231

Likelihood Ratio Based Mixed Resolution Facial Comparison

Y. Peng, Lieuwe Jan Spreeuwers, Raymond N.J. Veldhuis

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

6 Citations (Scopus)

46 Downloads (Pure)

Abstract

In this paper, we propose a novel method for low-resolution face recognition. It is especially useful for a common situation in forensic search where faces of low resolution, e.g. on surveillance footage or in a crowd, must be compared to a high-resolution reference. This method is based on the likelihood ratio of a pair of mixed-resolution input images. The effectiveness of our method is tested on the SCface database which contains face images taken by surveillance cameras. The results show that our method outperforms recently published state-of-the-art.

Original language	Undefined
Title of host publication	Proceedings of the 3rd International Workshop on Biometrics and Forensics, IWBF 2015
Place of Publication	USA
Publisher	IEEE Computer Society
Pages	1-5
Number of pages	5
ISBN (Print)	978-1-4799-8105-2
DOIs	https://doi.org/10.1109/IWBF.2015.7110231
Publication status	Published - 3 Mar 2015

Publication series

Name
Publisher	IEEE Computer Society

Keywords

EWI-26033
SCS-Safety
mixed resolution
METIS-312620
Face Recognition
SCface
Low Resolution
IR-95949

Access to Document

10.1109/IWBF.2015.7110231

Peng15_LIKELIHOOD_RATIO_BASED_MIXED_RESOLUTION_FACIAL_COMPARISON
open

Cite this

Peng, Y., Spreeuwers, L. J., & Veldhuis, R. N. J. (2015). Likelihood Ratio Based Mixed Resolution Facial Comparison. In Proceedings of the 3rd International Workshop on Biometrics and Forensics, IWBF 2015 (pp. 1-5). USA: IEEE Computer Society. https://doi.org/10.1109/IWBF.2015.7110231

@inproceedings{cce49ed0fb874e878677a5f165314eb2,

title = "Likelihood Ratio Based Mixed Resolution Facial Comparison",

abstract = "In this paper, we propose a novel method for low-resolution face recognition. It is especially useful for a common situation in forensic search where faces of low resolution, e.g. on surveillance footage or in a crowd, must be compared to a high-resolution reference. This method is based on the likelihood ratio of a pair of mixed-resolution input images. The effectiveness of our method is tested on the SCface database which contains face images taken by surveillance cameras. The results show that our method outperforms recently published state-of-the-art.",

keywords = "EWI-26033, SCS-Safety, mixed resolution, METIS-312620, Face Recognition, SCface, Low Resolution, IR-95949",

author = "Y. Peng and Spreeuwers, {Lieuwe Jan} and Veldhuis, {Raymond N.J.}",

note = "10.1109/IWBF.2015.7110231",

year = "2015",

month = "3",

day = "3",

doi = "10.1109/IWBF.2015.7110231",

language = "Undefined",

isbn = "978-1-4799-8105-2",

publisher = "IEEE Computer Society",

pages = "1--5",

booktitle = "Proceedings of the 3rd International Workshop on Biometrics and Forensics, IWBF 2015",

address = "United States",

}

TY - GEN

T1 - Likelihood Ratio Based Mixed Resolution Facial Comparison

AU - Peng, Y.

AU - Spreeuwers, Lieuwe Jan

AU - Veldhuis, Raymond N.J.

N1 - 10.1109/IWBF.2015.7110231

PY - 2015/3/3

Y1 - 2015/3/3

N2 - In this paper, we propose a novel method for low-resolution face recognition. It is especially useful for a common situation in forensic search where faces of low resolution, e.g. on surveillance footage or in a crowd, must be compared to a high-resolution reference. This method is based on the likelihood ratio of a pair of mixed-resolution input images. The effectiveness of our method is tested on the SCface database which contains face images taken by surveillance cameras. The results show that our method outperforms recently published state-of-the-art.

AB - In this paper, we propose a novel method for low-resolution face recognition. It is especially useful for a common situation in forensic search where faces of low resolution, e.g. on surveillance footage or in a crowd, must be compared to a high-resolution reference. This method is based on the likelihood ratio of a pair of mixed-resolution input images. The effectiveness of our method is tested on the SCface database which contains face images taken by surveillance cameras. The results show that our method outperforms recently published state-of-the-art.

KW - EWI-26033

KW - SCS-Safety

KW - mixed resolution

KW - METIS-312620

KW - Face Recognition

KW - SCface

KW - Low Resolution

KW - IR-95949

U2 - 10.1109/IWBF.2015.7110231

DO - 10.1109/IWBF.2015.7110231

M3 - Conference contribution

SN - 978-1-4799-8105-2

SP - 1

EP - 5

BT - Proceedings of the 3rd International Workshop on Biometrics and Forensics, IWBF 2015

PB - IEEE Computer Society

CY - USA

ER -