Finding and Improving the Key-Frames of Long Video Sequences for Face Recognition

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

11 Citations (Scopus)

Abstract

Face recognition systems are very sensitive to the quality and resolution of their input face images. This makes such systems unreliable when working with long surveillance video sequences without employing some selection and enhancement algorithms. On the other hand, processing all the frames of such video sequences by any enhancement or even face recognition algorithm is demanding. Thus, there is a need for a mechanism to summarize the input video sequence to a set of key-frames and then applying an enhancement algorithm to this subset. This paper presents a system doing exactly this. The system uses face quality assessment to select the key-frames and a hybrid super-resolution to enhance the face image quality. The suggested system that employs a linear associator face recognizer to evaluate the enhanced results has been tested on real surveillance video sequences and the experimental results show promising results.
Original languageEnglish
Title of host publicationIEEE 4th International Conference on Biometrics Theory, Applications and Systems (BTAS), Washington DC, USA
Number of pages6
Place of PublicationWashington, DC, USA
PublisherIEEE Press
Publication date27 Sep 2010
ISBN (Print)978-1-4244-7581-0
ISBN (Electronic)978-1-4244-7580-3
DOIs
Publication statusPublished - 27 Sep 2010
Event IEEE 4th International Conference on Biometrics Theory, Applications and Systems (BTAS) - Washington DC, United States
Duration: 27 Sep 201029 Sep 2010

Conference

Conference IEEE 4th International Conference on Biometrics Theory, Applications and Systems (BTAS)
CountryUnited States
CityWashington DC
Period27/09/201029/09/2010

Fingerprint

Face recognition
Set theory
Image quality
Processing

Cite this

Nasrollahi, K., & Moeslund, T. B. (2010). Finding and Improving the Key-Frames of Long Video Sequences for Face Recognition. In IEEE 4th International Conference on Biometrics Theory, Applications and Systems (BTAS), Washington DC, USA Washington, DC, USA : IEEE Press. https://doi.org/10.1109/BTAS.2010.5634491
Nasrollahi, Kamal ; Moeslund, Thomas B. / Finding and Improving the Key-Frames of Long Video Sequences for Face Recognition. IEEE 4th International Conference on Biometrics Theory, Applications and Systems (BTAS), Washington DC, USA. Washington, DC, USA : IEEE Press, 2010.
@inproceedings{fec4960a908b4bcf9e624e3e33c822a1,
title = "Finding and Improving the Key-Frames of Long Video Sequences for Face Recognition",
abstract = "Face recognition systems are very sensitive to the quality and resolution of their input face images. This makes such systems unreliable when working with long surveillance video sequences without employing some selection and enhancement algorithms. On the other hand, processing all the frames of such video sequences by any enhancement or even face recognition algorithm is demanding. Thus, there is a need for a mechanism to summarize the input video sequence to a set of key-frames and then applying an enhancement algorithm to this subset. This paper presents a system doing exactly this. The system uses face quality assessment to select the key-frames and a hybrid super-resolution to enhance the face image quality. The suggested system that employs a linear associator face recognizer to evaluate the enhanced results has been tested on real surveillance video sequences and the experimental results show promising results.",
author = "Kamal Nasrollahi and Moeslund, {Thomas B.}",
year = "2010",
month = "9",
day = "27",
doi = "10.1109/BTAS.2010.5634491",
language = "English",
isbn = "978-1-4244-7581-0",
booktitle = "IEEE 4th International Conference on Biometrics Theory, Applications and Systems (BTAS), Washington DC, USA",
publisher = "IEEE Press",

}

Nasrollahi, K & Moeslund, TB 2010, Finding and Improving the Key-Frames of Long Video Sequences for Face Recognition. in IEEE 4th International Conference on Biometrics Theory, Applications and Systems (BTAS), Washington DC, USA. IEEE Press, Washington, DC, USA , IEEE 4th International Conference on Biometrics Theory, Applications and Systems (BTAS), Washington DC, United States, 27/09/2010. https://doi.org/10.1109/BTAS.2010.5634491

Finding and Improving the Key-Frames of Long Video Sequences for Face Recognition. / Nasrollahi, Kamal; Moeslund, Thomas B.

IEEE 4th International Conference on Biometrics Theory, Applications and Systems (BTAS), Washington DC, USA. Washington, DC, USA : IEEE Press, 2010.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Finding and Improving the Key-Frames of Long Video Sequences for Face Recognition

AU - Nasrollahi, Kamal

AU - Moeslund, Thomas B.

PY - 2010/9/27

Y1 - 2010/9/27

N2 - Face recognition systems are very sensitive to the quality and resolution of their input face images. This makes such systems unreliable when working with long surveillance video sequences without employing some selection and enhancement algorithms. On the other hand, processing all the frames of such video sequences by any enhancement or even face recognition algorithm is demanding. Thus, there is a need for a mechanism to summarize the input video sequence to a set of key-frames and then applying an enhancement algorithm to this subset. This paper presents a system doing exactly this. The system uses face quality assessment to select the key-frames and a hybrid super-resolution to enhance the face image quality. The suggested system that employs a linear associator face recognizer to evaluate the enhanced results has been tested on real surveillance video sequences and the experimental results show promising results.

AB - Face recognition systems are very sensitive to the quality and resolution of their input face images. This makes such systems unreliable when working with long surveillance video sequences without employing some selection and enhancement algorithms. On the other hand, processing all the frames of such video sequences by any enhancement or even face recognition algorithm is demanding. Thus, there is a need for a mechanism to summarize the input video sequence to a set of key-frames and then applying an enhancement algorithm to this subset. This paper presents a system doing exactly this. The system uses face quality assessment to select the key-frames and a hybrid super-resolution to enhance the face image quality. The suggested system that employs a linear associator face recognizer to evaluate the enhanced results has been tested on real surveillance video sequences and the experimental results show promising results.

U2 - 10.1109/BTAS.2010.5634491

DO - 10.1109/BTAS.2010.5634491

M3 - Article in proceeding

SN - 978-1-4244-7581-0

BT - IEEE 4th International Conference on Biometrics Theory, Applications and Systems (BTAS), Washington DC, USA

PB - IEEE Press

CY - Washington, DC, USA

ER -

Nasrollahi K, Moeslund TB. Finding and Improving the Key-Frames of Long Video Sequences for Face Recognition. In IEEE 4th International Conference on Biometrics Theory, Applications and Systems (BTAS), Washington DC, USA. Washington, DC, USA : IEEE Press. 2010 https://doi.org/10.1109/BTAS.2010.5634491