Accurate eye localization in low and standard definition content

Bart Kroon, Sabri Boughorbel, Alan Hanjalic

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

2 Citations (Scopus)

Abstract

In this paper we address the problem of eye localization in low and standard definition content, such as webcam- generated and TV images. We present a probabilistic eye localization method based on well-known multiscale local binary patterns (LBPs), which provide a simple and pow- erful spatial description of texture, and are robust to the noise typical to low and standard definition content. Our primary contribution is in the proposed method of combin- ing the LBPs that is targeted towards achieving spatial ac- curacy under mentioned conditions. Evaluation performed on a standard dataset of webcam-quality images shows that our approach has superior performance with respect to the state of the art, while having a reasonable complexity and a low memory footprint.

Original languageEnglish
Title of host publication2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008
DOIs
Publication statusPublished - 2008
Externally publishedYes
Event2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008 - Amsterdam, Netherlands
Duration: 17 Sep 200819 Sep 2008

Other

Other2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008
CountryNetherlands
CityAmsterdam
Period17/9/0819/9/08

Fingerprint

Image quality
Textures
Data storage equipment

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction
  • Electrical and Electronic Engineering

Cite this

Kroon, B., Boughorbel, S., & Hanjalic, A. (2008). Accurate eye localization in low and standard definition content. In 2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008 [4813382] https://doi.org/10.1109/AFGR.2008.4813382

Accurate eye localization in low and standard definition content. / Kroon, Bart; Boughorbel, Sabri; Hanjalic, Alan.

2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008. 2008. 4813382.

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

Kroon, B, Boughorbel, S & Hanjalic, A 2008, Accurate eye localization in low and standard definition content. in 2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008., 4813382, 2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008, Amsterdam, Netherlands, 17/9/08. https://doi.org/10.1109/AFGR.2008.4813382
Kroon B, Boughorbel S, Hanjalic A. Accurate eye localization in low and standard definition content. In 2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008. 2008. 4813382 https://doi.org/10.1109/AFGR.2008.4813382
Kroon, Bart ; Boughorbel, Sabri ; Hanjalic, Alan. / Accurate eye localization in low and standard definition content. 2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008. 2008.
@inproceedings{5a7f0fc01d764d2f8a6d5fcc4bcb52fd,
title = "Accurate eye localization in low and standard definition content",
abstract = "In this paper we address the problem of eye localization in low and standard definition content, such as webcam- generated and TV images. We present a probabilistic eye localization method based on well-known multiscale local binary patterns (LBPs), which provide a simple and pow- erful spatial description of texture, and are robust to the noise typical to low and standard definition content. Our primary contribution is in the proposed method of combin- ing the LBPs that is targeted towards achieving spatial ac- curacy under mentioned conditions. Evaluation performed on a standard dataset of webcam-quality images shows that our approach has superior performance with respect to the state of the art, while having a reasonable complexity and a low memory footprint.",
author = "Bart Kroon and Sabri Boughorbel and Alan Hanjalic",
year = "2008",
doi = "10.1109/AFGR.2008.4813382",
language = "English",
isbn = "9781424421541",
booktitle = "2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008",

}

TY - GEN

T1 - Accurate eye localization in low and standard definition content

AU - Kroon, Bart

AU - Boughorbel, Sabri

AU - Hanjalic, Alan

PY - 2008

Y1 - 2008

N2 - In this paper we address the problem of eye localization in low and standard definition content, such as webcam- generated and TV images. We present a probabilistic eye localization method based on well-known multiscale local binary patterns (LBPs), which provide a simple and pow- erful spatial description of texture, and are robust to the noise typical to low and standard definition content. Our primary contribution is in the proposed method of combin- ing the LBPs that is targeted towards achieving spatial ac- curacy under mentioned conditions. Evaluation performed on a standard dataset of webcam-quality images shows that our approach has superior performance with respect to the state of the art, while having a reasonable complexity and a low memory footprint.

AB - In this paper we address the problem of eye localization in low and standard definition content, such as webcam- generated and TV images. We present a probabilistic eye localization method based on well-known multiscale local binary patterns (LBPs), which provide a simple and pow- erful spatial description of texture, and are robust to the noise typical to low and standard definition content. Our primary contribution is in the proposed method of combin- ing the LBPs that is targeted towards achieving spatial ac- curacy under mentioned conditions. Evaluation performed on a standard dataset of webcam-quality images shows that our approach has superior performance with respect to the state of the art, while having a reasonable complexity and a low memory footprint.

UR - http://www.scopus.com/inward/record.url?scp=67650694294&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67650694294&partnerID=8YFLogxK

U2 - 10.1109/AFGR.2008.4813382

DO - 10.1109/AFGR.2008.4813382

M3 - Conference contribution

AN - SCOPUS:67650694294

SN - 9781424421541

BT - 2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008

ER -