Face and texture analysis using local descriptors

A comparative analysis

A. Hadid, J. Ylioinas, Miguel Bordallo Lopez

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

7 Citations (Scopus)

Abstract

In contrast to global image descriptors which compute features directly from the entire image, local descriptors representing the features in small local image patches have proved to be more effective in real world conditions. This paper considers three recent yet popular local descriptors, namely Local Binary Patterns (LBP), Local Phase Quantization (LPQ) and Binarized Statistical Image Features (BSIF), and provides extensive comparative analysis on two different research problems (gender and texture classification) using benchmark datasets. The three descriptors are analyzed in terms of both classification accuracy and computational costs. Furthermore, experiments on combining these descriptors are provided, pointing out useful insight into their complementarity.
Original languageEnglish
Title of host publication4th International Conference on Image Processing Theory, Tools and Applications, IPTA 2014
PublisherInstitute of Electrical and Electronic Engineers IEEE
Number of pages4
ISBN (Electronic)978-1-4799-6463-5
ISBN (Print)978-1-4799-6462-8
DOIs
Publication statusPublished - 2014
MoE publication typeA4 Article in a conference publication
EventIEEE International conference in image processing tools and applications - France, Orleans, France
Duration: 15 Oct 2014 → …

Conference

ConferenceIEEE International conference in image processing tools and applications
CountryFrance
CityOrleans
Period15/10/14 → …

Fingerprint

Textures
Costs
Experiments

Keywords

  • Local descriptors
  • texture analysis
  • gender classification

Cite this

Hadid, A., Ylioinas, J., & Bordallo Lopez, M. (2014). Face and texture analysis using local descriptors: A comparative analysis. In 4th International Conference on Image Processing Theory, Tools and Applications, IPTA 2014 Institute of Electrical and Electronic Engineers IEEE. https://doi.org/10.1109/IPTA.2014.7001944
Hadid, A. ; Ylioinas, J. ; Bordallo Lopez, Miguel. / Face and texture analysis using local descriptors : A comparative analysis. 4th International Conference on Image Processing Theory, Tools and Applications, IPTA 2014. Institute of Electrical and Electronic Engineers IEEE, 2014.
@inproceedings{7ce3cd40d99e449290cdfe38ce7e4e2c,
title = "Face and texture analysis using local descriptors: A comparative analysis",
abstract = "In contrast to global image descriptors which compute features directly from the entire image, local descriptors representing the features in small local image patches have proved to be more effective in real world conditions. This paper considers three recent yet popular local descriptors, namely Local Binary Patterns (LBP), Local Phase Quantization (LPQ) and Binarized Statistical Image Features (BSIF), and provides extensive comparative analysis on two different research problems (gender and texture classification) using benchmark datasets. The three descriptors are analyzed in terms of both classification accuracy and computational costs. Furthermore, experiments on combining these descriptors are provided, pointing out useful insight into their complementarity.",
keywords = "Local descriptors, texture analysis, gender classification",
author = "A. Hadid and J. Ylioinas and {Bordallo Lopez}, Miguel",
year = "2014",
doi = "10.1109/IPTA.2014.7001944",
language = "English",
isbn = "978-1-4799-6462-8",
booktitle = "4th International Conference on Image Processing Theory, Tools and Applications, IPTA 2014",
publisher = "Institute of Electrical and Electronic Engineers IEEE",
address = "United States",

}

Hadid, A, Ylioinas, J & Bordallo Lopez, M 2014, Face and texture analysis using local descriptors: A comparative analysis. in 4th International Conference on Image Processing Theory, Tools and Applications, IPTA 2014. Institute of Electrical and Electronic Engineers IEEE, IEEE International conference in image processing tools and applications , Orleans, France, 15/10/14. https://doi.org/10.1109/IPTA.2014.7001944

Face and texture analysis using local descriptors : A comparative analysis. / Hadid, A.; Ylioinas, J.; Bordallo Lopez, Miguel.

4th International Conference on Image Processing Theory, Tools and Applications, IPTA 2014. Institute of Electrical and Electronic Engineers IEEE, 2014.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Face and texture analysis using local descriptors

T2 - A comparative analysis

AU - Hadid, A.

AU - Ylioinas, J.

AU - Bordallo Lopez, Miguel

PY - 2014

Y1 - 2014

N2 - In contrast to global image descriptors which compute features directly from the entire image, local descriptors representing the features in small local image patches have proved to be more effective in real world conditions. This paper considers three recent yet popular local descriptors, namely Local Binary Patterns (LBP), Local Phase Quantization (LPQ) and Binarized Statistical Image Features (BSIF), and provides extensive comparative analysis on two different research problems (gender and texture classification) using benchmark datasets. The three descriptors are analyzed in terms of both classification accuracy and computational costs. Furthermore, experiments on combining these descriptors are provided, pointing out useful insight into their complementarity.

AB - In contrast to global image descriptors which compute features directly from the entire image, local descriptors representing the features in small local image patches have proved to be more effective in real world conditions. This paper considers three recent yet popular local descriptors, namely Local Binary Patterns (LBP), Local Phase Quantization (LPQ) and Binarized Statistical Image Features (BSIF), and provides extensive comparative analysis on two different research problems (gender and texture classification) using benchmark datasets. The three descriptors are analyzed in terms of both classification accuracy and computational costs. Furthermore, experiments on combining these descriptors are provided, pointing out useful insight into their complementarity.

KW - Local descriptors

KW - texture analysis

KW - gender classification

U2 - 10.1109/IPTA.2014.7001944

DO - 10.1109/IPTA.2014.7001944

M3 - Conference article in proceedings

SN - 978-1-4799-6462-8

BT - 4th International Conference on Image Processing Theory, Tools and Applications, IPTA 2014

PB - Institute of Electrical and Electronic Engineers IEEE

ER -

Hadid A, Ylioinas J, Bordallo Lopez M. Face and texture analysis using local descriptors: A comparative analysis. In 4th International Conference on Image Processing Theory, Tools and Applications, IPTA 2014. Institute of Electrical and Electronic Engineers IEEE. 2014 https://doi.org/10.1109/IPTA.2014.7001944