Face Image Retrieval Revisited

D 2015

Face Image Retrieval Revisited

SEDMIDUBSKÝ, Jan, Vladimír MÍČ and Pavel ZEZULA

Basic information

Original name

Face Image Retrieval Revisited

Authors

SEDMIDUBSKÝ, Jan (203 Czech Republic, guarantor, belonging to the institution), Vladimír MÍČ (203 Czech Republic, belonging to the institution) and Pavel ZEZULA (203 Czech Republic, belonging to the institution)

Edition

Switzerland, Proceedings of 8th International Conference on Similarity Search and Applications (SISAP 2015), LNCS 9371, p. 204-216, 13 pp. 2015

Publisher

Springer

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

Switzerland

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

printed version "print"

Impact factor

Impact factor: 0.402 in 2005

RIV identification code

RIV/00216224:14330/15:00080525

Organization unit

Faculty of Informatics

ISBN

978-3-319-25086-1

ISSN

DOI

http://dx.doi.org/10.1007/978-3-319-25087-8_19

UT WoS

000374289600019

Keywords in English

face retrieval; face detection; effectiveness; efficiency; face matcher fusion

Abstract

V originále

The objective of face retrieval is to efficiently search an image database with detected faces and identify such faces that belong to the same person as a query face. Unlike most related papers, we concentrate on both retrieval effectiveness and efficiency. High retrieval effectiveness is achieved by proposing a new fusion approach which integrates existing state-of-the-art detection as well as matching methods. We further significantly improve a retrieval quality by employing the concept of multi-face queries along with optional relevance feedback. To be able to efficiently process queries on databases with millions of faces, we apply a specialized indexing algorithm. The proposed solutions are compared against four existing open-source and commercial technologies and experimentally evaluated on the standardized FERET dataset and on a real-life dataset of more than one million face images. The retrieval results demonstrate a significant gain in effectiveness and two-orders of magnitude more efficient query processing, with respect to a single technology executed sequentially.

Links

VG20122015073, research and development project

Name: Efektivní vyhledávání v rozsáhlých biometrických datech (Acronym: EFBIO)

Investor: Ministry of the Interior of the CR

Citovat

SEDMIDUBSKÝ, Jan, Vladimír MÍČ and Pavel ZEZULA. Face Image Retrieval Revisited. In G. Amato et al. Proceedings of 8th International Conference on Similarity Search and Applications (SISAP 2015), LNCS 9371. Switzerland: Springer, 2015, p. 204-216. ISBN 978-3-319-25086-1. Available from: https://dx.doi.org/10.1007/978-3-319-25087-8_19.

@inproceedings{1305715,
   author = {Sedmidubský, Jan and Míč, Vladimír and Zezula, Pavel},
   address = {Switzerland},
   booktitle = {Proceedings of 8th International Conference on Similarity Search and Applications (SISAP 2015), LNCS 9371},
   doi = {http://dx.doi.org/10.1007/978-3-319-25087-8_19},
   editor = {G. Amato et al.},
   keywords = {face retrieval; face detection; effectiveness; efficiency; face matcher fusion},
   howpublished = {tištěná verze "print"},
   language = {eng},
   location = {Switzerland},
   isbn = {978-3-319-25086-1},
   pages = {204-216},
   publisher = {Springer},
   title = {Face Image Retrieval Revisited},
   year = {2015}
}

TY  - JOUR
ID  - 1305715
AU  - Sedmidubský, Jan - Míč, Vladimír - Zezula, Pavel
PY  - 2015
TI  - Face Image Retrieval Revisited
PB  - Springer
CY  - Switzerland
SN  - 9783319250861
KW  - face retrieval
KW  - face detection
KW  - effectiveness
KW  - efficiency
KW  - face matcher fusion
N2  - The objective of face retrieval is to efficiently search an image database with detected faces and identify such faces that belong to the same person as a query face. Unlike most related papers, we concentrate on both retrieval effectiveness and efficiency. High retrieval effectiveness is achieved by proposing a new fusion approach which integrates existing state-of-the-art detection as well as matching methods. We further significantly improve a retrieval quality by employing the concept of multi-face queries along with optional relevance feedback. To be able to efficiently process queries on databases with millions of faces, we apply a specialized indexing algorithm. The proposed solutions are compared against four existing open-source and commercial technologies and experimentally evaluated on the standardized FERET dataset and on a real-life dataset of more than one million face images. The retrieval results demonstrate a significant gain in effectiveness and two-orders of magnitude more efficient query processing, with respect to a single technology executed sequentially.
ER  -

SEDMIDUBSKÝ, Jan, Vladimír MÍČ and Pavel ZEZULA. Face Image Retrieval Revisited. In G. Amato et al. \textit{Proceedings of 8th International Conference on Similarity Search and Applications (SISAP 2015), LNCS 9371}. Switzerland: Springer, 2015, p.~204-216. ISBN~978-3-319-25086-1. Available from: https://dx.doi.org/10.1007/978-3-319-25087-8\_{}19.

Detailed Information on Publication Record