Fusion of facial regions using color information in a forensic scenario

Tomé González, Pedro; Vera-Rodríguez, Rubén; Fiérrez, Julián; Ortega-García, Javier

Biblos-e Archivo
→
Investigación
→
Facultades y Escuela Politécnica Superior
→
Escuela Politécnica Superior
→
Departamento de Tecnología Electrónica y de las Comunicaciones
→
EPTEC - Comunicaciones en congresos
→
View Item

Fusion of facial regions using color information in a forensic scenario

Metadatos

Title: Fusion of facial regions using color information in a forensic scenario

Author: Tomé González, Pedro; Vera-Rodríguez, Rubén; Fiérrez, Julián; Ortega-García, Javier

Entity: UAM. Departamento de Tecnología Electrónica y de las Comunicaciones

UAM Author: Fierrez Aguilar, Julián

; Tome González, Pedro

Publisher: Springer Berlin Heidelberg

Date: 2013-12-01

Citation: 18th Iberoamerican Congress on Pattern Recognition, CIARP 2013; Havana; Cuba; 20 - 23 November 2013. Lecture Notes in Computer Science, Volume 8259. Springer, 2013. 399-406

ISSN: 0302-9743 (print); 1611-3349 (online)

ISBN: 978-3-642-41826-6 (print); 978-3-642-41827-3 (online)

DOI: 10.1007/978-3-642-41827-3_50

Funded by: This work has been partially supported by contract with Spanish Guardia Civil and projects BBfor2 (FP7-ITN-238803), bio-Challenge (TEC2009-11186), Bio Shield (TEC2012-34881), Contexts (S2009/TIC-1485), TeraSense (CSD2008-00068) and "Cátedra UAM-Telefónica"

Project: info:eu-repo/grantAgreement/EC/FP7/238803; Comunidad de Madrid. S2009/TIC-1485/CONTEXTS

Editor's Version: http://dx.doi.org/10.1007/978-3-642-41827-3_50

Subjects: At a distance; Color information; Face recognition; Facial components; Facial regions; Forensics; Video surveillance; Informática

URI: http://hdl.handle.net/10486/662719

Note: Comunicación presentada en: 18th Iberoamerican Congress on Pattern Recognition, CIARP 2013; Havana; Cuba; 20-23 November 2013
The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-642-41827-3_50

Rights: © Springer-Verlag 2013

Abstract:

This paper reports an analysis of the benefits of using color information on a region-based face recognition system. Three different color spaces are analysed (RGB, YCbCr, lαβ) in a very challenging scenario matching good quality mugshot images against video surveillance images. This scenario is of special interest for forensics, where examiners carry out a comparison of two face images using the global information of the faces, but paying special attention to each individual facial region (eyes, nose, mouth, etc.). This work analyses the discriminative power of 15 facial regions comparing both the grayscale and color information. Results show a significant improvement of performance when fusing several regions of the face compared to just using the whole face image. A further improvement of performance is achieved when color information is considered

Show full item record