2D face recognition

Massimo Tistarelli; Manuele Bicego; José L. Alba-Castro; Daniel Gonzàlez-Jiménez; Mohamed Anouar Mellakh; Albert Ali Salah; Dijana Petrovska-Delacrétaz; Bernadette Dorizzi

doi:10.1007/978-1-84800-292-0_8

2D face recognition

Massimo Tistarelli
, Manuele Bicego
, José L. Alba-Castro
, Daniel Gonzàlez-Jiménez
, Mohamed Anouar Mellakh
, Albert Ali Salah
, Dijana Petrovska-Delacrétaz
, Bernadette Dorizzi

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

Abstract

An overview of selected topics in face recognition is first presented in this chapter. The BioSecure 2D-face Benchmarking Framework is also described, composed of open-source software, publicly available databases and protocols. Three methods for 2D-face recognition, exploiting multiscale analysis, are presented. The first method exploits anisotropic smoothing, combined Gabor features and Linear Discriminant Analysis (LDA). The second approach is based on subject-specific face verification via Shape-Driven Gabor Jets (SDGJ), while the third combines Scale Invariant Feature Transform (SIFT) descriptors with graph matching. Comparative results are reported within the benchmarking framework on the BANCA database (with Mc and P protocols). Experimental results on the FRGCv2 database are also reported. The results show the improvements achieved with the presented multiscale analysis methods in order to cope with mismatched enrollment and test conditions.

Original language	English
Title of host publication	Guide to Biometric Reference Systems and Performance Evaluation
Publisher	Springer London
Pages	213-262
Number of pages	50
ISBN (Print)	9781848002913
DOIs	https://doi.org/10.1007/978-1-84800-292-0_8
Publication status	Published - 1 Dec 2009

Access to Document

10.1007/978-1-84800-292-0_8

Cite this

@inbook{e3400e1d2040465884c20a89ed927fba,

title = "2D face recognition",

abstract = "An overview of selected topics in face recognition is first presented in this chapter. The BioSecure 2D-face Benchmarking Framework is also described, composed of open-source software, publicly available databases and protocols. Three methods for 2D-face recognition, exploiting multiscale analysis, are presented. The first method exploits anisotropic smoothing, combined Gabor features and Linear Discriminant Analysis (LDA). The second approach is based on subject-specific face verification via Shape-Driven Gabor Jets (SDGJ), while the third combines Scale Invariant Feature Transform (SIFT) descriptors with graph matching. Comparative results are reported within the benchmarking framework on the BANCA database (with Mc and P protocols). Experimental results on the FRGCv2 database are also reported. The results show the improvements achieved with the presented multiscale analysis methods in order to cope with mismatched enrollment and test conditions.",

author = "Massimo Tistarelli and Manuele Bicego and Alba-Castro, \{Jos{\'e} L.\} and Daniel Gonz{\`a}lez-Jim{\'e}nez and Mellakh, \{Mohamed Anouar\} and \{Ali Salah\}, Albert and Dijana Petrovska-Delacr{\'e}taz and Bernadette Dorizzi",

year = "2009",

month = dec,

day = "1",

doi = "10.1007/978-1-84800-292-0\_8",

language = "English",

isbn = "9781848002913",

pages = "213--262",

booktitle = "Guide to Biometric Reference Systems and Performance Evaluation",

publisher = "Springer London",

}

TY - CHAP

T1 - 2D face recognition

AU - Tistarelli, Massimo

AU - Bicego, Manuele

AU - Alba-Castro, José L.

AU - Gonzàlez-Jiménez, Daniel

AU - Mellakh, Mohamed Anouar

AU - Ali Salah, Albert

AU - Petrovska-Delacrétaz, Dijana

AU - Dorizzi, Bernadette

PY - 2009/12/1

Y1 - 2009/12/1

N2 - An overview of selected topics in face recognition is first presented in this chapter. The BioSecure 2D-face Benchmarking Framework is also described, composed of open-source software, publicly available databases and protocols. Three methods for 2D-face recognition, exploiting multiscale analysis, are presented. The first method exploits anisotropic smoothing, combined Gabor features and Linear Discriminant Analysis (LDA). The second approach is based on subject-specific face verification via Shape-Driven Gabor Jets (SDGJ), while the third combines Scale Invariant Feature Transform (SIFT) descriptors with graph matching. Comparative results are reported within the benchmarking framework on the BANCA database (with Mc and P protocols). Experimental results on the FRGCv2 database are also reported. The results show the improvements achieved with the presented multiscale analysis methods in order to cope with mismatched enrollment and test conditions.

AB - An overview of selected topics in face recognition is first presented in this chapter. The BioSecure 2D-face Benchmarking Framework is also described, composed of open-source software, publicly available databases and protocols. Three methods for 2D-face recognition, exploiting multiscale analysis, are presented. The first method exploits anisotropic smoothing, combined Gabor features and Linear Discriminant Analysis (LDA). The second approach is based on subject-specific face verification via Shape-Driven Gabor Jets (SDGJ), while the third combines Scale Invariant Feature Transform (SIFT) descriptors with graph matching. Comparative results are reported within the benchmarking framework on the BANCA database (with Mc and P protocols). Experimental results on the FRGCv2 database are also reported. The results show the improvements achieved with the presented multiscale analysis methods in order to cope with mismatched enrollment and test conditions.

U2 - 10.1007/978-1-84800-292-0_8

DO - 10.1007/978-1-84800-292-0_8

M3 - Chapter

AN - SCOPUS:84889976975

SN - 9781848002913

SP - 213

EP - 262

BT - Guide to Biometric Reference Systems and Performance Evaluation

PB - Springer London

ER -

2D face recognition

Abstract

Access to Document

Fingerprint

Cite this