3-D face recognition using local appearance-based models

Hazým Kemal Ekenel; Gao Hua; Rainer Stiefelhagen

doi:10.1109/TIFS.2007.902924

3-D face recognition using local appearance-based models

Hazým Kemal Ekenel^*
, Gao Hua
, Rainer Stiefelhagen

^*Bu çalışma için yazışmadan sorumlu yazar

Karlsruhe Institute of Technology

Araştırma sonucu: Dergiye katkı › Makale › bilirkişi

13 Atıf (Scopus)

Özet

In this paper, we present a local appearance-based approach for 3-D face recognition. In the proposed algorithm, we first register the 3-D point clouds to provide a dense correspondence between faces. Afterwards, we analyze two mapping techniques-the closest-point mapping and the ray-casting mapping, to construct depth images from the corresponding well-registered point clouds. The depth images that are obtained are then divided into local regions where the discrete cosine transformation is performed to extract local information. The local features are combined at the feature level for classification. Experimental results on the FRGC version 2.0 face database show that the proposed algorithm performs superior to the well-known face recognition algorithms.

Orijinal dil	İngilizce
Sayfa (başlangıç-bitiş)	630-636
Sayfa sayısı	7
Dergi	IEEE Transactions on Information Forensics and Security
Hacim	2
Basın numarası	3
DOI'lar	https://doi.org/10.1109/TIFS.2007.902924
Yayın durumu	Yayınlandı - Eyl 2007
Harici olarak yayınlandı	Evet

Finansman

Manuscript received May 1, 2007. This work was supported in part by the European Union under the integrated project CHIL, Computers in the Human Interaction Loop under Contract 506909, and in part by the German Research Foundation (DFG) as part of the Collaborative Research Center 588 Humanoid Robots-Learning and Cooperating Multimodal Robots. The associate editor co-ordinating the review of this manuscript and approving it for publication was Prof. Bir Bhanu.

Finansörler	Finansör numarası
Computers in the Human Interaction Loop	506909
European Commission
Deutsche Forschungsgemeinschaft

Belgeye Erişim

10.1109/TIFS.2007.902924

Diğer Dosyalar ve Linkler

Link to publication in Scopus

Alıntı Yap

@article{4fd61139405e46e4896aa6c92328a7f0,

title = "3-D face recognition using local appearance-based models",

abstract = "In this paper, we present a local appearance-based approach for 3-D face recognition. In the proposed algorithm, we first register the 3-D point clouds to provide a dense correspondence between faces. Afterwards, we analyze two mapping techniques-the closest-point mapping and the ray-casting mapping, to construct depth images from the corresponding well-registered point clouds. The depth images that are obtained are then divided into local regions where the discrete cosine transformation is performed to extract local information. The local features are combined at the feature level for classification. Experimental results on the FRGC version 2.0 face database show that the proposed algorithm performs superior to the well-known face recognition algorithms.",

keywords = "3-D face recognition, Automatic registration, Depth image, Local appearance face recognition",

author = "Ekenel, \{Haz{\'y}m Kemal\} and Gao Hua and Rainer Stiefelhagen",

year = "2007",

month = sep,

doi = "10.1109/TIFS.2007.902924",

language = "English",

volume = "2",

pages = "630--636",

journal = "IEEE Transactions on Information Forensics and Security",

issn = "1556-6013",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "3",

}

TY - JOUR

T1 - 3-D face recognition using local appearance-based models

AU - Ekenel, Hazým Kemal

AU - Hua, Gao

AU - Stiefelhagen, Rainer

PY - 2007/9

Y1 - 2007/9

N2 - In this paper, we present a local appearance-based approach for 3-D face recognition. In the proposed algorithm, we first register the 3-D point clouds to provide a dense correspondence between faces. Afterwards, we analyze two mapping techniques-the closest-point mapping and the ray-casting mapping, to construct depth images from the corresponding well-registered point clouds. The depth images that are obtained are then divided into local regions where the discrete cosine transformation is performed to extract local information. The local features are combined at the feature level for classification. Experimental results on the FRGC version 2.0 face database show that the proposed algorithm performs superior to the well-known face recognition algorithms.

AB - In this paper, we present a local appearance-based approach for 3-D face recognition. In the proposed algorithm, we first register the 3-D point clouds to provide a dense correspondence between faces. Afterwards, we analyze two mapping techniques-the closest-point mapping and the ray-casting mapping, to construct depth images from the corresponding well-registered point clouds. The depth images that are obtained are then divided into local regions where the discrete cosine transformation is performed to extract local information. The local features are combined at the feature level for classification. Experimental results on the FRGC version 2.0 face database show that the proposed algorithm performs superior to the well-known face recognition algorithms.

KW - 3-D face recognition

KW - Automatic registration

KW - Depth image

KW - Local appearance face recognition

UR - https://www.scopus.com/pages/publications/34548058638

U2 - 10.1109/TIFS.2007.902924

DO - 10.1109/TIFS.2007.902924

M3 - Article

AN - SCOPUS:34548058638

SN - 1556-6013

VL - 2

SP - 630

EP - 636

JO - IEEE Transactions on Information Forensics and Security

JF - IEEE Transactions on Information Forensics and Security

IS - 3

ER -

3-D face recognition using local appearance-based models

Özet

Finansman

Belgeye Erişim

Diğer Dosyalar ve Linkler

Parmak izi

Alıntı Yap