3D Face Recognition: Feature Extraction Based on Directional Signatures from Range Data and Disparity Maps

Soodamani Ramalingam

doi:10.1109/SMC.2013.750

3D Face Recognition: Feature Extraction Based on Directional Signatures from Range Data and Disparity Maps

Soodamani Ramalingam

Centre for Engineering Research

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 Downloads (Pure)

Abstract

In this paper, the author presents a work on i) range data and ii) stereo-vision system based disparity map profiling that are used as signatures for 3D face recognition. The signatures capture the intensity variations along a line at sample points on a face in any particular direction. The directional signatures and some of their combinations are compared to study the variability in recognition performances. Two 3D face image datasets namely, a local student database captured with a stereo vision system and the FRGC v1 range dataset are used for performance evaluation.

Original language	English
Title of host publication	2013 IEEE International Conference on Systems, Man, and Cybernetics
Publisher	IEEE
Pages	4397-4402
Number of pages	6
ISBN (Electronic)	9781479906529
DOIs	https://doi.org/10.1109/SMC.2013.750
Publication status	E-pub ahead of print - 27 Jan 2014

Access to Document

10.1109/SMC.2013.750Licence: Other

DrSRamalingam_3D_Face_Recognition_IEESMC_2012
© 2013 IEEE.
Accepted author manuscript, 1 MBLicence: Other

Cite this

@inproceedings{ed93966b4f5a4159835479bec3ab71fc,

title = "3D Face Recognition: Feature Extraction Based on Directional Signatures from Range Data and Disparity Maps",

abstract = "In this paper, the author presents a work on i) range data and ii) stereo-vision system based disparity map profiling that are used as signatures for 3D face recognition. The signatures capture the intensity variations along a line at sample points on a face in any particular direction. The directional signatures and some of their combinations are compared to study the variability in recognition performances. Two 3D face image datasets namely, a local student database captured with a stereo vision system and the FRGC v1 range dataset are used for performance evaluation.",

author = "Soodamani Ramalingam",

year = "2014",

month = jan,

day = "27",

doi = "10.1109/SMC.2013.750",

language = "English",

pages = "4397--4402",

booktitle = "2013 IEEE International Conference on Systems, Man, and Cybernetics",

publisher = "IEEE",

}

TY - GEN

T1 - 3D Face Recognition: Feature Extraction Based on Directional Signatures from Range Data and Disparity Maps

AU - Ramalingam, Soodamani

PY - 2014/1/27

Y1 - 2014/1/27

N2 - In this paper, the author presents a work on i) range data and ii) stereo-vision system based disparity map profiling that are used as signatures for 3D face recognition. The signatures capture the intensity variations along a line at sample points on a face in any particular direction. The directional signatures and some of their combinations are compared to study the variability in recognition performances. Two 3D face image datasets namely, a local student database captured with a stereo vision system and the FRGC v1 range dataset are used for performance evaluation.

AB - In this paper, the author presents a work on i) range data and ii) stereo-vision system based disparity map profiling that are used as signatures for 3D face recognition. The signatures capture the intensity variations along a line at sample points on a face in any particular direction. The directional signatures and some of their combinations are compared to study the variability in recognition performances. Two 3D face image datasets namely, a local student database captured with a stereo vision system and the FRGC v1 range dataset are used for performance evaluation.

U2 - 10.1109/SMC.2013.750

DO - 10.1109/SMC.2013.750

M3 - Conference contribution

SP - 4397

EP - 4402

BT - 2013 IEEE International Conference on Systems, Man, and Cybernetics

PB - IEEE

ER -

3D Face Recognition: Feature Extraction Based on Directional Signatures from Range Data and Disparity Maps

Abstract

Access to Document

Fingerprint

Cite this