An adaptive resolution voxelization framework for 3D ear recognition

Steven Cadavid, Sherin Fathy, Jindan Zhou, Mohamed Abdel-Mottaleb

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

We present a novel voxelization framework for holistic Three-Dimensional (3D) object representation that accounts for distinct surface features. A voxelization of an object is performed by encoding an attribute or set of attributes of the surface region contained within each voxel occupying the space that the object resides in. To our knowledge, the voxel structures employed in previous methods consist of uniformly-sized voxels. The proposed framework, in contrast, generates structures consisting of variable-sized voxels that are adaptively distributed in higher concentration near distinct surface features. The primary advantage of the proposed method over its fixed resolution counterparts is that it yields a significantly more concise feature representation that is demonstrated to achieve a superior recognition performance. An evaluation of the method is conducted on a 3D ear recognition task. The ear provides a challenging case study because of its high degree of inter-subject similarity.

Original languageEnglish
Title of host publication2011 International Joint Conference on Biometrics, IJCB 2011
DOIs
StatePublished - Dec 1 2011
Event2011 International Joint Conference on Biometrics, IJCB 2011 - Washington, DC, United States
Duration: Oct 11 2011Oct 13 2011

Other

Other2011 International Joint Conference on Biometrics, IJCB 2011
CountryUnited States
CityWashington, DC
Period10/11/1110/13/11

Fingerprint

Ear

ASJC Scopus subject areas

  • Biotechnology

Cite this

Cadavid, S., Fathy, S., Zhou, J., & Abdel-Mottaleb, M. (2011). An adaptive resolution voxelization framework for 3D ear recognition. In 2011 International Joint Conference on Biometrics, IJCB 2011 [6117598] https://doi.org/10.1109/IJCB.2011.6117598

An adaptive resolution voxelization framework for 3D ear recognition. / Cadavid, Steven; Fathy, Sherin; Zhou, Jindan; Abdel-Mottaleb, Mohamed.

2011 International Joint Conference on Biometrics, IJCB 2011. 2011. 6117598.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Cadavid, S, Fathy, S, Zhou, J & Abdel-Mottaleb, M 2011, An adaptive resolution voxelization framework for 3D ear recognition. in 2011 International Joint Conference on Biometrics, IJCB 2011., 6117598, 2011 International Joint Conference on Biometrics, IJCB 2011, Washington, DC, United States, 10/11/11. https://doi.org/10.1109/IJCB.2011.6117598
Cadavid S, Fathy S, Zhou J, Abdel-Mottaleb M. An adaptive resolution voxelization framework for 3D ear recognition. In 2011 International Joint Conference on Biometrics, IJCB 2011. 2011. 6117598 https://doi.org/10.1109/IJCB.2011.6117598
Cadavid, Steven ; Fathy, Sherin ; Zhou, Jindan ; Abdel-Mottaleb, Mohamed. / An adaptive resolution voxelization framework for 3D ear recognition. 2011 International Joint Conference on Biometrics, IJCB 2011. 2011.
@inproceedings{36ceb88090334172ab55f916aeb453ab,
title = "An adaptive resolution voxelization framework for 3D ear recognition",
abstract = "We present a novel voxelization framework for holistic Three-Dimensional (3D) object representation that accounts for distinct surface features. A voxelization of an object is performed by encoding an attribute or set of attributes of the surface region contained within each voxel occupying the space that the object resides in. To our knowledge, the voxel structures employed in previous methods consist of uniformly-sized voxels. The proposed framework, in contrast, generates structures consisting of variable-sized voxels that are adaptively distributed in higher concentration near distinct surface features. The primary advantage of the proposed method over its fixed resolution counterparts is that it yields a significantly more concise feature representation that is demonstrated to achieve a superior recognition performance. An evaluation of the method is conducted on a 3D ear recognition task. The ear provides a challenging case study because of its high degree of inter-subject similarity.",
author = "Steven Cadavid and Sherin Fathy and Jindan Zhou and Mohamed Abdel-Mottaleb",
year = "2011",
month = "12",
day = "1",
doi = "10.1109/IJCB.2011.6117598",
language = "English",
isbn = "9781457713583",
booktitle = "2011 International Joint Conference on Biometrics, IJCB 2011",

}

TY - GEN

T1 - An adaptive resolution voxelization framework for 3D ear recognition

AU - Cadavid, Steven

AU - Fathy, Sherin

AU - Zhou, Jindan

AU - Abdel-Mottaleb, Mohamed

PY - 2011/12/1

Y1 - 2011/12/1

N2 - We present a novel voxelization framework for holistic Three-Dimensional (3D) object representation that accounts for distinct surface features. A voxelization of an object is performed by encoding an attribute or set of attributes of the surface region contained within each voxel occupying the space that the object resides in. To our knowledge, the voxel structures employed in previous methods consist of uniformly-sized voxels. The proposed framework, in contrast, generates structures consisting of variable-sized voxels that are adaptively distributed in higher concentration near distinct surface features. The primary advantage of the proposed method over its fixed resolution counterparts is that it yields a significantly more concise feature representation that is demonstrated to achieve a superior recognition performance. An evaluation of the method is conducted on a 3D ear recognition task. The ear provides a challenging case study because of its high degree of inter-subject similarity.

AB - We present a novel voxelization framework for holistic Three-Dimensional (3D) object representation that accounts for distinct surface features. A voxelization of an object is performed by encoding an attribute or set of attributes of the surface region contained within each voxel occupying the space that the object resides in. To our knowledge, the voxel structures employed in previous methods consist of uniformly-sized voxels. The proposed framework, in contrast, generates structures consisting of variable-sized voxels that are adaptively distributed in higher concentration near distinct surface features. The primary advantage of the proposed method over its fixed resolution counterparts is that it yields a significantly more concise feature representation that is demonstrated to achieve a superior recognition performance. An evaluation of the method is conducted on a 3D ear recognition task. The ear provides a challenging case study because of its high degree of inter-subject similarity.

UR - http://www.scopus.com/inward/record.url?scp=84862914488&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862914488&partnerID=8YFLogxK

U2 - 10.1109/IJCB.2011.6117598

DO - 10.1109/IJCB.2011.6117598

M3 - Conference contribution

SN - 9781457713583

BT - 2011 International Joint Conference on Biometrics, IJCB 2011

ER -