3D face analysis for distinct features using statistical randomization

Chunxiao Zhou, Yuxiao Hu, Yun Fu, Huixia Wang, Thomas S Huang, Michelle Yongmei Wang

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

Abstract

It is a fascinating yet challenging problem to accurately and efficiently localize regionally distinct features between face groups in multi-dimensional signal processing and analysis. Given a data with unknown distribution and small sample size, we propose a new statistical analysis framework using hybrid randomization (i.e., permutation) tests to improve the system's efficiency in identifying distinct features. The proposed method fits the nonparametric distribution of the test statistic with Pearson distribution series. We bypass the tedious online randomization via calculating the first four moments of the permutation distribution. This can reduce the computational complexity from O(n!) to O(n2) over traditional methods for the modified Hotelling's T2 test statistics. Experiments on simulated data and 3D face analysis demonstrate the efficiency, accuracy and robustness of the proposed approach.

Original languageEnglish (US)
Title of host publication2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP
Pages981-984
Number of pages4
DOIs
StatePublished - Sep 16 2008
Event2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP - Las Vegas, NV, United States
Duration: Mar 31 2008Apr 4 2008

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)1520-6149

Other

Other2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP
CountryUnited States
CityLas Vegas, NV
Period3/31/084/4/08

Fingerprint

permutations
Statistics
Pearson distributions
Signal analysis
statistics
Computational complexity
Statistical methods
Signal processing
signal analysis
bypasses
statistical analysis
signal processing
moments
Experiments

Keywords

  • 3D face analysis
  • Feature selection
  • Randomization test

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Signal Processing
  • Acoustics and Ultrasonics

Cite this

Zhou, C., Hu, Y., Fu, Y., Wang, H., Huang, T. S., & Wang, M. Y. (2008). 3D face analysis for distinct features using statistical randomization. In 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP (pp. 981-984). [4517776] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2008.4517776

3D face analysis for distinct features using statistical randomization. / Zhou, Chunxiao; Hu, Yuxiao; Fu, Yun; Wang, Huixia; Huang, Thomas S; Wang, Michelle Yongmei.

2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP. 2008. p. 981-984 4517776 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

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

Zhou, C, Hu, Y, Fu, Y, Wang, H, Huang, TS & Wang, MY 2008, 3D face analysis for distinct features using statistical randomization. in 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP., 4517776, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pp. 981-984, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, Las Vegas, NV, United States, 3/31/08. https://doi.org/10.1109/ICASSP.2008.4517776
Zhou C, Hu Y, Fu Y, Wang H, Huang TS, Wang MY. 3D face analysis for distinct features using statistical randomization. In 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP. 2008. p. 981-984. 4517776. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2008.4517776
Zhou, Chunxiao ; Hu, Yuxiao ; Fu, Yun ; Wang, Huixia ; Huang, Thomas S ; Wang, Michelle Yongmei. / 3D face analysis for distinct features using statistical randomization. 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP. 2008. pp. 981-984 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).
@inproceedings{35ce52db6eda48d886ac083b9e3ef82e,
title = "3D face analysis for distinct features using statistical randomization",
abstract = "It is a fascinating yet challenging problem to accurately and efficiently localize regionally distinct features between face groups in multi-dimensional signal processing and analysis. Given a data with unknown distribution and small sample size, we propose a new statistical analysis framework using hybrid randomization (i.e., permutation) tests to improve the system's efficiency in identifying distinct features. The proposed method fits the nonparametric distribution of the test statistic with Pearson distribution series. We bypass the tedious online randomization via calculating the first four moments of the permutation distribution. This can reduce the computational complexity from O(n!) to O(n2) over traditional methods for the modified Hotelling's T2 test statistics. Experiments on simulated data and 3D face analysis demonstrate the efficiency, accuracy and robustness of the proposed approach.",
keywords = "3D face analysis, Feature selection, Randomization test",
author = "Chunxiao Zhou and Yuxiao Hu and Yun Fu and Huixia Wang and Huang, {Thomas S} and Wang, {Michelle Yongmei}",
year = "2008",
month = "9",
day = "16",
doi = "10.1109/ICASSP.2008.4517776",
language = "English (US)",
isbn = "1424414849",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
pages = "981--984",
booktitle = "2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP",

}

TY - GEN

T1 - 3D face analysis for distinct features using statistical randomization

AU - Zhou, Chunxiao

AU - Hu, Yuxiao

AU - Fu, Yun

AU - Wang, Huixia

AU - Huang, Thomas S

AU - Wang, Michelle Yongmei

PY - 2008/9/16

Y1 - 2008/9/16

N2 - It is a fascinating yet challenging problem to accurately and efficiently localize regionally distinct features between face groups in multi-dimensional signal processing and analysis. Given a data with unknown distribution and small sample size, we propose a new statistical analysis framework using hybrid randomization (i.e., permutation) tests to improve the system's efficiency in identifying distinct features. The proposed method fits the nonparametric distribution of the test statistic with Pearson distribution series. We bypass the tedious online randomization via calculating the first four moments of the permutation distribution. This can reduce the computational complexity from O(n!) to O(n2) over traditional methods for the modified Hotelling's T2 test statistics. Experiments on simulated data and 3D face analysis demonstrate the efficiency, accuracy and robustness of the proposed approach.

AB - It is a fascinating yet challenging problem to accurately and efficiently localize regionally distinct features between face groups in multi-dimensional signal processing and analysis. Given a data with unknown distribution and small sample size, we propose a new statistical analysis framework using hybrid randomization (i.e., permutation) tests to improve the system's efficiency in identifying distinct features. The proposed method fits the nonparametric distribution of the test statistic with Pearson distribution series. We bypass the tedious online randomization via calculating the first four moments of the permutation distribution. This can reduce the computational complexity from O(n!) to O(n2) over traditional methods for the modified Hotelling's T2 test statistics. Experiments on simulated data and 3D face analysis demonstrate the efficiency, accuracy and robustness of the proposed approach.

KW - 3D face analysis

KW - Feature selection

KW - Randomization test

UR - http://www.scopus.com/inward/record.url?scp=51449103582&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51449103582&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2008.4517776

DO - 10.1109/ICASSP.2008.4517776

M3 - Conference contribution

AN - SCOPUS:51449103582

SN - 1424414849

SN - 9781424414840

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 981

EP - 984

BT - 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP

ER -