A methodology for evaluating robustness of face recognition algorithms with respect to variations in pose angle and illumination angle

Greg Little, Sreekar Krishna, John Black, Sethuraman Panchanathan

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

86 Citations (Scopus)

Abstract

In this paper, we present a methodology for precisely comparing the robustness of face recognition algorithms with respect to changes in pose angle and illumination angle. For this study, we have chosen four widely-used algorithms: two subspace analysis methods (Principle Component Analysis (PCA) and Linear Discriminant Analysis (LDA)) and two probabilistic learning methods (Hidden Markov Models (HMM) and Bayesian Intra-personal Classifier (BIC)). We compare the recognition robustness of these algorithms using a novel database (FacePix) that captures face images with a wide range of pose angles and illumination angles. We propose a method for deriving a robustness measure for each of these algorithms, with respect to pose and illumination angle changes. The results of this comparison indicate that the subspace methods perform more robustly than the probabilistic learning methods in the presence of pose and illumination angle changes.

Original languageEnglish (US)
Title of host publication2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05 - Proceedings - Image and Multidimensional Signal Processing Multimedia Signal Processing
VolumeII
DOIs
StatePublished - 2005
Event2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05 - Philadelphia, PA, United States
Duration: Mar 18 2005Mar 23 2005

Other

Other2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05
CountryUnited States
CityPhiladelphia, PA
Period3/18/053/23/05

Fingerprint

Face recognition
Lighting
illumination
methodology
learning
Discriminant analysis
Hidden Markov models
Classifiers
classifiers

ASJC Scopus subject areas

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

Cite this

Little, G., Krishna, S., Black, J., & Panchanathan, S. (2005). A methodology for evaluating robustness of face recognition algorithms with respect to variations in pose angle and illumination angle. In 2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05 - Proceedings - Image and Multidimensional Signal Processing Multimedia Signal Processing (Vol. II). [1415348] https://doi.org/10.1109/ICASSP.2005.1415348

A methodology for evaluating robustness of face recognition algorithms with respect to variations in pose angle and illumination angle. / Little, Greg; Krishna, Sreekar; Black, John; Panchanathan, Sethuraman.

2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05 - Proceedings - Image and Multidimensional Signal Processing Multimedia Signal Processing. Vol. II 2005. 1415348.

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

Little, G, Krishna, S, Black, J & Panchanathan, S 2005, A methodology for evaluating robustness of face recognition algorithms with respect to variations in pose angle and illumination angle. in 2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05 - Proceedings - Image and Multidimensional Signal Processing Multimedia Signal Processing. vol. II, 1415348, 2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05, Philadelphia, PA, United States, 3/18/05. https://doi.org/10.1109/ICASSP.2005.1415348
Little G, Krishna S, Black J, Panchanathan S. A methodology for evaluating robustness of face recognition algorithms with respect to variations in pose angle and illumination angle. In 2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05 - Proceedings - Image and Multidimensional Signal Processing Multimedia Signal Processing. Vol. II. 2005. 1415348 https://doi.org/10.1109/ICASSP.2005.1415348
Little, Greg ; Krishna, Sreekar ; Black, John ; Panchanathan, Sethuraman. / A methodology for evaluating robustness of face recognition algorithms with respect to variations in pose angle and illumination angle. 2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05 - Proceedings - Image and Multidimensional Signal Processing Multimedia Signal Processing. Vol. II 2005.
@inproceedings{40d7d07c98f04fd18a28f0614452b0eb,
title = "A methodology for evaluating robustness of face recognition algorithms with respect to variations in pose angle and illumination angle",
abstract = "In this paper, we present a methodology for precisely comparing the robustness of face recognition algorithms with respect to changes in pose angle and illumination angle. For this study, we have chosen four widely-used algorithms: two subspace analysis methods (Principle Component Analysis (PCA) and Linear Discriminant Analysis (LDA)) and two probabilistic learning methods (Hidden Markov Models (HMM) and Bayesian Intra-personal Classifier (BIC)). We compare the recognition robustness of these algorithms using a novel database (FacePix) that captures face images with a wide range of pose angles and illumination angles. We propose a method for deriving a robustness measure for each of these algorithms, with respect to pose and illumination angle changes. The results of this comparison indicate that the subspace methods perform more robustly than the probabilistic learning methods in the presence of pose and illumination angle changes.",
author = "Greg Little and Sreekar Krishna and John Black and Sethuraman Panchanathan",
year = "2005",
doi = "10.1109/ICASSP.2005.1415348",
language = "English (US)",
isbn = "0780388747",
volume = "II",
booktitle = "2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05 - Proceedings - Image and Multidimensional Signal Processing Multimedia Signal Processing",

}

TY - GEN

T1 - A methodology for evaluating robustness of face recognition algorithms with respect to variations in pose angle and illumination angle

AU - Little, Greg

AU - Krishna, Sreekar

AU - Black, John

AU - Panchanathan, Sethuraman

PY - 2005

Y1 - 2005

N2 - In this paper, we present a methodology for precisely comparing the robustness of face recognition algorithms with respect to changes in pose angle and illumination angle. For this study, we have chosen four widely-used algorithms: two subspace analysis methods (Principle Component Analysis (PCA) and Linear Discriminant Analysis (LDA)) and two probabilistic learning methods (Hidden Markov Models (HMM) and Bayesian Intra-personal Classifier (BIC)). We compare the recognition robustness of these algorithms using a novel database (FacePix) that captures face images with a wide range of pose angles and illumination angles. We propose a method for deriving a robustness measure for each of these algorithms, with respect to pose and illumination angle changes. The results of this comparison indicate that the subspace methods perform more robustly than the probabilistic learning methods in the presence of pose and illumination angle changes.

AB - In this paper, we present a methodology for precisely comparing the robustness of face recognition algorithms with respect to changes in pose angle and illumination angle. For this study, we have chosen four widely-used algorithms: two subspace analysis methods (Principle Component Analysis (PCA) and Linear Discriminant Analysis (LDA)) and two probabilistic learning methods (Hidden Markov Models (HMM) and Bayesian Intra-personal Classifier (BIC)). We compare the recognition robustness of these algorithms using a novel database (FacePix) that captures face images with a wide range of pose angles and illumination angles. We propose a method for deriving a robustness measure for each of these algorithms, with respect to pose and illumination angle changes. The results of this comparison indicate that the subspace methods perform more robustly than the probabilistic learning methods in the presence of pose and illumination angle changes.

UR - http://www.scopus.com/inward/record.url?scp=33646801648&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33646801648&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2005.1415348

DO - 10.1109/ICASSP.2005.1415348

M3 - Conference contribution

AN - SCOPUS:33646801648

SN - 0780388747

SN - 9780780388741

VL - II

BT - 2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05 - Proceedings - Image and Multidimensional Signal Processing Multimedia Signal Processing

ER -