A comparative study of baseline algorithms of face recognition

Zahid Mehmood; Tauseef Ali; Shahid Khattak; Samee U. Khan

doi:10.1109/FIT.2014.56

A comparative study of baseline algorithms of face recognition

Zahid Mehmood, Tauseef Ali, Shahid Khattak, Samee U. Khan

Faculty of Electrical Engineering, Mathematics and Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

13 Citations (Scopus)

270 Downloads (Pure)

Abstract

In this paper we present a comparative study of two well-known face recognition algorithms. The contribution of this work is to reveal the robustness of each FR algorithm with respect to various factors, such as variation in pose and low resolution of the images used for recognition. This evaluation is useful for practical applications where the types of the expected images are known. The two FR algorithms studied in this work are Principal Component Analysis (PCA) and AdaBoost with Linear Discriminant Analysis (LDA) as a weak learner. Images from multi-pie database are used for evaluation. Simulation results revealed that given one gallery (Training) face image and four different pose images as a probe (Testing), PCA based system is more accurate in recognizing pose, while AdaBoost was more robust on recognizing low resolution images.

Original language	English
Title of host publication	12th International Conference on Frontiers of Information Technology, FIT 2014
Place of Publication	Piscataway, NJ
Publisher	IEEE
Pages	263-268
Number of pages	6
ISBN (Electronic)	978-1-4799-7505-1
ISBN (Print)	978-1-4799-7504-4
DOIs	https://doi.org/10.1109/FIT.2014.56
Publication status	Published - Dec 2014
Event	12th International Conference on Frontiers of Information Technology, FIT 2014 - Islamabad, Pakistan Duration: 17 Dec 2014 → 19 Dec 2014

Conference

Conference	12th International Conference on Frontiers of Information Technology, FIT 2014
Period	17/12/14 → 19/12/14
Other	17-19 December 2014

Keywords

SCS-Safety
METIS-312728
IR-97324
EWI-26323

Access to Document

10.1109/FIT.2014.56

Cite this

@inproceedings{9fa74c149dac4cefbd32577aadef4e5a,

title = "A comparative study of baseline algorithms of face recognition",

abstract = "In this paper we present a comparative study of two well-known face recognition algorithms. The contribution of this work is to reveal the robustness of each FR algorithm with respect to various factors, such as variation in pose and low resolution of the images used for recognition. This evaluation is useful for practical applications where the types of the expected images are known. The two FR algorithms studied in this work are Principal Component Analysis (PCA) and AdaBoost with Linear Discriminant Analysis (LDA) as a weak learner. Images from multi-pie database are used for evaluation. Simulation results revealed that given one gallery (Training) face image and four different pose images as a probe (Testing), PCA based system is more accurate in recognizing pose, while AdaBoost was more robust on recognizing low resolution images.",

keywords = "SCS-Safety, METIS-312728, IR-97324, EWI-26323",

author = "Zahid Mehmood and Tauseef Ali and Shahid Khattak and Khan, {Samee U.}",

year = "2014",

month = dec,

doi = "10.1109/FIT.2014.56",

language = "English",

isbn = "978-1-4799-7504-4",

pages = "263--268",

booktitle = "12th International Conference on Frontiers of Information Technology, FIT 2014",

publisher = "IEEE",

address = "United States",

note = "12th International Conference on Frontiers of Information Technology, FIT 2014 ; Conference date: 17-12-2014 Through 19-12-2014",

}

TY - GEN

T1 - A comparative study of baseline algorithms of face recognition

AU - Mehmood, Zahid

AU - Ali, Tauseef

AU - Khattak, Shahid

AU - Khan, Samee U.

PY - 2014/12

Y1 - 2014/12

N2 - In this paper we present a comparative study of two well-known face recognition algorithms. The contribution of this work is to reveal the robustness of each FR algorithm with respect to various factors, such as variation in pose and low resolution of the images used for recognition. This evaluation is useful for practical applications where the types of the expected images are known. The two FR algorithms studied in this work are Principal Component Analysis (PCA) and AdaBoost with Linear Discriminant Analysis (LDA) as a weak learner. Images from multi-pie database are used for evaluation. Simulation results revealed that given one gallery (Training) face image and four different pose images as a probe (Testing), PCA based system is more accurate in recognizing pose, while AdaBoost was more robust on recognizing low resolution images.

AB - In this paper we present a comparative study of two well-known face recognition algorithms. The contribution of this work is to reveal the robustness of each FR algorithm with respect to various factors, such as variation in pose and low resolution of the images used for recognition. This evaluation is useful for practical applications where the types of the expected images are known. The two FR algorithms studied in this work are Principal Component Analysis (PCA) and AdaBoost with Linear Discriminant Analysis (LDA) as a weak learner. Images from multi-pie database are used for evaluation. Simulation results revealed that given one gallery (Training) face image and four different pose images as a probe (Testing), PCA based system is more accurate in recognizing pose, while AdaBoost was more robust on recognizing low resolution images.

KW - SCS-Safety

KW - METIS-312728

KW - IR-97324

KW - EWI-26323

U2 - 10.1109/FIT.2014.56

DO - 10.1109/FIT.2014.56

M3 - Conference contribution

SN - 978-1-4799-7504-4

SP - 263

EP - 268

BT - 12th International Conference on Frontiers of Information Technology, FIT 2014

PB - IEEE

CY - Piscataway, NJ

T2 - 12th International Conference on Frontiers of Information Technology, FIT 2014

Y2 - 17 December 2014 through 19 December 2014

ER -

A comparative study of baseline algorithms of face recognition

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this