FacePerf: Benchmarks for face recognition algorithms

David S. Bolme; Michelle Strout; J. Ross Beveridge

doi:10.1109/IISWC.2007.4362187

FacePerf: Benchmarks for face recognition algorithms

David S. Bolme, Michelle Strout, J. Ross Beveridge

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

6 Scopus citations

Abstract

In this paper we present a collection of C and C++ biometric performance benchmark algorithms called FacePerf. The benchmark includes three different face recognition algorithms that are historically important to the face recognition community: Haar-based face detection, Principal Components Analysis, and Elastic Bunch Graph Matching. The algorithms are fast enough to be useful in realtime systems; however, improving performance would allow the algorithms to process more images or search larger face databases. Bottlenecks for each phase in the algorithms have been identified. A cosine approximation was able to reduce the execution time of the Elastic Bunch Graph Matching implementation by 32%.

Original language	English (US)
Title of host publication	Proceedings of the 2007 IEEE International Symposium on Workload Characterization, IISWC
Pages	114-119
Number of pages	6
DOIs	https://doi.org/10.1109/IISWC.2007.4362187
State	Published - 2007
Externally published	Yes
Event	2007 IEEE International Symposium on Workload Characterization, IISWC - Boston, MA, United States Duration: Sep 27 2007 → Sep 29 2007

Publication series

Name	Proceedings of the 2007 IEEE International Symposium on Workload Characterization, IISWC

Conference

Conference	2007 IEEE International Symposium on Workload Characterization, IISWC
Country/Territory	United States
City	Boston, MA
Period	9/27/07 → 9/29/07

ASJC Scopus subject areas

Computer Science Applications
Hardware and Architecture
Electrical and Electronic Engineering

Access to Document

10.1109/IISWC.2007.4362187

Cite this

FacePerf: Benchmarks for face recognition algorithms. / Bolme, David S.; Strout, Michelle; Beveridge, J. Ross.
Proceedings of the 2007 IEEE International Symposium on Workload Characterization, IISWC. 2007. p. 114-119 4362187 (Proceedings of the 2007 IEEE International Symposium on Workload Characterization, IISWC).

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

Bolme, DS, Strout, M & Beveridge, JR 2007, FacePerf: Benchmarks for face recognition algorithms. in Proceedings of the 2007 IEEE International Symposium on Workload Characterization, IISWC., 4362187, Proceedings of the 2007 IEEE International Symposium on Workload Characterization, IISWC, pp. 114-119, 2007 IEEE International Symposium on Workload Characterization, IISWC, Boston, MA, United States, 9/27/07. https://doi.org/10.1109/IISWC.2007.4362187

@inproceedings{d841d2c62b034647b6b66ae8dd97f049,

title = "FacePerf: Benchmarks for face recognition algorithms",

abstract = "In this paper we present a collection of C and C++ biometric performance benchmark algorithms called FacePerf. The benchmark includes three different face recognition algorithms that are historically important to the face recognition community: Haar-based face detection, Principal Components Analysis, and Elastic Bunch Graph Matching. The algorithms are fast enough to be useful in realtime systems; however, improving performance would allow the algorithms to process more images or search larger face databases. Bottlenecks for each phase in the algorithms have been identified. A cosine approximation was able to reduce the execution time of the Elastic Bunch Graph Matching implementation by 32%.",

author = "Bolme, {David S.} and Michelle Strout and Beveridge, {J. Ross}",

year = "2007",

doi = "10.1109/IISWC.2007.4362187",

language = "English (US)",

isbn = "1424415616",

series = "Proceedings of the 2007 IEEE International Symposium on Workload Characterization, IISWC",

pages = "114--119",

booktitle = "Proceedings of the 2007 IEEE International Symposium on Workload Characterization, IISWC",

note = "2007 IEEE International Symposium on Workload Characterization, IISWC ; Conference date: 27-09-2007 Through 29-09-2007",

}

TY - GEN

T1 - FacePerf

T2 - 2007 IEEE International Symposium on Workload Characterization, IISWC

AU - Bolme, David S.

AU - Strout, Michelle

AU - Beveridge, J. Ross

PY - 2007

Y1 - 2007

N2 - In this paper we present a collection of C and C++ biometric performance benchmark algorithms called FacePerf. The benchmark includes three different face recognition algorithms that are historically important to the face recognition community: Haar-based face detection, Principal Components Analysis, and Elastic Bunch Graph Matching. The algorithms are fast enough to be useful in realtime systems; however, improving performance would allow the algorithms to process more images or search larger face databases. Bottlenecks for each phase in the algorithms have been identified. A cosine approximation was able to reduce the execution time of the Elastic Bunch Graph Matching implementation by 32%.

AB - In this paper we present a collection of C and C++ biometric performance benchmark algorithms called FacePerf. The benchmark includes three different face recognition algorithms that are historically important to the face recognition community: Haar-based face detection, Principal Components Analysis, and Elastic Bunch Graph Matching. The algorithms are fast enough to be useful in realtime systems; however, improving performance would allow the algorithms to process more images or search larger face databases. Bottlenecks for each phase in the algorithms have been identified. A cosine approximation was able to reduce the execution time of the Elastic Bunch Graph Matching implementation by 32%.

UR - http://www.scopus.com/inward/record.url?scp=47349119875&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=47349119875&partnerID=8YFLogxK

U2 - 10.1109/IISWC.2007.4362187

DO - 10.1109/IISWC.2007.4362187

M3 - Conference contribution

AN - SCOPUS:47349119875

SN - 1424415616

SN - 9781424415618

T3 - Proceedings of the 2007 IEEE International Symposium on Workload Characterization, IISWC

SP - 114

EP - 119

BT - Proceedings of the 2007 IEEE International Symposium on Workload Characterization, IISWC

Y2 - 27 September 2007 through 29 September 2007

ER -

FacePerf: Benchmarks for face recognition algorithms

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this