Method for real-time face region tracking based on color histogram

Tae Woong Yoo; Il Seok Oh

Method for real-time face region tracking based on color histogram

Tae Woong Yoo^*
, Il Seok Oh

^*Corresponding author for this work

Jeonbuk National University

Research output: Contribution to conference › Conference paper › peer-review

1 Scopus citations

Abstract

This paper describes a fast algorithm that tracks face region in dynamic images. We adopt the color histogram backprojection algorithm of swain-Ballar in order to find face region in subsequent frames. The algorithm has the advantages of being invariant to object rotation, small deformation, and noise. The following problems are addressed: building a model histogram, backprojecting model histogram, searching the peak response location, and updating the model histogram. The experimentation shows the possibility of realtime face tracking on PC or low-performance workstation.

Original language	English
Title of host publication	Proceedings of SPIE - The International Society for Optical Engineering
Editors	Michael K. Masten, Larry A. Stockum
Pages	361-365
Number of pages	5
State	Published - 1996
Event	Acquisition, Tracking, and Pointing X - Orlando, FL, USA Duration: 1996.04.10 → 1996.04.11

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	2739

Conference

Conference	Acquisition, Tracking, and Pointing X
City	Orlando, FL, USA
Period	96.04.10 → 96.04.11

Quacquarelli Symonds(QS) Subject Topics

Materials Science
Computer Science & Information Systems
Mathematics
Engineering - Electrical & Electronic
Engineering - Petroleum
Data Science
Physics & Astronomy

Cite this

@inproceedings{1fc1bc4235dd426c83fa6506d15ab02c,

title = "Method for real-time face region tracking based on color histogram",

abstract = "This paper describes a fast algorithm that tracks face region in dynamic images. We adopt the color histogram backprojection algorithm of swain-Ballar in order to find face region in subsequent frames. The algorithm has the advantages of being invariant to object rotation, small deformation, and noise. The following problems are addressed: building a model histogram, backprojecting model histogram, searching the peak response location, and updating the model histogram. The experimentation shows the possibility of realtime face tracking on PC or low-performance workstation.",

author = "Yoo, \{Tae Woong\} and Oh, \{Il Seok\}",

year = "1996",

language = "English",

isbn = "0819421200",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

pages = "361--365",

editor = "Masten, \{Michael K.\} and Stockum, \{Larry A.\}",

booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

note = "Acquisition, Tracking, and Pointing X ; Conference date: 10-04-1996 Through 11-04-1996",

}

Method for real-time face region tracking based on color histogram. / Yoo, Tae Woong; Oh, Il Seok.
Proceedings of SPIE - The International Society for Optical Engineering. ed. / Michael K. Masten; Larry A. Stockum. 1996. p. 361-365 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 2739).

Research output: Contribution to conference › Conference paper › peer-review

TY - GEN

T1 - Method for real-time face region tracking based on color histogram

AU - Yoo, Tae Woong

AU - Oh, Il Seok

PY - 1996

Y1 - 1996

N2 - This paper describes a fast algorithm that tracks face region in dynamic images. We adopt the color histogram backprojection algorithm of swain-Ballar in order to find face region in subsequent frames. The algorithm has the advantages of being invariant to object rotation, small deformation, and noise. The following problems are addressed: building a model histogram, backprojecting model histogram, searching the peak response location, and updating the model histogram. The experimentation shows the possibility of realtime face tracking on PC or low-performance workstation.

AB - This paper describes a fast algorithm that tracks face region in dynamic images. We adopt the color histogram backprojection algorithm of swain-Ballar in order to find face region in subsequent frames. The algorithm has the advantages of being invariant to object rotation, small deformation, and noise. The following problems are addressed: building a model histogram, backprojecting model histogram, searching the peak response location, and updating the model histogram. The experimentation shows the possibility of realtime face tracking on PC or low-performance workstation.

UR - https://www.scopus.com/pages/publications/0029727410

M3 - Conference paper

AN - SCOPUS:0029727410

SN - 0819421200

SN - 9780819421203

T3 - Proceedings of SPIE - The International Society for Optical Engineering

SP - 361

EP - 365

BT - Proceedings of SPIE - The International Society for Optical Engineering

A2 - Masten, Michael K.

A2 - Stockum, Larry A.

T2 - Acquisition, Tracking, and Pointing X

Y2 - 10 April 1996 through 11 April 1996

ER -

Method for real-time face region tracking based on color histogram

Abstract

Publication series

Conference

Quacquarelli Symonds(QS) Subject Topics

Other files and links

Fingerprint

Cite this