Use of projection histograms for tracking faces under out-of-plane rotation

Hanjin Ryu, Myounghoon Kim, Seungwook Cha, Sanghoon Sull

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

We present an efficient face tracking method that is robust, especially when the face is turned away from the frontal view to the side view (out-of-plane rotation). The proposed method, consisting of three steps, utilizes the horizontal and vertical projection histograms of a face region to model the visual appearance of the face. The vertical and horizontal positions of a face are sequentially determined. First, the horizontal projection histogram of each potential face region in the current frame near the corresponding face region in the previous frame is used as an input to a back-propagation neural network (BPNN) to reliably estimate the vertical position of the face, based on the observation that the distribution of the horizontal projection histogram of a face region is stable, even when the head is rotating about an axis parallel to the vertical axis of an image plane. Second, the vertical projection histogram of an eye region derived from the estimated vertical position of the face as well as output values from the BPNN is used to estimate the horizontal position of the face. Third, the detected face region is refined by head boundary detection. These three steps are repeatedly applied to track faces in each shot of an input video. Experimental results are provided to demonstrate the efficiency of the proposed method.

Original languageEnglish
Article number097205
JournalOptical Engineering
Volume47
Issue number9
DOIs
Publication statusPublished - 2008 Dec 1

Fingerprint

Backpropagation
histograms
projection
Neural networks
edge detection
estimates
shot
output

Keywords

  • Face tracking
  • Projection histogram
  • Template matching

ASJC Scopus subject areas

  • Engineering(all)
  • Atomic and Molecular Physics, and Optics

Cite this

Use of projection histograms for tracking faces under out-of-plane rotation. / Ryu, Hanjin; Kim, Myounghoon; Cha, Seungwook; Sull, Sanghoon.

In: Optical Engineering, Vol. 47, No. 9, 097205, 01.12.2008.

Research output: Contribution to journalArticle

Ryu, Hanjin ; Kim, Myounghoon ; Cha, Seungwook ; Sull, Sanghoon. / Use of projection histograms for tracking faces under out-of-plane rotation. In: Optical Engineering. 2008 ; Vol. 47, No. 9.
@article{f7c6797b5d984735a3540216bb23431b,
title = "Use of projection histograms for tracking faces under out-of-plane rotation",
abstract = "We present an efficient face tracking method that is robust, especially when the face is turned away from the frontal view to the side view (out-of-plane rotation). The proposed method, consisting of three steps, utilizes the horizontal and vertical projection histograms of a face region to model the visual appearance of the face. The vertical and horizontal positions of a face are sequentially determined. First, the horizontal projection histogram of each potential face region in the current frame near the corresponding face region in the previous frame is used as an input to a back-propagation neural network (BPNN) to reliably estimate the vertical position of the face, based on the observation that the distribution of the horizontal projection histogram of a face region is stable, even when the head is rotating about an axis parallel to the vertical axis of an image plane. Second, the vertical projection histogram of an eye region derived from the estimated vertical position of the face as well as output values from the BPNN is used to estimate the horizontal position of the face. Third, the detected face region is refined by head boundary detection. These three steps are repeatedly applied to track faces in each shot of an input video. Experimental results are provided to demonstrate the efficiency of the proposed method.",
keywords = "Face tracking, Projection histogram, Template matching",
author = "Hanjin Ryu and Myounghoon Kim and Seungwook Cha and Sanghoon Sull",
year = "2008",
month = "12",
day = "1",
doi = "10.1117/1.2981563",
language = "English",
volume = "47",
journal = "Optical Engineering",
issn = "0091-3286",
publisher = "SPIE",
number = "9",

}

TY - JOUR

T1 - Use of projection histograms for tracking faces under out-of-plane rotation

AU - Ryu, Hanjin

AU - Kim, Myounghoon

AU - Cha, Seungwook

AU - Sull, Sanghoon

PY - 2008/12/1

Y1 - 2008/12/1

N2 - We present an efficient face tracking method that is robust, especially when the face is turned away from the frontal view to the side view (out-of-plane rotation). The proposed method, consisting of three steps, utilizes the horizontal and vertical projection histograms of a face region to model the visual appearance of the face. The vertical and horizontal positions of a face are sequentially determined. First, the horizontal projection histogram of each potential face region in the current frame near the corresponding face region in the previous frame is used as an input to a back-propagation neural network (BPNN) to reliably estimate the vertical position of the face, based on the observation that the distribution of the horizontal projection histogram of a face region is stable, even when the head is rotating about an axis parallel to the vertical axis of an image plane. Second, the vertical projection histogram of an eye region derived from the estimated vertical position of the face as well as output values from the BPNN is used to estimate the horizontal position of the face. Third, the detected face region is refined by head boundary detection. These three steps are repeatedly applied to track faces in each shot of an input video. Experimental results are provided to demonstrate the efficiency of the proposed method.

AB - We present an efficient face tracking method that is robust, especially when the face is turned away from the frontal view to the side view (out-of-plane rotation). The proposed method, consisting of three steps, utilizes the horizontal and vertical projection histograms of a face region to model the visual appearance of the face. The vertical and horizontal positions of a face are sequentially determined. First, the horizontal projection histogram of each potential face region in the current frame near the corresponding face region in the previous frame is used as an input to a back-propagation neural network (BPNN) to reliably estimate the vertical position of the face, based on the observation that the distribution of the horizontal projection histogram of a face region is stable, even when the head is rotating about an axis parallel to the vertical axis of an image plane. Second, the vertical projection histogram of an eye region derived from the estimated vertical position of the face as well as output values from the BPNN is used to estimate the horizontal position of the face. Third, the detected face region is refined by head boundary detection. These three steps are repeatedly applied to track faces in each shot of an input video. Experimental results are provided to demonstrate the efficiency of the proposed method.

KW - Face tracking

KW - Projection histogram

KW - Template matching

UR - http://www.scopus.com/inward/record.url?scp=80455178502&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80455178502&partnerID=8YFLogxK

U2 - 10.1117/1.2981563

DO - 10.1117/1.2981563

M3 - Article

AN - SCOPUS:80455178502

VL - 47

JO - Optical Engineering

JF - Optical Engineering

SN - 0091-3286

IS - 9

M1 - 097205

ER -