Head pose-invariant eyelid and iris tracking method

Kimimasa Tamura, Kiyoshi Hashimoto, Yoshimitsu Aoki

Research output: Contribution to journalArticle

Abstract

These days, there is more demand for a camera-based gaze estimation method for new interfaces and new marketing measurement tools. Considering these applications, the system should track a new user without any operation such as calibration. It should also admit user's natural head pose changes. Previous methods, however, need a calibration procedure before execution and have less accuracy in a head moving situation. In this paper, we propose a method which tracks the user's eyelids and iris automatically and accurately. Our method is a pretreatment of gaze estimation without any calibration and head pose restraint. First of all, we track the facial feature points from an input face image and estimate its head pose, extracting the eye region image. On the eye region image, we track the eyelid shape based on an eyelid shape model generated beforehand from PCA. Finally we track the iris inside the eyelid based on the eyeball model. The eyelid and iris tracking is processed by Particle Filter. An evaluation against a database including head pose changes confirmed that the accuracy of eyelid and iris tracking was improved compared with previous methods.

Original languageEnglish
Pages (from-to)19-27
Number of pages9
JournalElectronics and Communications in Japan
Volume99
Issue number2
DOIs
Publication statusPublished - 2016 Feb 1

Fingerprint

Iris
Calibration
Invariant
Marketing
marketing
Cameras
Feature Point
Particle Filter
pretreatment
Camera
cameras
Face
filters
evaluation
Evaluation
estimates
Model
Estimate

Keywords

  • 3D reconstruction
  • ASM
  • eyelid tracking
  • gaze estimation
  • interface
  • iris tracking

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Networks and Communications
  • Physics and Astronomy(all)
  • Signal Processing
  • Applied Mathematics

Cite this

Head pose-invariant eyelid and iris tracking method. / Tamura, Kimimasa; Hashimoto, Kiyoshi; Aoki, Yoshimitsu.

In: Electronics and Communications in Japan, Vol. 99, No. 2, 01.02.2016, p. 19-27.

Research output: Contribution to journalArticle

Tamura, Kimimasa ; Hashimoto, Kiyoshi ; Aoki, Yoshimitsu. / Head pose-invariant eyelid and iris tracking method. In: Electronics and Communications in Japan. 2016 ; Vol. 99, No. 2. pp. 19-27.
@article{2fe9ef3d07bd447f9d4003d08508db65,
title = "Head pose-invariant eyelid and iris tracking method",
abstract = "These days, there is more demand for a camera-based gaze estimation method for new interfaces and new marketing measurement tools. Considering these applications, the system should track a new user without any operation such as calibration. It should also admit user's natural head pose changes. Previous methods, however, need a calibration procedure before execution and have less accuracy in a head moving situation. In this paper, we propose a method which tracks the user's eyelids and iris automatically and accurately. Our method is a pretreatment of gaze estimation without any calibration and head pose restraint. First of all, we track the facial feature points from an input face image and estimate its head pose, extracting the eye region image. On the eye region image, we track the eyelid shape based on an eyelid shape model generated beforehand from PCA. Finally we track the iris inside the eyelid based on the eyeball model. The eyelid and iris tracking is processed by Particle Filter. An evaluation against a database including head pose changes confirmed that the accuracy of eyelid and iris tracking was improved compared with previous methods.",
keywords = "3D reconstruction, ASM, eyelid tracking, gaze estimation, interface, iris tracking",
author = "Kimimasa Tamura and Kiyoshi Hashimoto and Yoshimitsu Aoki",
year = "2016",
month = "2",
day = "1",
doi = "10.1002/ecj.11776",
language = "English",
volume = "99",
pages = "19--27",
journal = "Electronics and Communications in Japan",
issn = "1942-9533",
publisher = "Scripta Technica",
number = "2",

}

TY - JOUR

T1 - Head pose-invariant eyelid and iris tracking method

AU - Tamura, Kimimasa

AU - Hashimoto, Kiyoshi

AU - Aoki, Yoshimitsu

PY - 2016/2/1

Y1 - 2016/2/1

N2 - These days, there is more demand for a camera-based gaze estimation method for new interfaces and new marketing measurement tools. Considering these applications, the system should track a new user without any operation such as calibration. It should also admit user's natural head pose changes. Previous methods, however, need a calibration procedure before execution and have less accuracy in a head moving situation. In this paper, we propose a method which tracks the user's eyelids and iris automatically and accurately. Our method is a pretreatment of gaze estimation without any calibration and head pose restraint. First of all, we track the facial feature points from an input face image and estimate its head pose, extracting the eye region image. On the eye region image, we track the eyelid shape based on an eyelid shape model generated beforehand from PCA. Finally we track the iris inside the eyelid based on the eyeball model. The eyelid and iris tracking is processed by Particle Filter. An evaluation against a database including head pose changes confirmed that the accuracy of eyelid and iris tracking was improved compared with previous methods.

AB - These days, there is more demand for a camera-based gaze estimation method for new interfaces and new marketing measurement tools. Considering these applications, the system should track a new user without any operation such as calibration. It should also admit user's natural head pose changes. Previous methods, however, need a calibration procedure before execution and have less accuracy in a head moving situation. In this paper, we propose a method which tracks the user's eyelids and iris automatically and accurately. Our method is a pretreatment of gaze estimation without any calibration and head pose restraint. First of all, we track the facial feature points from an input face image and estimate its head pose, extracting the eye region image. On the eye region image, we track the eyelid shape based on an eyelid shape model generated beforehand from PCA. Finally we track the iris inside the eyelid based on the eyeball model. The eyelid and iris tracking is processed by Particle Filter. An evaluation against a database including head pose changes confirmed that the accuracy of eyelid and iris tracking was improved compared with previous methods.

KW - 3D reconstruction

KW - ASM

KW - eyelid tracking

KW - gaze estimation

KW - interface

KW - iris tracking

UR - http://www.scopus.com/inward/record.url?scp=84954159736&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84954159736&partnerID=8YFLogxK

U2 - 10.1002/ecj.11776

DO - 10.1002/ecj.11776

M3 - Article

AN - SCOPUS:84954159736

VL - 99

SP - 19

EP - 27

JO - Electronics and Communications in Japan

JF - Electronics and Communications in Japan

SN - 1942-9533

IS - 2

ER -