Person identification system for future digital tv with intelligence

Min Cheol Hwang, Le Thanh Ha, Nam Hyeong Kim, Chun S. Park, Sung-Jea Ko

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

Intelligent digital TV (iDTV) is a future digital TV with intelligence which can automatically provide userpersonalized services for each audience. For the userpersonalized services, the iDTV should recognize audiences in real-time. In this paper, we define a novel structure of the iDTV and propose a real-time person identification system in the iDTV that analyzes captured images and recognizes audiences. The proposed system consists of three processing units: preprocessing for reducing computational costs of the proposed system, face detection using a statistical approach, and face recognition using Support Vector Machines (SVMs). Experimental results show that the proposed system achieves efficient performance with high recognition accuracy of 90% or higher at the speed of 15∼20 fps, which is suitable for the iDTV.

Original languageEnglish
Pages (from-to)218-226
Number of pages9
JournalIEEE Transactions on Consumer Electronics
Volume53
Issue number1
DOIs
Publication statusPublished - 2007 Feb 1

Fingerprint

Face recognition
Identification (control systems)
Support vector machines
Processing
Costs

Keywords

  • Audience identification
  • Face detection
  • Face recognition
  • Intelligent digital TV
  • Personalized services

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Cite this

Person identification system for future digital tv with intelligence. / Hwang, Min Cheol; Ha, Le Thanh; Kim, Nam Hyeong; Park, Chun S.; Ko, Sung-Jea.

In: IEEE Transactions on Consumer Electronics, Vol. 53, No. 1, 01.02.2007, p. 218-226.

Research output: Contribution to journalArticle

Hwang, Min Cheol ; Ha, Le Thanh ; Kim, Nam Hyeong ; Park, Chun S. ; Ko, Sung-Jea. / Person identification system for future digital tv with intelligence. In: IEEE Transactions on Consumer Electronics. 2007 ; Vol. 53, No. 1. pp. 218-226.
@article{10cfc99c89694cabb6fb7d53b4915e7a,
title = "Person identification system for future digital tv with intelligence",
abstract = "Intelligent digital TV (iDTV) is a future digital TV with intelligence which can automatically provide userpersonalized services for each audience. For the userpersonalized services, the iDTV should recognize audiences in real-time. In this paper, we define a novel structure of the iDTV and propose a real-time person identification system in the iDTV that analyzes captured images and recognizes audiences. The proposed system consists of three processing units: preprocessing for reducing computational costs of the proposed system, face detection using a statistical approach, and face recognition using Support Vector Machines (SVMs). Experimental results show that the proposed system achieves efficient performance with high recognition accuracy of 90{\%} or higher at the speed of 15∼20 fps, which is suitable for the iDTV.",
keywords = "Audience identification, Face detection, Face recognition, Intelligent digital TV, Personalized services",
author = "Hwang, {Min Cheol} and Ha, {Le Thanh} and Kim, {Nam Hyeong} and Park, {Chun S.} and Sung-Jea Ko",
year = "2007",
month = "2",
day = "1",
doi = "10.1109/TCE.2007.339528",
language = "English",
volume = "53",
pages = "218--226",
journal = "IEEE Transactions on Consumer Electronics",
issn = "0098-3063",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "1",

}

TY - JOUR

T1 - Person identification system for future digital tv with intelligence

AU - Hwang, Min Cheol

AU - Ha, Le Thanh

AU - Kim, Nam Hyeong

AU - Park, Chun S.

AU - Ko, Sung-Jea

PY - 2007/2/1

Y1 - 2007/2/1

N2 - Intelligent digital TV (iDTV) is a future digital TV with intelligence which can automatically provide userpersonalized services for each audience. For the userpersonalized services, the iDTV should recognize audiences in real-time. In this paper, we define a novel structure of the iDTV and propose a real-time person identification system in the iDTV that analyzes captured images and recognizes audiences. The proposed system consists of three processing units: preprocessing for reducing computational costs of the proposed system, face detection using a statistical approach, and face recognition using Support Vector Machines (SVMs). Experimental results show that the proposed system achieves efficient performance with high recognition accuracy of 90% or higher at the speed of 15∼20 fps, which is suitable for the iDTV.

AB - Intelligent digital TV (iDTV) is a future digital TV with intelligence which can automatically provide userpersonalized services for each audience. For the userpersonalized services, the iDTV should recognize audiences in real-time. In this paper, we define a novel structure of the iDTV and propose a real-time person identification system in the iDTV that analyzes captured images and recognizes audiences. The proposed system consists of three processing units: preprocessing for reducing computational costs of the proposed system, face detection using a statistical approach, and face recognition using Support Vector Machines (SVMs). Experimental results show that the proposed system achieves efficient performance with high recognition accuracy of 90% or higher at the speed of 15∼20 fps, which is suitable for the iDTV.

KW - Audience identification

KW - Face detection

KW - Face recognition

KW - Intelligent digital TV

KW - Personalized services

UR - http://www.scopus.com/inward/record.url?scp=34147154182&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34147154182&partnerID=8YFLogxK

U2 - 10.1109/TCE.2007.339528

DO - 10.1109/TCE.2007.339528

M3 - Article

VL - 53

SP - 218

EP - 226

JO - IEEE Transactions on Consumer Electronics

JF - IEEE Transactions on Consumer Electronics

SN - 0098-3063

IS - 1

ER -