Face detection in color images

Rein Lien Hsu, Mohamed Abdel-Mottaleb, Anil K. Jain

Research output: Contribution to journalArticle

1442 Citations (Scopus)

Abstract

Human face detection plays an important role in applications such as video surveillance, human computer interface, face recognition, and face image database management. We propose a face detection algorithm for color images in the presence of varying lighting conditions as well as complex backgrounds. Based on a novel lighting compensation technique and a nonlinear color transformation, our method detects skin regions over the entire image and then generates face candidates based on the spatial arrangement of these skin patches. The algorithm constructs eye, mouth, and boundary maps for verifying each face candidate. Experimental results demonstrate successful face detection over a wide range of facial variations in color, position, scale, orientation, 3D pose, and expression in images from several photo collections (both indoors and outdoors).

Original languageEnglish
Pages (from-to)696-706
Number of pages11
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume24
Issue number5
DOIs
StatePublished - May 1 2002

Fingerprint

Face Detection
Color Image
Face recognition
Face
Color
Skin
Human Detection
Human-computer Interface
Video Surveillance
Lighting
Image Database
Face Recognition
Patch
Arrangement
Entire
Interfaces (computer)
Experimental Results
Range of data
Demonstrate

Keywords

  • Color transformation
  • Face detection
  • Face recognition
  • Facial feature map
  • Hough transform
  • Lighting compensation
  • Skin tone

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering
  • Artificial Intelligence
  • Computer Vision and Pattern Recognition

Cite this

Face detection in color images. / Hsu, Rein Lien; Abdel-Mottaleb, Mohamed; Jain, Anil K.

In: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, No. 5, 01.05.2002, p. 696-706.

Research output: Contribution to journalArticle

@article{5a054bdc28564e328df5ac643462dbdc,
title = "Face detection in color images",
abstract = "Human face detection plays an important role in applications such as video surveillance, human computer interface, face recognition, and face image database management. We propose a face detection algorithm for color images in the presence of varying lighting conditions as well as complex backgrounds. Based on a novel lighting compensation technique and a nonlinear color transformation, our method detects skin regions over the entire image and then generates face candidates based on the spatial arrangement of these skin patches. The algorithm constructs eye, mouth, and boundary maps for verifying each face candidate. Experimental results demonstrate successful face detection over a wide range of facial variations in color, position, scale, orientation, 3D pose, and expression in images from several photo collections (both indoors and outdoors).",
keywords = "Color transformation, Face detection, Face recognition, Facial feature map, Hough transform, Lighting compensation, Skin tone",
author = "Hsu, {Rein Lien} and Mohamed Abdel-Mottaleb and Jain, {Anil K.}",
year = "2002",
month = "5",
day = "1",
doi = "10.1109/34.1000242",
language = "English",
volume = "24",
pages = "696--706",
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
issn = "0162-8828",
publisher = "IEEE Computer Society",
number = "5",

}

TY - JOUR

T1 - Face detection in color images

AU - Hsu, Rein Lien

AU - Abdel-Mottaleb, Mohamed

AU - Jain, Anil K.

PY - 2002/5/1

Y1 - 2002/5/1

N2 - Human face detection plays an important role in applications such as video surveillance, human computer interface, face recognition, and face image database management. We propose a face detection algorithm for color images in the presence of varying lighting conditions as well as complex backgrounds. Based on a novel lighting compensation technique and a nonlinear color transformation, our method detects skin regions over the entire image and then generates face candidates based on the spatial arrangement of these skin patches. The algorithm constructs eye, mouth, and boundary maps for verifying each face candidate. Experimental results demonstrate successful face detection over a wide range of facial variations in color, position, scale, orientation, 3D pose, and expression in images from several photo collections (both indoors and outdoors).

AB - Human face detection plays an important role in applications such as video surveillance, human computer interface, face recognition, and face image database management. We propose a face detection algorithm for color images in the presence of varying lighting conditions as well as complex backgrounds. Based on a novel lighting compensation technique and a nonlinear color transformation, our method detects skin regions over the entire image and then generates face candidates based on the spatial arrangement of these skin patches. The algorithm constructs eye, mouth, and boundary maps for verifying each face candidate. Experimental results demonstrate successful face detection over a wide range of facial variations in color, position, scale, orientation, 3D pose, and expression in images from several photo collections (both indoors and outdoors).

KW - Color transformation

KW - Face detection

KW - Face recognition

KW - Facial feature map

KW - Hough transform

KW - Lighting compensation

KW - Skin tone

UR - http://www.scopus.com/inward/record.url?scp=0036566509&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036566509&partnerID=8YFLogxK

U2 - 10.1109/34.1000242

DO - 10.1109/34.1000242

M3 - Article

AN - SCOPUS:0036566509

VL - 24

SP - 696

EP - 706

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

IS - 5

ER -