An enhanced face detection method using skin color and back-Prodagation neural network

Mansaf M. Elmansori, Khairuddin Omar

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Face detection is a challenging computer vision problem. Given a still image or an image sequence, the goal of face detection is to locate all regions that contain a face regardless of any 3D transformation and lighting condition. There are two main solutions for this problem: feature-based and image-based approaches. In this paper, a face detection method is presented where it combines two algorithms. In the first module, named skin color based face detector, used Modeling the distribution of skin color to identify areas most likely to be regions of the skin, so as to identify potential areas of skin by equalizing the probability of likelihood, the problem space is assumed to be linearly separable and, a linear threshold function is offered for the solution which is supported by a sparse feature mapping architecture. For the second module, a neural network in the form of a multilayer perceptron with back propagation solution is used which assumes to represent any function using arbitrary decision surfaces by utilizing nonlinear activation functions. Observations in the comparative experiments show that the methods show closer performances for the classification in the face and non-face space, and the method has achieved high detection rates and an acceptable number of false negatives and false positives.

Original languageEnglish
Pages (from-to)80-86
Number of pages7
JournalEuropean Journal of Scientific Research
Volume55
Issue number1
Publication statusPublished - 2011

Fingerprint

Skin Pigmentation
Face Detection
detection method
Face recognition
neural networks
Skin
skin
Neural Networks
Color
Neural networks
color
Face
Neural Networks (Computer)
Lighting
computer vision
Module
Threshold Function
back propagation
Activation Function
Back Propagation

Keywords

  • Back-propagation neural network
  • Face detection
  • Skin color

ASJC Scopus subject areas

  • Agricultural and Biological Sciences(all)
  • Earth and Planetary Sciences(all)
  • Engineering(all)
  • Materials Science(all)
  • Mathematics(all)
  • Computer Science(all)

Cite this

An enhanced face detection method using skin color and back-Prodagation neural network. / Elmansori, Mansaf M.; Omar, Khairuddin.

In: European Journal of Scientific Research, Vol. 55, No. 1, 2011, p. 80-86.

Research output: Contribution to journalArticle

@article{9fbff3734526498cb28538734c81c2c7,
title = "An enhanced face detection method using skin color and back-Prodagation neural network",
abstract = "Face detection is a challenging computer vision problem. Given a still image or an image sequence, the goal of face detection is to locate all regions that contain a face regardless of any 3D transformation and lighting condition. There are two main solutions for this problem: feature-based and image-based approaches. In this paper, a face detection method is presented where it combines two algorithms. In the first module, named skin color based face detector, used Modeling the distribution of skin color to identify areas most likely to be regions of the skin, so as to identify potential areas of skin by equalizing the probability of likelihood, the problem space is assumed to be linearly separable and, a linear threshold function is offered for the solution which is supported by a sparse feature mapping architecture. For the second module, a neural network in the form of a multilayer perceptron with back propagation solution is used which assumes to represent any function using arbitrary decision surfaces by utilizing nonlinear activation functions. Observations in the comparative experiments show that the methods show closer performances for the classification in the face and non-face space, and the method has achieved high detection rates and an acceptable number of false negatives and false positives.",
keywords = "Back-propagation neural network, Face detection, Skin color",
author = "Elmansori, {Mansaf M.} and Khairuddin Omar",
year = "2011",
language = "English",
volume = "55",
pages = "80--86",
journal = "European Journal of Scientific Research",
issn = "1450-202X",
publisher = "European Journals Inc.",
number = "1",

}

TY - JOUR

T1 - An enhanced face detection method using skin color and back-Prodagation neural network

AU - Elmansori, Mansaf M.

AU - Omar, Khairuddin

PY - 2011

Y1 - 2011

N2 - Face detection is a challenging computer vision problem. Given a still image or an image sequence, the goal of face detection is to locate all regions that contain a face regardless of any 3D transformation and lighting condition. There are two main solutions for this problem: feature-based and image-based approaches. In this paper, a face detection method is presented where it combines two algorithms. In the first module, named skin color based face detector, used Modeling the distribution of skin color to identify areas most likely to be regions of the skin, so as to identify potential areas of skin by equalizing the probability of likelihood, the problem space is assumed to be linearly separable and, a linear threshold function is offered for the solution which is supported by a sparse feature mapping architecture. For the second module, a neural network in the form of a multilayer perceptron with back propagation solution is used which assumes to represent any function using arbitrary decision surfaces by utilizing nonlinear activation functions. Observations in the comparative experiments show that the methods show closer performances for the classification in the face and non-face space, and the method has achieved high detection rates and an acceptable number of false negatives and false positives.

AB - Face detection is a challenging computer vision problem. Given a still image or an image sequence, the goal of face detection is to locate all regions that contain a face regardless of any 3D transformation and lighting condition. There are two main solutions for this problem: feature-based and image-based approaches. In this paper, a face detection method is presented where it combines two algorithms. In the first module, named skin color based face detector, used Modeling the distribution of skin color to identify areas most likely to be regions of the skin, so as to identify potential areas of skin by equalizing the probability of likelihood, the problem space is assumed to be linearly separable and, a linear threshold function is offered for the solution which is supported by a sparse feature mapping architecture. For the second module, a neural network in the form of a multilayer perceptron with back propagation solution is used which assumes to represent any function using arbitrary decision surfaces by utilizing nonlinear activation functions. Observations in the comparative experiments show that the methods show closer performances for the classification in the face and non-face space, and the method has achieved high detection rates and an acceptable number of false negatives and false positives.

KW - Back-propagation neural network

KW - Face detection

KW - Skin color

UR - http://www.scopus.com/inward/record.url?scp=79960387204&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79960387204&partnerID=8YFLogxK

M3 - Article

VL - 55

SP - 80

EP - 86

JO - European Journal of Scientific Research

JF - European Journal of Scientific Research

SN - 1450-202X

IS - 1

ER -