Cover Image

Real-time face detection using dynamic background subtraction

Link to publisher's homepage at http://www.wseas.org/

Saved in:
Bibliographic Details
Main Author: Sundaraj, Kenneth, Prof. Dr.
Other Authors: kenneth@unimap.edu.my
Format: Article
Language:English
Published: World Scientific and Engineering Academy and Society 2014
Subjects:
Face detection
Background subtraction
Online Access:http://dspace.unimap.edu.my:80/dspace/handle/123456789/33514
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.unimap-33514
record_format dspace
spelling my.unimap-335142014-04-08T07:39:58Z Real-time face detection using dynamic background subtraction Sundaraj, Kenneth, Prof. Dr. kenneth@unimap.edu.my Face detection Background subtraction Link to publisher's homepage at http://www.wseas.org/ Face biometrics is an automated method of recognizing a person’s face based on a physiological or behavioral characteristic. Face recognition works by first obtaining an image of a person. This process is usually known as face detection. In this paper, we describe an approach for face detection that is able to locate a human face embedded in an outdoor or indoor background. Segmentation of novel or dynamic objects in a scene, often referred to as background subtraction or foreground segmentation, is a critical early step in most computer vision applications in domains such as surveillance and human-computer interaction. All previous implementations aim to handle properly one or more problematic phenomena, such as global illumination changes, shadows, highlights, foreground-background similarity, occlusion and background clutter. Satisfactory results have been obtained but very often at the expense of real-time performance. We propose a method for modeling the background that uses per-pixel time-adaptive Gaussian mixtures in the combined input space of pixel color and pixel neighborhood. We add a safety net to this approach by splitting the luminance and chromaticity components in the background and use their density functions to detect shadows and highlights. Several criteria are then combined to discriminate foreground and background pixels. Our experiments show that the proposed method possesses robustness to problematic phenomena such as global illumination changes, shadows and highlights, without sacrificing real-time performance, making it well-suited for a live video event like face biometric that requires face detection and recognition. 2014-04-08T03:31:16Z 2014-04-08T03:31:16Z 2008 Article WSEAS Transactions on Information Science and Applications, vol. 5(11), pages 1531-1540 1790-0832 http://dspace.unimap.edu.my:80/dspace/handle/123456789/33514 http://www.wseas.us/e-library/transactions/information/2008/28-450.pdf en World Scientific and Engineering Academy and Society
institution Universiti Malaysia Perlis
building UniMAP Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaysia Perlis
content_source UniMAP Library Digital Repository
url_provider http://dspace.unimap.edu.my/
language English
topic Face detection
Background subtraction
spellingShingle Face detection
Background subtraction
Sundaraj, Kenneth, Prof. Dr.
Real-time face detection using dynamic background subtraction
description Link to publisher's homepage at http://www.wseas.org/
author2 kenneth@unimap.edu.my
author_facet kenneth@unimap.edu.my
Sundaraj, Kenneth, Prof. Dr.
format Article
author Sundaraj, Kenneth, Prof. Dr.
author_sort Sundaraj, Kenneth, Prof. Dr.
title Real-time face detection using dynamic background subtraction
title_short Real-time face detection using dynamic background subtraction
title_full Real-time face detection using dynamic background subtraction
title_fullStr Real-time face detection using dynamic background subtraction
title_full_unstemmed Real-time face detection using dynamic background subtraction
title_sort real-time face detection using dynamic background subtraction
publisher World Scientific and Engineering Academy and Society
publishDate 2014
url http://dspace.unimap.edu.my:80/dspace/handle/123456789/33514
_version_ 1643797196486737920
score 13.222552

Similar Items