Face detection based neural networks using robust skin color segmentation

Aamer Mohamed, Ying Weng, Jianmin Jiang, Stan Ipson

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

19 Citations (Scopus)

Abstract

This paper proposes a robust schema for face detection system via Gaussian mixture model to segment image based on skin color. After skin and non skin face candidates' selection, features are extracted directly from discrete cosine transform (DCT) coefficients computed from these candidates. Moreover, the back-propagation neural networks are used to train and classify faces based on DCT feature coefficients in Cb and Cr color spaces. This schema utilizes the skin color information, which is the main feature of face detection. DCT feature values of faces, representing the data set of skin/non-skin face candidates obtained from Gaussian mixture model are fed into the back-propagation neural networks to classify whether the original image includes a face or not. Experimental results shows that the proposed schema is reliable for face detection, and pattern features are detected and classified accurately by the back-propagation neural networks.

Original languageEnglish
Title of host publication2008 5th International Multi-Conference on Systems, Signals and Devices, SSD'08
DOIs
Publication statusPublished - 2008
Externally publishedYes
Event2008 5th International Multi-Conference on Systems, Signals and Devices, SSD'08 - Amman, Jordan
Duration: 20 Jul 200823 Jul 2008

Publication series

Name2008 5th International Multi-Conference on Systems, Signals and Devices, SSD'08

Conference

Conference2008 5th International Multi-Conference on Systems, Signals and Devices, SSD'08
Country/TerritoryJordan
CityAmman
Period20/07/0823/07/08

Keywords

  • DCT
  • Face detection
  • Feature extraction
  • Neural networks

ASJC Scopus subject areas

  • Signal Processing
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Face detection based neural networks using robust skin color segmentation'. Together they form a unique fingerprint.

Cite this