DMCA
Component Based Method for Face Detection using Fuzzy Membership Functions
BibTeX
@MISC{Mirhassani_componentbased,
author = {Seyed Mostafa Mirhassani and Bardia Yousefi and Maysam Yazdan Panahi and M. J. Rastegar Fatemi},
title = {Component Based Method for Face Detection using Fuzzy Membership Functions},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
In this paper we address the problem of face detection in grayscale images. Before make candidates we calculate membership face components that influence to make more accurate answer and rejecting false positives in detection. The proposed method detects all candidate windows that has enough membership of face components. Eyes, eyebrows and Lip are organized to build fuzzifier membership functions using their pattern, distances of their location in 2D plan, and edginess of forehead. α cut is used as defuzzifier and a parameter to achieve fuzzy based decision using empirical face features. A novel and simple fuzzy method for face detection using the face structural model is introduced. Due to using fuzzy membership functions for face detection, its rate using has increased over the original qualitative model for face detection. The experiments show promising results compared to the original structural method without using fuzzy. Key words:
Keyphrases
face detection fuzzy membership function membership function false positive grayscale image membership face component simple fuzzy method make candidate promising result candidate window original qualitative model face structural model original structural method face component enough membership empirical face feature key word accurate answer
