Extracting Faces and Facial Features From Color Images

Abstract

In this paper, we present image processing and pattern recognition techniques to extract human faces and facial features from color images. First, we segment a color image into skin and non-skin regions by a Gaussian skin-color model. Then, we apply mathematical morphology and region filling techniques for noise removal and hole filling. We determine whether a skin region is a face candidate by its size and shape. Principle component analysis (PCA) is used to verify face candidates. We create an ellipse model to locate eyes and mouths areas roughly, and apply the support vector machine (SVM) to classify them. Finally, we develop knowledge rules to verify eyes. Experimental results show that our algorithm achieves the accuracy rate of 96.7% in face detection and 90.0% in facial feature extraction.

Facial Feature Location and Pose Estimation for Color Face Image based on an Unsupervised Sphere Model and Fused Features

“…Calculate color adjustment factors (fR1, fG1, fB1) using respective accumulations of Cr, Cg, and Cb by formula (2). …”

“…In existed skin models, the regional model [1] doesn't have good adaptability because it usually adopts some fixed threshold values. The accuracy and adaptability of SGM (Single Gaussian Model) [2] are also not high enough, which lead to decrease the segmentation rate. The learning process and parameter estimation of GMM (Gaussian Mixture Model) [3,4] are time-consuming, which lead to increase the time and space complexity of the algorithm.…”

“…Many related methods had been presented in the past. For example, face detection or recognition based on skin models [1][2][3][4][5][6], facial feature extraction based on PCA (Principal Component Analysis) and LBP (Local Binary Patterns) [7], face detection based on template matching [3,9], face detection based on Adaboost classifer [10]. In these methods, A. R. Nusirwan et al presented a regional model with many fixed threshold in multiple color space to detect skin [1].…”

“…In these methods, A. R. Nusirwan et al presented a regional model with many fixed threshold in multiple color space to detect skin [1]. F. Y. Shih, et al, used the Single Gaussian skin model to realize the multi-face detection [2]. Z. W. Wang, et al, [3] or P. L. M. Bouttefroy, et al, [4] used Gaussian mixture model to segment skin or subtract background.…”

Methods for Ellipse Detection from Edge Maps of Real Images

“…Specifically, it is important that the structures that are elliptical are indeed detected and the structures that are non-elliptical are not detected as (Antonaros and Petrou, 2001;Belaroussi et al, 2005;Bell et al, 2006;Burrill et al, 1996;Chia et al, 2009;Dijkers et al, 2005;Fernandes, 2009;Feyaerts et al, 2001;Foresti, 2002;Foresti et al, 2005;Fu and Huang, 1995;He et al, 2009;Hua et al, 2007;Hwang et al, 2006;Iles et al, 2007;Ji et al, 1999;Kayikcioglu et al, 2000;Kumar et al, 2009;Kuno et al, 1991;Liu et al, 2007;Lu et al, 2005;Matson et al, 1970;O'Leary et al, 2005;Prasad 2011c;Rosin and West, 1992;Salas et al, 2006;Shen et al, 2009;Shih et al, 2008;Smereka and Glab, 2006;Soetedjo and Yamada, 2005;Sood et al, 2005;Takimoto et al, 2004;Tang et al, 2000;Wang et al, 2006;Wu and Wang, 1993;Yuasa et al, 2004;Zaim et al, 2006;Zhang et al, 2003;Zhou and Shen, 2003;Zhou et al, 2009) ellipses. However, the problem of detecting ellipses in real images is very challenging due to many reasons.…”