AUTOMATIC FACIAL SKIN DETECTION USING GAUSSIAN MIXTURE MODEL UNDER VARYING ILLUMINATION

作者：Hossain Md Foisal^*; Shamsi Mousa; Alsharif Mohammad Reza; Zoroofi Reza A; Yamashita Katsumi

来源：International Journal of Innovative Computing Information and Control, 2012, 8(2): 1135-1144.

• Facial skin detection
• Gaussian mixture model
• Varying illumination
• Skin models

Recently, skin detection methodologies based on skin-color information as a cue have gained much attention as skin-color provides computationally effective, robust information against rotations, scaling and partial occlusions. Skin detection using color information can be a challenging task as the skin appearance in images is affected by various factors such as illumination, background, camera characteristics and ethnicity. This paper presents a method of facial skin extraction by estimating varying illumination of the image and using Gaussian Mixture Model (GMM) of facial images. For illumination estimation, two skin models are used. One is under normal condition and the other is under bright illumination condition. If the estimated illumination is very far from the normal image, then the given image is illumination compensated and feeds again to Gaussian Mixture Model for segmentation, which automatically segments the skin portion. Experimental results on frontal and lateral color images show the efficiency of the proposed method compared with the conventional skin color segmentation method based on GMM. Experimental results show that this method is highly applicable for practical purpose such as surgical planning.

• 出版日期2012-2