Lip Segmentation Using Geometrical Model Of ColorDistribution

An accurate and robust lip region detection algorithmbased on skin and lip color segmentation is presented in thispaper. Here skin and lip color analysis performs in chromaticand YCbCr color space respectively. The proposed algorithmdefines geometrical models for skin and lip color distribution inorder to detect skin and lip pixels in color image. The proposedalgorithm performs lip detection in two stages. First skin pixelsare detected in a given color image and face candidates areextracted. Then lip pixels are investigated within face candidates.We propose a segmentation method based on horizontal andvertical accumulation of the image pixel values. Experimentalresults show that the proposed method detects lips effectivelywith high accuracy