The skin color in an image captured by a camera undergoes variation as the illumination changes. Therefore, the skin color detection based only on a static model often decreases the detection rate. For enhancing the robust skin color detection using a static model, the illuminant color estimated from images captured under various illumination conditions is converted to a canonical illuminant. This paper first estimates the illuminant color from the pixels in the sclera region of the eyes and then converts it to a canonical color for robust skin color detection. Experimental results show that the skin color detection using the proposed method increases the detection rate especially for the images taken in the low or high correlated color temperature of the illumination.
展开▼
