Abstract. This paper proposes a method for skin region segmentation for face images with unbalanced color and light based on preprocessing of a multicolor face image sequence. In this method, multicolor face images from a sequence are preprocessed in order to remove color offset and uneven brightness. Then the color data from the preprocessed face images are used for taking the average in order to remove noise and smoothen the face image. Finally, skin region segmentation for the average preprocessed face image is realized based on the established ellipse skin model. Experiments have shown that this method has good performance.
Keywords: skin region; multicolor; image sequence; preprocessing; face detection
Begin on 10 October 2014 this website is no longer activated for article process in Journal of Mathematical and Fundamental Sciences, Journal of Engineering and Technological Sciences,
Journal of ICT Research and Applications and Journal of Visual Art and Design. The next process will be proceeded under new website at http://journals.itb.ac.id.
Download Article