A study of skin color detection using a merging technique

Abstract

With advances in technology, image-processing techniques are changing daily. All high-tech products are moving toward controls using human touch. Therefore, in the future, human face detection will have an important role in applications such as facial recognition, human computer interfaces, facial image database management, and video surveillance. This study has three parts: (1) a comparison of the effect on skin color of the YC r C b and YC 0 r C 0 b threshold values, for three different races' skin colors; (2) the segmentation of skin and skin-like objects; and (3) the way in which image-merging techniques effectively filter out skin-like interference in a skin-like environment and repair-broken images. This study uses a merging algorithm, which uses a relative Euclidean and 8-neighbors method to merge broken binary images in the region of interest. The experiments show that the completeness of the image is improved, which proves the effectiveness of the method.