Image segmentation of the acetowhite region in cervix images based on chromaticity

The authors proposed a novel approach for the acetowhite region segmentation in order to improve the segmentation accuracy. The proposed algorithm took two steps to finish the segmentation work, the first step: applied the watershed algorithm to finish the coarse segmentation and locate the acetowhite region, the second step: adjusted the acetowhite region boundary to plot precise acetowhite region. 163 uterine neck images were selected from a database to verify the segmenting algorithm. To some extend, 97% of the segmentation results were identical with the segmentation results that were marked by radiologist.