Skin Color Detection Using Region-Based Approach

Skin color provides a powerful cue for complex computer vision applications. Although skin color detection has been an active research area for decades, the mainstream technology is based on the individual pixels. This paper, which extended our previous work [1], presented a new regionbased technique for skin color detection which outperformed the current state-of-the-art pixelbased skin color detection technique on the popular Compaq dataset [2]. Color and spatial distance based clustering technique is used to extract the regions from the images, also known as superpixels followed by a state-of-the-art non-parametric pixel-based skin color classifier called the basic skin color classifier. The pixel-based skin color evidence is then aggregated to classify the superpixels. Finally, the Conditional Random Field (CRF) is applied to further improve the results. As CRF operates over superpixels, the computational overhead is minimal. Our technique achieved 91.17% true positive rate with 13.12% false negative rate on the Compaq dataset tested over approximately 14,000 web images.