ABSTRACT
Skin segmentation is a pre-processing step in any application involving the detection of face, biometrics, gesture recognition, objectionable image blocking, human computer interaction and other recognition systems with pre-processing element being skin. The challenges in skin segmentation process are background blend, illumination variation, variation in skin tone and occlusion. In this paper, an Eight-fold supervised non-parametric skin-segmentation approach is designed to address these challenges. In this method, 96 features are extracted from the input image and 12 sets are formed with initial set containing 8 features and subsequent set consisting 8 new features to the existing set. Kendall correlation coefficient is used to select the 8 features based on their performance. The algorithm is tested on “Compaq” dataset and performance parameters are calculated. These parameters are compared with state-of-the-art techniques to qualitatively prove the performance of the work. The measured parameters indicate an increase of 19.47% in F1-score, 7.23% increase in specificity and 6.67% increase in the accuracy compared to existing techniques.
