Energy-based adaptive skin segmentation for hand and head detection

This paper addresses a problem of skin segmentation for sign language recognition purposes. The main contributions of the presented research is an adaptive skin model enhanced with a blob analysis algorithm which significantly improves skin detection effectiveness. Adaptive skin detector utilizes a statistical skin color model updated dynamically based on a face region defined by eye positions. Face geometry is used for eye detection in luminance channel prior to the model adaptation. Color-based skin detectors classify every pixel separately which results in high false positives for background pixels which color is similar to human skin. The proposed blob analysis technique verifies detected skin regions by taking into account pixel topology. The experiments for ECU database showed that with the proposed approach false positive rate was reduced from 15.6% to 6% compared with a statistical model in RGB. Increased precision of skin detection makes it applicable to gesture recognition purposes.