Real-time face and hand detection

We present a visual processing system to detect the face and hands of a human being in real time from a video sequence captured by a webcam regardless of position and background and even with poor and changing illumination conditions. The system has a first preprocessing stage, including a color filtering module, a motion filtering module, a color-based segmentation, 4 processing channels merge module and, finally, a contour search and selection module. The aim of the first stage is to discard the image regions which are highly unlikely to correspond with skin. Thus, the second and most important stage of the system is a previously trained Fuzzy ARTMAP multiscale neural network architecture, which only processes the image regions selected by the preprocessing stage. As a result, a saving in processing time needed to make a real-time detection is achieved. The multiscale module is formed by three paths, each having one of three different Fuzzy ARTMAP networks. The neural networks make the last decision about face and hand detection.