FUZZY CLASSIFICATION, IMAGE SEGMENTATION AND SHAPE ANALYSIS FOR HUMAN FACE DETECTION

In this paper, we describe a new algorithm for human face detection. The algorithm uses both color and shape analysis. Color analysis is based on the novel idea of fuzzy classification that manipulates ambiguity in colors; using this technique we can robustly classify skin region and non-skin region. In order to decide whether the skin region is a face or not, we test its shape by applying an edge detection using Canny operator and an ellipse detection using Hough transform. We show with experimental results how the important detection ratio makes our system an effective tool for face detection