We describe a two-stage algorithm for detecting human faces based on the grey-scale information of the input image and facial geometry. The first stage involves locating approximately the head boundaries and the facial features, the exactlocations of which are determined in the second stage. The algorithm is evaluated on datasets and some characteristics of its performance are identified. As well as being of value for the feature location algorithm in particular, the approach is intendedto illustrate how any vision technique may be characterized in an objective way.
展开▼