Real-time head detection

This paper describes a syntactic approach to the classification of moving objects in front of a video camera. The implementation of syntactic pattern recognition techniques is examined for a real-time system, focusing on the detection of human heads in front of a video camera. In particular, the author describes the technique used to classify objects between heads and non-heads, the results achieved, and the implications of the real-time property of this system. In a syntactic approach the higher level information of an image is extracted from the lower level structure of that image. The techniques used by this application to extract the higher level of information from the lower level structure of the image is discussed in this paper. This paper also examines how a quadratic neural network may be used as both a classifier, and as a tool for modelling data. In this system quadratic neural networks are used both to model the lower level structure of the images from the video camera, and as a tool for classifying the objects in front of the video camera.