Point Pattern Matching

Shape recognition is an important task in computer vision and pattern recognition. The term shape is referred to as the invariant geometrical properties of the relative distances among a set of static spatial features of an object. These static spatial features are known as the shape features of the object [17]. For the purpose of recognition, much of the visual data perceived by the human eye is highly redundant. It has been suggested from the viewpoint of the human visual system that some dominant points along an object contour are rich in information content and sufficient to characterize the shape of the object. Thus, point pattern matching (PPM),wherein points are used as shape features, is a crucial vision task.