Representative patterns for model-based matching

Abstract A single intensity image of a three-dimensional (3D) object obtained under perspective projection can be reduced to a two-dimensional (2D) line drawing which contains patterns characteristic of the object and of its pose. These patterns can provide clues to narrow down the search for possible objects and poses when comparing 2D view-class models of 3D objects against images. This paper describes a general way of representing 2D line patterns and of using the patterns to consistently label 2D models of 3D objects. The representation is based on groups of three line segments that are likely to be found in most images containing man-made objects, but are unlikely to occur by accident. Experimental results using representative patterns to match 2D view-class models of 3D objects against real images of the objects are included.