Two-dimensional object recognition using multiresolution models

Abstract

A multiresolution, model-based matching technique is described for coarse-to-fine object recognition. Each two-dimensional object is modeled as a directed acyclic graph. Each node in the graph stores a boundary segment of the object model at a selected level of spatial resolution. The root node of the graph contains the coarsest resolution representation of the boundary of the object, leaf nodes contain sections of the boundary at the highest resolution, and intermediate nodes contain features at intermediate levels of resolution. Arcs are directed from boundary segments at one level of resolution to spatially related boundary segments at finer levels of resolution. A generalized Hough transform is used to match the model nodes with regions in the corresponding level of resolution in a given input image pyramid. First, the root node of the model graph is matched with the coarsest level of the input image pyramid and an ordered list of hypothesized positions and orientations for the object is generated. These hypotheses limit the area in which the search for subobjects (children nodes) must be conducted. If the subobjects of a hypothesis are not found, the next best hypothesis for the position and orientation of the object at the coarsest level is tried. Advantages of this approach include the use of multiresolution descriptions to model different parts of an object at different scales, the ability to detect partially occluded objects, the ability to dynamically control the coarse-to-fine matching process, and the increase in recognition speed over conventional single resolution recognition algorithms.