Grouping via the Matching of Repeated Patterns

In this contribution, a novel and robust, geometry-based grouping strategy is proposed. Repeated, planar patterns in special relative positions are detected. The grouping is based on the idea of fixed structures. These are structures such as lines or points that remain fixed under the transformations mapping the patterns onto each other. As they define subgroups of the general group of projectivities, they significantly reduce the complexity of the problem. First, some initial matches are found by comparing local, affinely invariant regions. Then, possible fixed structure candidates are hypothesized using a cascaded Hough transform. In a further step, these candidates are verified. In this paper, we concentrate on planar homologies, i.e. subgroups that have a line of fixed points and a pencil of fixed lines.