Token-based extraction of straight lines

The authors present a computational approach to the extraction of straight lines based on the principles of perceptual organization. In particular, they consider how local information that is spatially distributed can be organized into a large-scale geometric structure in a computationally efficient manner. Symbolic tokens representing line segments and relations which are primarily geometric in nature and used to control a hierarchical grouping process. The relational measures on pairs of lines are based on collinearity, proximity, and similarity in contrast. The algorithm is implemented within a local, parallel, hierarchical framework for symbolic grouping that involves a cycle of linking, optimization, and replacement steps. Experimental results on a variety of natural scene images demonstrate effectiveness of the filtering and optimization stages in the extraction of straight lines. Issues in the development of a more general framework for symbolic grouping are also discussed