EXTRACTING STRAIGHT LINES.

Abstract

This paper presents a new approach to the extraction of straight lines in intensity images. Pixels are grouped into edge support regions of similar gradient orientation, and then the structure of the associated intensity surface is used to determine the location of properties of the edge. The resulting regions and extracted parameters form two separate representations of a straight line segment, pixel-based and symbolic, that can be used together for a variety of purposes. The algorithm appears to be far more effective than previous techniques for two key reasons: 1) the gradient orientation is used as the initial organizing criterion in the extraction of straight lines, instead of the gradient magnitude; and 2) data directed organization of the complete context of a straight line is determined prior to any local decisions about participating edge points.