Orientation space filtering for multiple orientation line segmentation

Abstract

The goal of this paper is to present an appropriate method for the segmentation of lines at intersections (X-junctions) and branches (T-junctions), which can be regarded as local regions where lines occur at multiple orientations. A novel representation called “orientation space” is proposed, which is derived by adding the orientation axis to the abscissa and the ordinate of the image. The orientation space representation is constructed by treating the orientation parameter, to which Gabor filters can be tuned, as a continuous variable. The problem of segmenting lines at multiple orientations is dealt with by thresholding 3D images in the orientation space and then detecting the connected components therein. In this way, X-junctions and T-junctions can be separated effectively. Curve grouping can also be accomplished. The segmentation of mathematically modeled X-, T-, and L-junctions is demonstrated and analyzed. The sensitivity limits of the method are also discussed. Experimental results using both synthesized and real images show the method to be effective for junction segmentation and curve grouping