Journal
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
Volume 25, Issue 9, Pages 1193-1200Publisher
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2003.1227997
Keywords
shape; polygons; rectilinearity; measurement
Ask authors/readers for more resources
The paper introduces a shape measure intended to describe the extent to which a closed polygon is rectilinear. Other than somewhat obvious measures of rectilinearity (e.g., the sum of the differences of each corner's angle from multiples of 90degrees), there has been little work in deriving a measure that is straightforward to compute, is invariant under scale, rotation, and translation, and corresponds with the intuitive notion of rectilinear shapes. There are applications in a number of different areas of computer vision and photogrammetry. Rectilinear structures often correspond to human-made objects and are therefore justified as attentional cues for further processing. For instance, in aerial image processing and reconstruction, where building footprints are often rectilinear on the local ground plane, building structures, once recognized as rectilinear, can be matched to corresponding shapes in other views for stereo reconstruction. Perceptual grouping algorithms may seek to complete shapes based on the assumption that the object in question is rectilinear. Using the proposed measure, such systems can verify this assumption.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available