Geometric Segmentation of Perspective Images Based on Symmetry Groups

Authors:
Allen Y. Yang;Shankar Rao;Kun Huang;Wei Hong;Yi Ma
Affiliations:
-;-;-;-;-
Venue:
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Year:
2003

Citing 0
Cited 4

On Symmetry and Multiple-View Geometry: Structure, Pose, and Calibration from a Single Image

International Journal of Computer Vision
Symmetry-based photo-editing

Pattern Recognition
Detecting symmetry and symmetric constellations of features

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
Unified detection of skewed rotation, reflection and translation symmetries from affine invariant contour features

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

Symmetry is an effective geometric cue to facilitate conventionalsegmentation techniques on images of man-madeenvironment. Based on three fundamental principles thatsummarize the relations between symmetry and perspectiveimaging, namely, structure from symmetry, symmetry hypothesistesting, and global symmetry testing, we developa prototype system which is able to automatically segmentsymmetric objects in space from single 2-D perspective images.The result of such a segmentation is a hierarchy ofgeometric primitives, called symmetry cells and complexes,whose 3-D structure and pose are fully recovered. Such ageometrically meaningful segmentation may greatly facilitateapplications such as feature matching and robot navigation.