Geometric Segmentation of Perspective Images Based on Symmetry Groups

Symmetry is an effective geometric cue to facilitate conventional segmentation techniques on images of man-made environment. Based on three fundamental principles that summarize the relations between symmetry and perspective imaging, namely, structure from symmetry, symmetry hypothesis testing, and global symmetry testing, we develop a prototype system which is able to automatically segment symmetric objects in space from single 2-D perspective images. The result of such a segmentation is a hierarchy of geometric primitives, called symmetry cells and complexes, whose 3-D structure and pose are fully recovered. Such a geometrically meaningful segmentation may greatly facilitate applications such as feature matching and robot navigation.

• Type: Conference
• Year: 2003
• Where: ICCV
• Authors: Allen Y. Yang, Shankar Rao, Kun Huang, Wei Hong, Yi Ma
• Keywords: Computer Vision, Conventional Segmentation Techniques, Global Symmetry Testing, ICCV 2003, Meaningful Segmentation, Symmetry Cells, Symmetry Hypothesis Testing