An axis-based representation for recognition

@inproceedings{citeulike:1151237, abstract = {We present a new axis-based shape representation scheme along with a matching framework to address the problem of generic shape recognition. The main idea is to define the relative spatial arrangement of local symmetry axes and their metric properties in a shape centered coordinate frame. The resulting descriptions are invariant to scale, rotation, small changes in viewpoint and articulations. Symmetry points are extracted from a surface whose level curves roughly mimic the motion by curvature. By increasing the amount of smoothing on the evolving curve, only those symmetry axes that correspond to the most prominent parts of a shape are extracted. The representation does not suffer from the common instability problems of the traditional connected skeletons. It captures the perceptual qualities of shapes well. 'Therefore finding the similarities and the differences among shapes becomes easier. The matching process gives highly successful results on a diverse database of 2D shapes.}, author = {Asian, C. and Tari, S. }, citeulike-article-id = {1151237}, journal = {Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on}, pages = {1339--1346 Vol. 2}, posted-at = {2007-03-09 14:04:50}, priority = {2}, title = {An axis-based representation for recognition}, url = {http://ieeexplore.ieee.org/xpls/abs\_all.jsp?arnumber=1544875}, volume = {2}, year = {2005} }

TY - CONF ID - citeulike:1151237 L3 - citeulike-article-id:1151237 N2 - We present a new axis-based shape representation scheme along with a matching framework to address the problem of generic shape recognition. The main idea is to define the relative spatial arrangement of local symmetry axes and their metric properties in a shape centered coordinate frame. The resulting descriptions are invariant to scale, rotation, small changes in viewpoint and articulations. Symmetry points are extracted from a surface whose level curves roughly mimic the motion by curvature. By increasing the amount of smoothing on the evolving curve, only those symmetry axes that correspond to the most prominent parts of a shape are extracted. The representation does not suffer from the common instability problems of the traditional connected skeletons. It captures the perceptual qualities of shapes well. 'Therefore finding the similarities and the differences among shapes becomes easier. The matching process gives highly successful results on a diverse database of 2D shapes. JF - Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on EP - 1346 Vol. 2 TI - An axis-based representation for recognition VL - 2 SP - 1339 AU - Asian, C AU - Tari, S PY - 2005/// UR - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1544875 ER -