Title :
Contour matching using local affine transformations
Author :
Bachelder, Ivan A. ; Ullman, Shimon
Author_Institution :
Artificial Intelligence Lab., MIT, Cambridge, MA, USA
Abstract :
A noniterative scheme for determining contour matches using locally affine transformations is proposed. The method assumes that contours are approximated by the orthographic projection of planar patches within oriented neighborhoods of varying sizes. For degenerate cases, a minimal matching solution is chosen closest to the minimal pure translation. Performance on noisy synthetic and natural contour imagery is reported
Keywords :
image recognition; contour matches; locally affine transformations; minimal matching; natural contour imagery; noisy synthetic imagery; oriented neighborhoods; orthographic projection; planar patches; Apertures; Artificial intelligence; Computed tomography; Image motion analysis; Laboratories; Least squares approximation; Motion measurement; Object recognition; Optical sensors; Stability;
Conference_Titel :
Computer Vision and Pattern Recognition, 1992. Proceedings CVPR '92., 1992 IEEE Computer Society Conference on
Conference_Location :
Champaign, IL
Print_ISBN :
0-8186-2855-3
DOI :
10.1109/CVPR.1992.223169
