DSpace About DSpace Software     MIT Libraries    
 

DSpace at MIT >
Computer Science and Artificial Intelligence Lab (CSAIL) >
Artificial Intelligence Lab Publications >
AI Memos (1959 - 2004) >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1721.1/5979

Title: Contour Matching Using Local Affine Transformations
Authors: Bachelder, Ivan A.
Keywords: matching
affine transformation
optical flow
aperturesproblem
correspondence
Issue Date: 1-Apr-1992
Series/Report no.: AIM-1326
Abstract: Partial constraints are often available in visual processing tasks requiring the matching of contours in two images. We propose a non- iterative scheme to determine contour matches using locally affine transformations. The method assumes that contours are approximated by the orthographic projection of planar patches within oriented neighborhoods of varying size. 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.
URI: http://hdl.handle.net/1721.1/5979
Appears in Collections:AI Memos (1959 - 2004)

Files in This Item:

File Description SizeFormat
AIM-1326.ps2738KbPostScriptView/Open
AIM-1326.pdf2141KbAdobe PDFView/Open


This item is protected by original copyright

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

 

invent @ MIT: The HP-MIT Alliance Copyright © 2002 MIT and  Hewlett-Packard - Feedback