Matching Interest Points Using Projective Invariant Concentric Circles
Author(s)
Chiu, Han-Pang
Lozano-Pérez, Tomás
Date Issued
January 2005
Series/Report no.
Computer Science (CS);
Abstract
We present a new method to perform reliable matching between different images. This method exploits a projective invariant property between concentric circles and the corresponding projected ellipses to find complete region correspondences centered on interest points. The method matches interest points allowing for a full perspective transformation and exploiting all the available luminance information in the regions. Experiments have been conducted on many different data sets to compare our approach to SIFT local descriptors. The results show the new method offers increased robustness to partial visibility, object rotation in depth, and viewpoint angle change.
Subjects
Image Matching
Interest Point
Local Descriptors
Persistent DSpace Link
