Abstract
Images of the same scene object can easily be considered as belonging to different objects if these objects are viewed from different orientation and ranges. Hence, image recognition calls for choosing the proper geometric transformation functions to match images as the initial step so that recognition by template matching can be done as the second step. This paper describes new method that represents the boundary of each two images by B-splines and matches the B-spline of each two objects to determine whether they belong to the same scene object. The method concentrates on solving linear simultaneous equations only when handling the geometric transformation functions, which takes almost negligible computational time by using the standard Gaussian Elimination.
Original language | English |
---|---|
Pages (from-to) | 1219-1224 |
Number of pages | 6 |
Journal | IEICE Transactions on Information and Systems |
Volume | E77-D |
Issue number | 11 |
Publication status | Published - 1 Nov 1994 |
ASJC Scopus subject areas
- Computer Graphics and Computer-Aided Design
- Information Systems
- Software