Share Email Print

Proceedings Paper

Fast algorithm of calculating invariant features for image matching
Author(s): Feng Gui; QiWei Lin
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Image matching method is an important technique in image processing. It gives reference and methodology to fully use different kinds of data. An image matching method based on invariant features of image and image data basis generating method are presented in this paper. The method is realized by following procedures: first, we establish the image data basis, then we change the newly obtained image to the scale of the base image, and finally we use invariant features of image to correlate the base image and the newly obtained image, in this way to find the best matching point. At the same time, a fast algorithm is introduced in this paper to calculate the invariant features of image. The method is insensitive to translation, rotation and scale, also it is simple and stable.

Paper Details

Date Published: 10 October 2000
PDF: 5 pages
Proc. SPIE 4222, Process Control and Inspection for Industry, (10 October 2000); doi: 10.1117/12.403860
Show Author Affiliations
Feng Gui, Jianghan Petroleum Univ. (China)
QiWei Lin, Jianghan Petroleum Univ. (China)

Published in SPIE Proceedings Vol. 4222:
Process Control and Inspection for Industry
Shulian Zhang; Wei Gao, Editor(s)

© SPIE. Terms of Use
Back to Top