Invariant-based registration of rotated and blurred images
Authors:
- B. ZitovaBZB. Zitova
- T. SukTST. Suk
- 20 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 1262-1264
Abstract
Image registration is a classical problem in remotely sensed image analysis. In this paper, attention is paid to control point matching for the case when the images are blurred and rotated compared to one another. The matching is performed by means of a new class of moment invariants, which are calculated over the neighborhood of each candidate. The proposed invariants are invariant not only to rotation and translation but also to image blurring by any symmetric point spread function. Thanks to this, the authors can register blurred images directly without any de-blurring.Keywords
This publication has 5 references indexed in Scilit:
- Robust detection of significant points in multiframe imagesPattern Recognition Letters, 1999
- Degraded image analysis: an invariant approachIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- Object matching by means of matching likelihood coefficientsPattern Recognition Letters, 1995
- Restoration and reconstruction of AVHRR imagesIEEE Transactions on Geoscience and Remote Sensing, 1995
- A survey of image registration techniquesACM Computing Surveys, 1992