Abstract
This paper focuses on a novel region-based image fusion method which facilitates increased flexibility with the definition of a variety of fusion rules. A dual-tree complex wavelet transform (DT-CWT) is used to segment the features of the input images, either jointly or separately, to produce a region map. Characteristics of each region are calculated and a region-based approach is used to fuse the images, region-by-region, in the wavelet domain. This method gives results comparable to pixel-based fusion methods, but despite an increase in complexity, has a number of advantages over such methods. These include: the ability to use more intelligent semantic fusion rules; and for regions with certain properties to be attenuated or accentuated
Translated title of the contribution | Region-based image fusion using complex wavelets |
---|---|
Original language | English |
Title of host publication | Seventh International Conference on Information Fusion, Stockholm, Sweden |
Publisher | Int. Soc. of Information Fusion |
Pages | 555 - 562 |
Number of pages | 8 |
Volume | 1 |
ISBN (Print) | 917056115X |
Publication status | Published - 28 Jun 2004 |