Fusion of 2D grayscale images using multiscale morphology

A scheme for fusion of multi-sensor 2D images based on multiscale morphology is presented in this paper. A point-based registration, using affine transformation is performed prior to fusion. The scale-specific features are extracted from both the images using the morphological towers constructed in course of various types of multiscale filtering. Extracted features are combined to get the fused image. A quantitative measure of the degree of fusion is estimated by cross-correlation coefficient and the error measure obtained by eigenvector fitting between the fused image and each of the constituting images. (C) 2001 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.