Skip to Main Content
Frequently the need arises to combine remotely sensed data taken from different sensors for improved interpretation of an imaged area. However, before this multi-sensor data fusion can be performed the image data must first be registered geometrically. In this paper we investigate the use of an information-theoretic similarity measure known as cross-cumulative residual entropy (CCRE) to perform the registration of SAR imagery and optical data. An affine transformation is implemented in the registration procedure to account for geometric errors other than simple translation and rotation. The results of our experiments showed that the CCRE registration algorithm performed satisfactorily and provided a significant improvement over the standard mutual-information based technique.