Image registration is a basic and troublesome assignment where managing
remotely sensed satellite images. The registration of different platform images has turned
into a critical issue with an expanding number of images gathered each day from various
satellites. There exist an extensive variety of registration strategies for various kinds of
utilizations and information sources, however no calculation is exact for enrolling multisource
images reliably. This exploration tends to this issue by examining the advancement
of a completely automatic registration system for an extremely confused issue of multisensor
remote detecting images particularly Synthetic aperture radar (SAR) and electrooptical
images.
The development of this automatic image registration method is based on the
extraction and matching of common features that are visible in both images. The algorithm
involves the following five steps: noise removal, edge extraction, edge linking, pattern
extraction and pattern matching to collect automatically the Ground Control Points (GCPs)
required to the image registration.
The application of the developed automatic image registration model to different SAR
and optical image pairs showed that accurate ground control points (GCPs) could be
identified automatically.