AUTOMATED ASSEMBLING OF IMAGES - IMAGE MONTAGE PREPARATION

Image montage (or mosaic) rinds a great deal of applications in ophtha lmology, digital terrain mapping, and in autonomous navigation of re-e ntry vehicles. However, there is no direct method available for image montage preparation. Image registration methods may be used to solve t his problem, but most of these methods are not useful, because they re quire either specific feature points in images or a great deal of over lapping between images of neighboring regions. A normalized correlatio n method is used for the preparation of montages when there is no rota tional shirt between neighboring images. A pyramidal approach is devel oped to reduce the computation. Further, a new method is developed for montage preparation when there is also a relational shift between two neighboring regions. Different sets of subimages, which have both rot ational and translational shifts with the subimages of neighboring reg ions, are taken for preparing image montages. The proposed method does not require any human supervision and the results are found to be ver y accurate.