Image Registration Using Object Shape's Chain Code
Ranjan Jana, Chhanda Ray · 2009
This paper focuses an efficient image registration method based on image features. Image registration is the process of overlaying two or more images of the same scene taken at different times, from different viewpoints, and/or by different sensors. This approach uses four basic steps of image registration procedure; namely, feature detection, feature matching, mapping function design, and image transformation and re-sampling. In this paper, object shape of images has been considered as an important feature for image registration. Initially, a process to obtain the unique chain code for each shape of images, which is invariant to translation, scaling and rotation, is generated. Using this unique chain code of shape representation, the translation, scaling and rotation of two different images has been calculated. Finally, the image registration has been done based on the unique chain code for each shape of the same image. The major goal of this paper is to register two or more different images of the same scene using object shape's chain code.