35. Automatic Image Mosaicing Using Discrete Cosine Transform

The image mosaicing can be used to combine two or more pictures extracted at different time from different sensors or different views. The general problem of mosaicing is to create a single seamless image by aligning a series of spatially overlapped images; the result is an image with a field of view greater than that of a single image. This paper proposes a framework for creating particularly convenient way to generate mosaics is by stitching together many ordinary photographs(capturing static scenes), proposed algorithm uses creating visually pleasing mosaics using a discrete cosine transform (DCT), it is a separable linear transformation and phase-correlation method to estimate the displacement between two adjacent images, DCT performs along a single dimension and the other dimension for an input images and also correlation-based scheme is used which operates in the discrete domain for finding the transformed coordinates (translational and rotational parameters) and use them for image mosaicing.