| Superresolution Of Images With (2002) | |||||||||||||||||
Abstract | |||||||||||||||||
| This chapter develops a superresolution methodology and specifies an architecture to magnify and make clear small-sized and/or low-fidelity images. Superresolution is particularly relevant for multimedia applications due to the poor quality of images imposed by low bandwidth requirements. The method is based on the fact that data dependent bases are able to reconstruct signals with a resolution above the one imposed by the Shannon sampling theorem, provided that statistical information about the signals is utilized to specify the bases. Here we propose to learn the bases and the reconstruction kernels using the information available in local neighborhoods and across scales. First, local neighborhoods of a training image are clustered based on local features. Each cluster is assigned to a reconstruction kernel that is designed as an optimal mapping relating homologous neighborhoods across scales. A superresolved image is obtained by feeding an image through the architecture, or equivalently, by convolving the image with the learned family of kernels. Several examples are presented demonstrating the effectiveness of the approach. | |||||||||||||||||
Details der Publikation | |||||||||||||||||
| |||||||||||||||||