Hyper spectral images provide a more detailed information than multispectral images, as every pixel in the image contains contiguous spectral bands to characterize the details in the scene. Since hyper spectral images occupy large memory space and take more processing time for the transmission, it is highly desirable to use an efficient compression technique. In this paper we discuss hyper spectral image compression using matrix factorization based on a proposed non-iterative method and compare with the Tucker decomposition for hyper spectral image compression. The proposed non-iterative positive matrix factorization method is based on least mean square error (LMSE) criterion. Results indicate that hyper spectral image compression based on non-iterative method of matrix factorization needs less processing time, compared with compression based on Tucker decomposition.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.