ON OPTIMAL LOW-RANK APPROXIMATION OF MULTIDIMENSIONAL DISCRETE SIGNALS

This brief describes an algorithmic development of the optimal low-ran k approximation (LRA) of multidimensional (M-D) signals with M greater than or equal to 3. The algorithms developed can he regarded as a dim ensional generalization of the singular value decomposition (SVD) whic h is of fundamental importance for analyzing signals that can be repre sented in a matrix form. In particular, iterative algorithms for optim al and suboptimal LRA of three-dimensional (3-D) arrays are presented in detail. Application of the 3-D LRA to the compression of image sequ ences is discussed.