A new two-dimensional block least mean squares adaptive algorithm

In this paper, a new 2-D block LMS algorithm is presented. This algorithm, which is an exact mathematical formulation of classical 2-D LMS algorithms, presents the advantage of preserving a good convergence as the block size increases. The reduction in the computational complexity is achieved by exploiting the redundancy between successive computations, rather than using disjoint or partially overlapping windows. The latter are known to degrade the convergence when the block size is large.