A NEW 2-DIMENSIONAL BLOCK ADAPTIVE FIR FILTERING ALGORITHM AND ITS APPLICATION TO IMAGE-RESTORATION

This paper presents a new two-dimensional (2-D) optimum block stochast ic gradient (TDOBSG) algorithm for 2-D adaptive finite impulse respons e (FIR) filtering. The TDOBSG algorithm employs a space-varying conver gence factor for all the filter coefficients, where the convergence fa ctor at each block iteration is optimized in a least squares sense tha t the squared norm of the a posteriori estimation error vector is mini mized, It has the same order of computational complexity as another 2- D optimum block adaptive (TDOBA) algorithm reported recently. Computer simulations for image restoration show that the TDOBSG algorithm outp erforms the TDOBA algorithm and other related algorithms in terms of o bjective and/or subjective measures.