A Novel Approach of 2D Adaptive Filter Based on MPSO Technique for Biomedical Image

Abstract

In this paper, extension of the 1-D adaptive filter schemes to 2D formation and the new 2D adaptive filters are designed. The results of proposed scheme are compared with 2D variable step-size normalized least mean squares, the 2D VSS affine projection algorithms, the 2D set-membership NLMS, and 2D SM APA. The performance of proposed scheme is compared with other reported methods for 2D adaptive filter design. Based on simulation results, it is demonstrated that the proposed method can achieve 85% and 90% reduction in normalized mean square error and normalized maximum error mean, respectively. Moreover, the proposed 2D-ANC filter applied for reconstruction of a biomedical image shows 6 dB signal-to-noise ratio improved as compared to recently reported algorithm.