Title :
Two-dimensional block diagonal LMS adaptive filtering
Author :
Azimi-Sadjadi, Mahmood R. ; Pan, Hongye
Author_Institution :
Dept. of Electr. Eng., Colorado State Univ., Fort Collins, CO, USA
fDate :
9/1/1994 12:00:00 AM
Abstract :
The paper is concerned with the development of two-dimensional (2D) adaptive filters using the block diagonal least mean squared (BDLMS) method. In this adaptive filtering scheme, the image is scanned and processed block by block in a diagonal fashion, and the filter weights are adjusted once per block rather than once per pixel. The diagonal scanning is adopted to avoid the problems inherent in the 1D standard scanning schemes and to account for the correlations in two directions. The weight updating equation for 2D BDLMS is derived, and the convergence properties of the algorithms are investigated. Simulation results that indicate the effectiveness of the 2D BDLMS when used for image enhancement, estimation, and detection applications are presented
Keywords :
adaptive filters; convergence of numerical methods; filtering and prediction theory; image processing; least squares approximations; two-dimensional digital filters; block diagonal least mean squared method; convergence properties; correlations; detection applications; diagonal scanning; estimation; filter weights; image; image enhancement; two-dimensional block diagonal adaptive filtering; weight updating equation; Adaptive control; Adaptive filters; Convergence; Filtering; Image enhancement; Least squares approximation; Pixel; System identification; Transversal filters; Two dimensional displays;
Journal_Title :
Signal Processing, IEEE Transactions on
