Efficient multidimensional nonlinear but seperable filtering operation. The concept of a nonlinear seperable filter is not very common, but nevertheless can prove very useful since computation time can be reduced greatly. Consider a funciton like max that is applied to a 2 dimensional window. max could also be applied to each row of the window, then to the resulting column, insead of being applied to the entire window simultaneously. This is what is meant here by a seperable nonlinear filter. The function fun must be able to take an input of the form C=fun(I,radius,param1,...paramk). The return C must have the same size as I, and each element of C must be the result of applying the nlfilt operation to the local column (of size 2r+1) of A. For example: % COMPUTES LOCAL SUMS: C = nlfilt_sep( I, dims, shape, @rnlfilt_sum ); % COMPUTES LOCAL MAXES: C = nlfilt_sep( I, dims, shape, @rnlfilt_max ); INPUTS I - matrix to compute fun over dims - size of volume to compute fun over shape - 'valid', 'full', or 'same', see conv2 help fun - nonlinear filter params - optional parameters for nonlinear filter OUTPUTS I - resulting image DATESTAMP 26-Jan-2006 2:00pm See also NLFILTBLOCK_SEP, RNLFILT_SUM, RNLFILT_MAX