i've a grayscale image and i've divided it into discrete blocks of 8x8
Then, i've calculated the mean of each block and i want to check how one block is correlated to the other block
which type of correlation should i use?
or something else???
i want the correlation of two image blocks in the range -1, 0, 1
can anybody tell me how to do so?
i've used corrcoef
Error using bsxfun Mixed integer class inputs are not supported.
Error in cov (line 93) xc = bsxfun(@minus,x,sum(x,1)/m); % Remove mean
Error in corrcoef>correl (line 209) r = cov(x);
Error in corrcoef (line 92) r = correl(x);
93 xc = bsxfun(@minus,x,sum(x,1)/m); % Remove mean
but the above error occurs.