Viewing a response to: @terrylovejoy/re-alexs1320-math-from-finland-yes-it-s-fast-fastica-20180507t085604484z
(Probably) the best algorithm would be the SOBI-RO from the package ICALAB, by Andrzej Cichocki. That obscure method works with everything I've ever put as the input. It's especially good for sparse signals. In your case, the workflow would be: each image --> image to vector (in Matlab) --> all the vectors packed into the input matrix --> SOBI-RO --> back to images (vector to matrix) --> and... see what is the signal and what is the noise :) --> discard the noise From *n* images, *n* components could be extracted (both in ICA and SOBI), in contrast to PCA/FA where you need *2n+1* starting signals for only *n* components,
post_id | 47,357,136 |
---|---|
author | alexs1320 |
permlink | re-terrylovejoy-re-alexs1320-math-from-finland-yes-it-s-fast-fastica-20180507t094617112z |
category | steemstem |
json_metadata | "{"app": "steemit/0.1", "tags": ["steemstem"]}" |
created | 2018-05-07 09:46:21 |
last_update | 2018-05-07 09:46:21 |
depth | 2 |
children | 0 |
net_rshares | 0 |
last_payout | 2018-05-14 09:46:21 |
cashout_time | 1969-12-31 23:59:59 |
total_payout_value | 0.000 SBD |
curator_payout_value | 0.000 SBD |
pending_payout_value | 0.000 SBD |
promoted | 0.000 SBD |
body_length | 631 |
author_reputation | 149,050,464,338,619 |
root_title | "Math from Finland, yes, it's fast: FastICA" |
beneficiaries | [] |
max_accepted_payout | 1,000,000.000 SBD |
percent_steem_dollars | 10,000 |