Documentaton - BLOCKS - BLOCK_TEST_SEGLOC

Superpixel neighborhoods, as proposed in Fulkerson et. al 2009.

BK = BLOCK_TEST_SEGLOC() Initializes the block with the default options.

BK = BLOCK_TEST_SEGLOC(BK) Executes the block with options and inputs BK.

Required inputs:

db

The database.

hist

The segment histograms.

classifier

The trained segment classifier.

Options:

bk.rand_seed

Set the random seeds before proceeding. Default of [] does not change the seeds.

bk.seg_neighbors

The number of neighbors to use. Default 0.

bk.testall

Test on all segments instead of only training segments. Default 0.

Fetchable attributes:

test

Classification result (images). Returns [class confidence] for required input: seg_id.

segtest

Classification result (superpixels). Returns [class confidence] for required input: seg_id. class is a vector Nx1 where N is the number of superpixels. confidence is a matrix Nx1 cell array, where each cell is a Cx1 vector expressing the confidence in each of C classes.