Robust Object Recognition under Partial Occlusions Using NMF
Figure 1
Visualization
of the Nmfsc results for a low-dimension example (3D data sets and as
training points). The plane spanned by and represents the
NMF subspace due to this training set.
and
are the
training set projections to the subspace implicitly given by matrix in the
NMF algorithm. and are the
orthogonal projections of the training sets onto the NMF subspace.