From 3ed331b9254d70ac564e4a19163e5b7ad1eba572 Mon Sep 17 00:00:00 2001 From: Vasil Zlatanov Date: Tue, 20 Nov 2018 19:20:24 +0000 Subject: Quick error fixes in alternative method desc --- report/paper.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'report') diff --git a/report/paper.md b/report/paper.md index e94e3a0..134243b 100755 --- a/report/paper.md +++ b/report/paper.md @@ -162,8 +162,8 @@ K=1, as visible in figure \ref{fig:k-diff}. \end{center} \end{figure} -The process for alternative method is draws similarities to LDA. Similarly to LDA it calculates per class means. It then projects -images onto eigenvectors from subspaces generated per each class. While it does not attempt to discriminate features per class, the +The process for alternative method draws similarities to LDA. It calculates per class means and then projects +images onto eigenvectors of subspaces generated from training data per class. While it does not attempt to discriminate features per class, the calculation of independent class subspaces is effective at differentiating between the classes when reconstruction error from each class subspace is compared. The class with the subspace that generates the least error is selected as the label. -- cgit v1.2.3-54-g00ecf