From c8be196fb7ee4f795238f63a617a896041cd5583 Mon Sep 17 00:00:00 2001 From: nunzip Date: Sun, 18 Nov 2018 16:27:57 +0000 Subject: Fix labels problem with reconstruction face --- report/paper.md | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'report') diff --git a/report/paper.md b/report/paper.md index e756f69..4a5e90a 100755 --- a/report/paper.md +++ b/report/paper.md @@ -131,6 +131,7 @@ number 21 and 2 respectively, are reconstructed as shown in fig.\ref{face10rec} of M=10, M=100, M=200, M=300. The last picture is the original face. ![Reconstructed Face C21\label{face160rec}](fig/face160rec.pdf) + ![Reconstructed Face C2\label{face10rec}](fig/face10rec.pdf) It is already observable that the improvement in reconstruction is marginal for M=200 @@ -334,8 +335,10 @@ vaying between 0.11s(low M_pca) and 0.19s(high M_pca). The scatter matrices obtained, S\textsubscript{B}(scatter matrix between classes) and S\textsubscript{W}(within-class scatter matrix), respectively show ranks of at most c-1(51) and -N-c(312 maximum for our standard 70-30 split). The rank of S\textsubscript{W} -will have the same value of M_pca for M_pca$\leq$N-c. +N-c(312 maximum for our standard 70-30 split). +The rank of S\textsubscript{W} will have the same value of M_pca for M_pca$\leq$N-c. + +NEED MORE SCATTER MATRIX CONTENT Testing with M_lda=50 and M_pca=115 gives 92.9% accuracy. The results of such test can be observed in the confusion matrix shown in figure \ref{ldapca_cm}. -- cgit v1.2.3-54-g00ecf