From 646a0e43c4a52d16528c9d2692143e90b56e8774 Mon Sep 17 00:00:00 2001
From: Vasil Zlatanov <v@skozl.com>
Date: Tue, 20 Nov 2018 18:40:43 +0000
Subject: Add conclusion

---
 report/paper.md | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/report/paper.md b/report/paper.md
index 0f385c1..af24be3 100755
--- a/report/paper.md
+++ b/report/paper.md
@@ -461,6 +461,10 @@ Seed & Individual$(M=120)$ & Bag + Feature Ens.$(M=60+95)$\\ \hline
 \label{tab:compare}
 \end{table}
 
+# Conclusion
+
+We have looked at the relevance of PCA and LDA when applied to face recognition, and analyzed the individual and combined performance. We have further looked at improvement made available by ensemble learning, utilising data and feature randomisation together with PCA-LDA and found that it is an effective approach to face recognition.
+
 # References
 
 <div id="refs"></div>
-- 
cgit v1.2.3-54-g00ecf