aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authornunzip <np.scarh@gmail.com>2018-12-10 18:01:09 +0000
committernunzip <np.scarh@gmail.com>2018-12-10 18:01:09 +0000
commitc8f0949a6192b68a8e2ea62836ee97ecbdf3eb3e (patch)
tree8a295eb043ea349d373ef198e7945fd0fbc27599
parent30583c4ce19bc77e48810894b277857429fbc201 (diff)
downloadvz215_np1915-c8f0949a6192b68a8e2ea62836ee97ecbdf3eb3e.tar.gz
vz215_np1915-c8f0949a6192b68a8e2ea62836ee97ecbdf3eb3e.tar.bz2
vz215_np1915-c8f0949a6192b68a8e2ea62836ee97ecbdf3eb3e.zip
Fix failed merge
-rwxr-xr-xreport2/paper.md32
1 files changed, 12 insertions, 20 deletions
diff --git a/report2/paper.md b/report2/paper.md
index 2e0bb0a..4ccf5ca 100755
--- a/report2/paper.md
+++ b/report2/paper.md
@@ -1,25 +1,17 @@
-# Summary
-
-In this report we analysed how distance metrics learning affects classification
-accuracy for the dataset CUHK03. The baseline method used for classification is
-Nearest Neighbors based on Euclidean distance. The improved approach we propose
-mixes Jaccardian and Mahalanobis metrics to obtain a ranklist that takes into
-account also the reciprocal neighbors. This approach is computationally more
-complex, since the matrices representing distances are effectively calculated
-twice. However it is possible to observe a significant accuracy improvement of
-around 10% for the $@rank1$ case. Accuracy improves overall, especially for
-$@rankn$ cases with low n.
+
+# Forulation of the Addresssed Machine Learning Problem
+
+## Probelm Definition
The person re-identification problem presented in this paper requires mtatching
-pedestrian images from disjoint camera's by pedestrian detectors. This problem
-is challenging, as identities captured in photsos are subject to various
-lighting, pose, blur, background and oclusion from various camera views. This
-report considers features extracted from the CUHK03 dataset, following a 50 layer
-Residual network (Resnet50). This paper considers distance metrics techniques which
-can be used to perform person re-identification across **disjoint* cameras, using
-these features.
-
-## CUHK03
+pedestrian images from disjoint camera's by pedestrian detectors. This problem is
+challenging, as identities captured in photsos are subject to various lighting, pose,
+blur, background and oclusion from various camera views. This report considers
+features extracted from the CUHK03 dataset, following a 50 layer Residual network
+(Resnet50). This paper considers distance metrics techniques which can be used to
+perform person re-identification across **disjoint* cameras, using these features.
+
+## Dataset - CUHK03 Summary
The dataset CUHK03 contains 14096 pictures of people captured from two
different cameras. The feature vectors used, extracted from a trained ResNet50 model