sarsoo/visual-search
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

submitted

Browse Source
This commit is contained in:
aj 2019-12-03 13:46:34 +00:00
parent 10cd140c2c
commit 3bb054ff23
2 changed files with 16 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.txt
View File

@ -1,7 +1,7 @@
/data - pulled images and spreadsheet of data
/descriptor - functions for extracting descriptors
/distance - functions fo measuring distance between descriptors
/distance - functions for measuring distance between descriptors
/util - util functions such as toGreyscale and EVD
There are two types of script, ones that run a category response once (cvpr_visualsearch_*) and ones that iteratively

25
report/coursework.lyx
View File

@ -3431,8 +3431,18 @@ Conclusions
\end_layout
\begin_layout Standard
To summarise, spatial texture techniques were found to perform better than
exclusively colour based methods such as a global colour histogram.
To summarise, each descriptor has varying efficacy for different applications
and the context should be identified before selecting one over the other.
\end_layout
\begin_layout Standard
Optimum internal parameters for each are data and query dependedent but
well performing values can be obtained experimentally.
\end_layout
\begin_layout Standard
Spatial texture techniques were found to perform better than exclusively
colour based methods such as a global colour histogram.
While the combination of both colour and texture information didn't provide
as much of an improvement over either separately as expected, the combination
of both colour and texture information as part of the descriptor was the
@ -3441,14 +3451,9 @@ To summarise, spatial texture techniques were found to perform better than
\begin_layout Standard
The use of appropriate amounts (approximately 2%) of dimensionality reduction
following principal component analysis provided additional performance
increases.
\end_layout
\begin_layout Standard
Following investigations into difference distance measures the L1 norm tended
to be best performing method.
following principal component analysis provided performance increases over
the standard L2 norm, however following investigations into difference
distance measures the L1 norm tended to be best performing method.
\end_layout
\begin_layout Standard