Dekker1/ResearchMethods
Archived
1
0
Fork 0
Code

Missed one

Browse Source
This commit is contained in:
Jip J. Dekker 2018-05-25 15:11:00 +10:00
parent 7ccbb169ca
commit ea18a4ca3e
1 changed files with 9 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
mini_proj/report/waldo.tex
View File

@ -211,15 +211,15 @@
Each original puzzle is broken down into many images, and only contains one
Waldo. Although Waldo might span multiple 64$\times$64 pixel squares, this
means that the non-Waldo data far outnumbers the Waldo data. To combat the
bias introduced by the skewed data, all Waldo images were artificially
augmented by performing random rotations, reflections, and introducing
random noise in the image to produce news images. In this way, each original
Waldo image was used to produce an additional 10 variations of the image,
inserted into the image array. This provided more variation in the true
positives of the data set and assists in the development of more robust
methods by exposing each technique to variations of the image during the
training phase. \\
means that the ``non-Waldo'' data far outnumbers the ``Waldo'' data. To
combat the bias introduced by the skewed data, all Waldo images were
artificially augmented by performing random rotations, reflections, and
introducing random noise in the image to produce news images. In this way,
each original Waldo image was used to produce an additional 10 variations of
the image, inserted into the image array. This provided more variation in
the true positives of the data set and assists in the development of more
robust methods by exposing each technique to variations of the image during
the training phase. \\
Despite the additional data, there were still ten times more ``non-Waldo''
images than Waldo images. Therefore, it was necessary to cull the