ImProc: added 'visually comparing of the results'.

parent ef71a246
......@@ -42,7 +42,38 @@ convert the RGB color model the HSV color model.
% Does your model improve the results compared with the RGB model?
\begin{table}
In most cases, the HSV color model gives a better result. When comparing
picture 8 with picture 1, 2 and 3, the histogram intersections of the RGB color
model are resp. 52\%, 66\% and 66\%. With the HSV color model, these
intersections are resp. 28\%, 61\% and 45\%.
\begin{figure}[H]
\center
\includegraphics[height=3cm]{../database/8.jpg}
\caption{Picture 8 from the given database.}
\end{figure}
If we visually compare picture 8 with the pictures 1, 2 and 3, we can clearly
see that picture 2 shows more similarities (similar yellow color, similar size
and ratio of the object) than the other two pictures.
\begin{figure}[H]
\center
\includegraphics[height=3cm]{1-2-3.jpg}
\caption{From left to right picture 1, 2 and 3 from the given database.}
\end{figure}
However, in the RGB model, there is no clear distinction in the histogram
intersections (52\%, 66\% and 66\%), while the HSV model gives picture 1 and 3
a much lower intersection percentage (picture 2 has 61\%, picture 1 has 28\%
and picture 3 has 45\%).
So, using the HSV color model does improve the results.
\subsection{Histogram intersection tables}
\begin{table}[H]
\hspace{-1.5in}
\begin{tabular}{r|rrrrrrrrrrrrrrrrrrrr}
\toprule
......@@ -77,7 +108,7 @@ convert the RGB color model the HSV color model.
\caption{Histogram intersection of 20 pictures with the RGB color model.}
\end{table}
\begin{table}
\begin{table}[H]
\hspace{-1.5in}
\begin{tabular}{r|rrrrrrrrrrrrrrrrrrrr}
\toprule
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment