expeAuto.tex

The third campaign of tests aims at evaluating the performance of the new
detector with respect to the previous one on a selection of more standard
images.
Compared measures $M$ are the execution time $T$, the amount $N$ of detected
blurred segments, the mean length $L$ and the mean width $W$ of the detected
segments.
For the sake of objectivity, these results are also compared to the same
measurements made on the 20 images data base used for the CannyLine line
segment detector \cite{LuAl15}.
\RefTab{tab:auto} gives the measures obtained on one of the selected images
(\RefFig{fig:auto}) and the result of a systematic test on the CannyLine
data base.
\begin{figure}[h]
%\center
  \begin{tabular}{
      c@{\hspace{0.1cm}}c@{\hspace{0.1cm}}c@{\hspace{0.1cm}}}
    \includegraphics[width=0.32\textwidth]{Expe_auto/buro.png} &
%    \includegraphics[width=0.32\textwidth]{Expe_auto/coloredOld.png} &
%    \includegraphics[width=0.32\textwidth]{Expe_auto/coloredNew.png} \\
    \includegraphics[width=0.32\textwidth]{Expe_auto/bsOld.png} &
    \includegraphics[width=0.32\textwidth]{Expe_auto/bsNew.png} \\
    & \includegraphics[width=0.22\textwidth]{Expe_auto/dssDetailOld.png} &
    \includegraphics[width=0.22\textwidth]{Expe_auto/dssDetailNew.png}
    \begin{picture}(1,1)
      {\color{red}{
        \put(-19.5,31){\framebox(28,9)}
        \put(-5.5,31){\vector(-2,-1){20}}
        \put(-133.5,31){\framebox(28,9)}
        \put(-117.5,31){\vector(-2,-1){20}}
      }}
      {\color{dwhite}{
        \put(-291,32.5){\circle*{8}}
        \put(-177,32.5){\circle*{8}}
        \put(-63,32.5){\circle*{8}}
        \put(-188,4.5){\circle*{8}}
        \put(-75,4.5){\circle*{8}}
      }}
      \put(-293.5,30){a}
      \put(-179.5,30){b}
      \put(-65.5,30){c}
      \put(-191,2){d}
      \put(-77.5,2){e}
    \end{picture}
  \end{tabular}
  \caption{Automatic detection on standard images:
           an input image (a), the segments found by the old detector (b)
           and those found by the new detector (c), and a detail of the
           enclosing digital segments for both old (d) and new (e) detectors.}
  \label{fig:auto}
\end{figure}
\begin{table}
\centering
\input{Expe_auto/perfTable}
\caption{Measured performance of both detectors on standard images.
         $M_{old}$ (resp. $M_{new}$) denotes the measure obtained with
         the previous (resp. new) detector.}
\label{tab:auto}
\end{table}

The new detector is faster and finds more edges than the previous one.
The details of \RefFig{fig:auto} d) and e) illustrate the achieved
accuracy improvements.
The output segments are thinner but also shorter.
The control of the assigned width to fit to the detected segment width
has the side effect of blocking the segment expansion when the remote parts
are more noisy.
Found edges are thus more fragmented.
The relevance of this behavior depends strongly on application requirements.
Therefore the control of the assigned width is left as an option, the user
can let or cancel it.
In both case, it could be interesting to combine the detector with a tool
to merge aligned segments.

%Although these observations in unsupervised context should be reproduced
%in supervised context, similar experiments require an application context
%to dispose of a ground truth and of real users to assess the detector
%relevance through ergonomy evaluations.