X-Git-Url: https://bilbo.iut-bm.univ-fcomte.fr/and/gitweb/canny.git/blobdiff_plain/ded436ff1397fd455304cbae04f58e4c0703ea01..24da70a2907152b45f175222de4962951669ac12:/experiments.tex

diff --git a/experiments.tex b/experiments.tex
index 60b0f2f..b952fae 100644
--- a/experiments.tex
+++ b/experiments.tex
@@ -1,6 +1,77 @@
+
+\subsection{Image Quality}
+The visual quality of the STABYLO scheme is evaluated in this section.
+Four metrics are computed in these experiments : 
+the Peak Signal to Noise Ratio (PSNR), 
+the PSNR-HVS-M familly~\cite{PSECAL07,psnrhvsm11} , 
+the BIQI~\cite{MB10,biqi11} and 
+the weigthed PSNR (wPSNR)~\cite{DBLP:conf/ih/PereiraVMMP01}.
+The first one is widely used but does not take into
+account Human Visual System (HVS).
+The other last ones have been designed to tackle this problem.
+
+\begin{table}
+\begin{center}
+\begin{tabular}{|c|c|c|}
+\hline
+Embedding rate &  Adaptive 
+10 \% &  \\
+\hline
+PSNR &      &      \\
+\hline
+PSNR-HVS-M & 78.6  & 72.9 \\
+\hline
+BIQI & 28.3 & 28.4 \\
+\hline
+wPSNR & 86.43& 77.47 \\
+\hline
+\end{tabular}
+\end{center}
+\caption{Quality measeures of our steganography approach\label{table:quality}} 
+\end{table}
+
+
+Compare to the Edge Adpative scheme detailed in~\cite{Luo:2010:EAI:1824719.1824720}, our both wPSNR and PSNR values are always higher than their ones.
+
+\JFC{comparer aux autres approaches}
+
+
+
 \subsection{Steganalysis}
 
 
-Détailler \cite{Fillatre:2012:ASL:2333143.2333587}
 
-Vainqueur du BOSS challenge~\cite{DBLP:journals/tifs/KodovskyFH12}
+The quality of our approach has been evaluated through the two 
+AUMP~\cite{Fillatre:2012:ASL:2333143.2333587}
+and Ensemble Classifier~\cite{DBLP:journals/tifs/KodovskyFH12} based steganalysers.
+Both aims at detecting hidden bits in grayscale natural images and are 
+considered as the state of the art of steganalysers in spatial domain~\cite{FK12}.
+The former approach is based on a simplified parametric model of natural images.
+Parameters are firstly estimated and a adaptive Asymptotically Uniformly Most Powerful
+(AUMP) test is designed (theoretically and practically) to check whether
+a natural image has stego content or not.  
+In the latter, the authors show that the 
+machine learning step, (which is often
+implemented as support vector machine)
+can be a favourably executed thanks to an Ensemble Classifiers.
+
+
+
+\begin{table}
+\begin{center}
+\begin{tabular}{|c|c|c|c|}
+Shemes & \multicolumn{2}{|c|}{STABYLO} & HUGO\\
+\hline
+Embedding rate &  Adaptive & 10 \% &  10 \%\\
+\hline
+AUMP & 0.39  & 0.22     &  0.50     \\
+\hline
+Ensemble Classifier &   &      &      \\
+
+\hline
+\end{tabular}
+\end{center}
+\caption{Steganalysing STABYLO\label{table:steganalyse}} 
+\end{table}
+
+