X-Git-Url: https://bilbo.iut-bm.univ-fcomte.fr/and/gitweb/canny.git/blobdiff_plain/dc91e8c17710cc249f83001625e1d14581f2d276..5178f772a789c49b261c48acc466a982d413a9a9:/experiments.tex?ds=sidebyside

diff --git a/experiments.tex b/experiments.tex
index 22900c0..9590b1c 100644
--- a/experiments.tex
+++ b/experiments.tex
@@ -150,9 +150,12 @@ The steganalysis quality of our approach has been evaluated through the % two
 Ensemble Classifier~\cite{DBLP:journals/tifs/KodovskyFH12} based steganalyser.
 Its  particularization to spatial domain is 
 considered as state of the art steganalysers.
-Firstly, a space 
-of 686 co-occurrence and Markov features is extracted from the 
-set of cover images and the set of training images. Next a small 
+\JFC{Features that are embedded into this steganalysis process 
+are CCPEV and SPAM features as described 
+in~\cite{DBLP:dblp_conf/mediaforensics/KodovskyPF10}.
+These latter are extracted from the 
+set of cover images and the set of training images.}
+Next a small 
 set of weak classifiers is randomly built,
 each one working on a subspace of all the features.
 The final classifier is constructed by a majority voting 
@@ -213,3 +216,13 @@ However due to its huge number of integration features, it is not lightweight.
 All these numerical experiments confirm 
 the objective presented in the motivations:
 providing an efficient steganography approach in a lightweight manner.
+
+\RC{In Figure~\ref{fig:error}, Ensemble Classifier has been used with all the previsou steganalizers with 3 different payloads. It can be observed that with important payload, STABYLO is not efficient, but as mentionned its complexity is far more simple compared to other tools.\\
+\begin{figure}
+\begin{center}
+\includegraphics[scale=0.5]{error}
+\end{center}
+\caption{Error obtained by Ensemble classifier with WOW/UNIWARD, HUGO, and STABYLO and different paylaods.}
+\label{fig:error} 
+\end{figure}
+}