integration des remarques des reviewer en vert

diff --git a/biblioand.bib b/biblioand.bib
index d37cf9d89c3d7a8e9c00bc766bffd19bc05828f3..9d1171e9a0e811847815cd804decb3681e238c40 100644 (file)
--- a/biblioand.bib
+++ b/biblioand.bib
@@ -1396,3 +1396,16 @@ keywords = "Fuzzy edge detector"
 }
 
 
 }
 
 

+
+
+@inproceedings{DBLP:dblp_conf/mediaforensics/KodovskyPF10,
+   author              = {Jan Kodovský and 
+                          Tomás Pevný and 
+                          Jessica J. Fridrich},
+   title               = {Modern steganalysis can detect YASS.},
+   booktitle           = {Media Forensics and Security},
+   year                = {2010},
+   pages               = {754102},
+   ee                  = {http://dx.doi.org/10.1117/12.838768}
+}
+

diff --git a/experiments.tex b/experiments.tex
index 22900c0ec35afc7f4a5dc8937e27b2da0e0110f7..61d2971c734c41e789c2f37229ca282a67b53b58 100644 (file)
--- 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.
 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 one 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 
 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 

diff --git a/ourapproach.tex b/ourapproach.tex
index f9ca3d15a0b5660ee9e12ef69b117262d8bbbf49..534fb29fc23e96d7d6925ad413bdb8243aae41a8 100644 (file)
--- a/ourapproach.tex
+++ b/ourapproach.tex
@@ -48,6 +48,8 @@ Let us first focus on the data embedding.
 
 
 \subsection{Security considerations}\label{sub:bbs}
 
 
 \subsection{Security considerations}\label{sub:bbs}

+\JFC{To provide a self-contained article without any bias, we shortly 
+pressent the retained encryption process.}

 Among the methods of  message encryption/decryption 
 (see~\cite{DBLP:journals/ejisec/FontaineG07} for a survey)
 we implement the asymmetric 
 Among the methods of  message encryption/decryption 
 (see~\cite{DBLP:journals/ejisec/FontaineG07} for a survey)
 we implement the asymmetric 

diff --git a/stc.tex b/stc.tex
index 8da157375145ff05382bc63829c4ab9e21300acc..c195fca622c7d3284ce7f78893c0249f84249890 100644 (file)
--- a/stc.tex
+++ b/stc.tex
@@ -1,5 +1,6 @@
 To make this article self-contained, this section recalls
 To make this article self-contained, this section recalls

-the basis of the Syndrome Treillis Codes  (STC).
+the basis of the Syndrome Treillis Codes  (STC). 
+\JFC{A reader that is familar with syndrome coding can skip it.}

 
 Let 
 $x=(x_1,\ldots,x_n)$ be the $n$-bits cover vector issued from an image $X$, 
 
 Let 
 $x=(x_1,\ldots,x_n)$ be the $n$-bits cover vector issued from an image $X$,