diff --git a/Article/Expe_auto/compTable.tex b/Article/Expe_auto/compTable.tex
index e779148ff6f78d4bd7037c0f87c43c5fe19c6607..2dd1069b2d63787eec2e55eb26f0166f4d727069 100644
--- a/Article/Expe_auto/compTable.tex
+++ b/Article/Expe_auto/compTable.tex
@@ -14,7 +14,7 @@ CannyLines
& 75.5 & 11.7 & 60.6 & 10.6
& 467 & 139 & 17678 & 4419 & 39.5 & 10.2 \\
Our detector
-& 66.6 & 14.8 & 65.8 & 9.3
+& 66.6 & 14.8 & \textbf{65.8} & \textbf{9.3}
& 524 & 119 & 19210 & 3797 & 37.4 & 5.9 \\
\hline
\end{tabular}
diff --git a/Article/Fig_synth/statsTable.tex b/Article/Fig_synth/statsTable.tex
index 33c04ff99e32aa8c793db115502d02eed990a2bf..62c08f1ba1aa6838cc01072b5f142ff724650939 100644
--- a/Article/Fig_synth/statsTable.tex
+++ b/Article/Fig_synth/statsTable.tex
@@ -7,16 +7,16 @@ Detected blurred segments per image
Detected long (> 40 pixels) blurred segments per image
& 10.41 & $\pm$ & 1.84 & 11.14 & $\pm$ & 1.92 \\
Undetected input segments per image
-& 2.53 & $\pm$ & 2.54 & 0.64 & $\pm$ & 0.91 \\
+& 2.53 & $\pm$ & 2.54 & \textbf{0.64} & $\pm$ & \textbf{0.91} \\
Precision (\%) : $P = \#(D\cap S)/\#D$
-& 72.76 & $\pm$ & 9.69 & 79.19 & $\pm$ & 6.30 \\
-Recall (ratio of true detection) (\%) : $R = \#(D\cap S)/\#S$
-& 89.20 & $\pm$ & 3.94 & 90.08 & $\pm$ & 2.77 \\
-F-measure (harmonic mean) (\%) : $F = 2\times P\times R/(P+R)$
-& 79.85 & $\pm$ & 6.78 & 84.17 & $\pm$ & 4.17 \\
+& 72.76 & $\pm$ & 9.69 & \textbf{79.19} & $\pm$ & \textbf{6.30} \\
+Recall (ratio of true detection, \%): $R = \#(D\cap S)/\#S$
+& 89.20 & $\pm$ & 3.94 & \textbf{90.08} & $\pm$ & \textbf{2.77} \\
+F-measure (harmonic mean,\%): $F = 2\times P\times R/(P+R)$
+& 79.85 & $\pm$ & 6.78 & \textbf{84.17} & $\pm$ & \textbf{4.17} \\
Width difference (in pixels) to matched input segment
-& 0.92 & $\pm$ & 0.31 & 0.76 & $\pm$ & 0.23 \\
+& 0.92 & $\pm$ & 0.31 & \textbf{0.76} & $\pm$ & \textbf{0.23} \\
Angle difference (in degrees) to matched input segment
-& 1.48 & $\pm$ & 1.42 & 1.05 & $\pm$ & 0.80 \\
+& 1.48 & $\pm$ & 1.42 & \textbf{1.05} & $\pm$ & \textbf{0.80} \\
\hline
\end{tabular}
diff --git a/Article/abstract.tex b/Article/abstract.tex
index c1742d750250d6579abec0085dc3920a93bcf5c8..63b48cfe0b18c354304c7aee5d175121c2fc64a4 100755
--- a/Article/abstract.tex
+++ b/Article/abstract.tex
@@ -2,9 +2,9 @@
detector in gray-level images,
where line segments are enriched with a thickness parameter
intended to provide a quality criterion on the extracted feature.
-This study enhances previous works on interactive
+This study firstly enhances previous works on interactive
line detection with a better estimation of the segment width and
orientation through two main improvements: adaptive directional scans and
the control of the assigned width to the detection algorithm.
-A new contribution to the automatic detection of all the segments in a single
+Then, a new contribution to the automatic detection of all the segments in a single
image is also proposed and left available in an online demonstration.
diff --git a/Article/conclusion.tex b/Article/conclusion.tex
index 2ff83218a902eb702fbc326c623fe1c09706a5f0..fe06c83330c923e2ea45e244514ef9378c7074e0 100755
--- a/Article/conclusion.tex
+++ b/Article/conclusion.tex
@@ -22,8 +22,8 @@ control of the assigned width based on the observation of the
blurred segment growth.
Experiments on synthetic images show the better performance
and especially the more accurate estimation of the line width brought by
-these concepts.
-Moreover the performance is quite comparable to other recent edge detectors.
+these concepts. Such an result can not be compared to other approach since they do not provide any width estimation.
+Moreover the performance of the unsupervised mode give better coverage of the detected edges and produce quite comparable execution time.
A residual weakness of the approach is the sensitivity to the initial
conditions.
diff --git a/Article/introV2.tex b/Article/introV2.tex
index 3bbc5fcf3c46a6ee30140165b3917d0f2b621132..aba20e58d2bee833cb8fb32caef57c20abb54615 100755
--- a/Article/introV2.tex
+++ b/Article/introV2.tex
@@ -2,10 +2,10 @@
\label{sec:intro}
-Straight lines are commonly used visual features for many image analysis
+Straight lines are commonly used as visual features for many image analysis
processes.
For instance in computer vision, they are used to estimate the vanishing
-points associated to main directions of the 3D world, thus allowing camera
+points associated to main directions of the 3D world, thus allowing to compute camera
orientation. They are also used to detect structured features for
3D reconstruction.
@@ -55,9 +55,9 @@ but the segment width was initially fixed by the user and not estimated,
leading to erroneous orientations of the detected lines.
In the present work, the limitations of this first detector were solved
by the introduction of two new concepts:
-(i) {\bf adaptive directional scan} designed to get some
+(i) adaptive directional scan designed to get some
compliance to the unpredictable orientation problem;
-(ii) {\bf control of the assigned width} to the blurred segment
+(ii) control of the assigned width to the blurred segment
recognition algorithm, intended to derive more reliable information on the
line orientation and quality.
As a side effect, these two major evolutions also led to a noticeable
diff --git a/Article/main.tex b/Article/main.tex
index 2e223fe720f9c22a2ca80a0c18c655238f60c6cd..b95e82bc8149929bef6d2a78b620990d7992b194 100755
--- a/Article/main.tex
+++ b/Article/main.tex
@@ -26,8 +26,9 @@
\begin{frontmatter}
% \title{Straight edge detection
% based on adaptive directional tracking of blurred segments}
- \title{Fast Directional Tracking of Thick Line Segments}
-
+%% \title{Fast Directional Tracking of Thick Line Segments}
+ %% Proposition BK:
+ \title{Thick Line Segments Detection with Fast Directional Tracking}
\author{Philippe Even\inst{1} \and
Phuc Ngo\inst{1} \and
Bertrand Kerautret\inst{2}}
diff --git a/Article/methodV2.tex b/Article/methodV2.tex
index 3ff5ec2b812b759738b0298e7da579dd8c9efda3..204d4c8ff0f3c859e05fb177ba668129e9187f79 100755
--- a/Article/methodV2.tex
+++ b/Article/methodV2.tex
@@ -160,7 +160,7 @@ a director vector and a width observed at iteration $i$.
In the scope of the present detector, $C_{i-1}$ is the intersection of
the input selection and the central line of $\mathcal{B}_{i-1}$,
$\vec{D}_{i-1}$ the support vector of the enclosing digital segment
-$E(\mathcal{B}_{i-1})$, and $w_{i-1}$ a value slightly greater than the
+$\mathcal{B}_{i-1}$, and $w_{i-1}$ a value slightly greater than the
minimal width of $\mathcal{B}_{i-1}$.
So the last clause expresses the update of the scan bounds at iteration $i$.
Compared to static directional scans where the scan strip remains fixed to
@@ -268,7 +268,7 @@ $2~\varepsilon_{ini}$, and $M_j$ is used as start point of the blurred
segment;
\item the occupancy mask is filled in with the points of the dilated blurred
segments $\mathcal{B}_j'$ at the end of each successful detection
-(a 21 pixels neighborhood is used);
+(a $5 \times 5$ octogonal neighborhood region of 21 pixels is used);
\item points marked as occupied are rejected when selecting candidates for the
blurred segment extension in the fine tracking step.
\end{enumerate}
@@ -285,7 +285,7 @@ swept in both directions, vertical then horizontal, from the center to
the borders. At each position, the multi-detection algorithm is run
to collect all the segments found under the stroke.
Then small blurred segments are rejected in order to avoid the formation
-of mis-aligned segments when the sweeping stroke crosses an image edge
+of misaligned segments when the sweeping stroke crosses an image edge
near one of its ends.
In such situation, any nearby disturbing gradient is likely to deviate
the blurred segment direction, and its expansion is quickly stopped.
diff --git a/Article/notions.tex b/Article/notions.tex
index 0830d85c8bbeb0a07d34bdb196df96f2fefadeb6..f2e631180848faf9ee7a0320a02ba2bfee95dbe3 100755
--- a/Article/notions.tex
+++ b/Article/notions.tex
@@ -29,7 +29,7 @@ $\mathcal{L}$ of arithmetical width $w(\mathcal{L}) = \varepsilon$.
\end{definition}
A linear-time algorithm to recognize a blurred segment of assigned width
-$\varepsilon$ \cite{DebledAl05} is used in the work.
+$\varepsilon$ \cite{DebledAl05} is used in this work.
It is based on an incremental growth of the convex hull of the blurred
segment when adding each point $P_i$ successively.
The minimal width $\mu$ of the blurred segment $\mathcal{B}$ is the
@@ -56,7 +56,7 @@ and $\mathcal{B}_i = \mathcal{B}_{i-1}$.}
\end{figure}
Associated to this primitive, the following definition of a directional scan
-based on digital straight lines is used in this work.
+ is an important point the proposed method.
\subsection{Directional scan}
@@ -163,6 +163,6 @@ $\mathcal{N}_i^{C,\vec{D},w}$:
\mathcal{D}^{C,\vec{D},w}
= \mathcal{L}(Y_D,~ -X_D,~ c_3 - w / 2,~ w) \\
\mathcal{N}_i^{C,\vec{D},w} = \mathcal{L}(X_D,~ Y_D,~
- c_4 - w / 2 + i\cdot w,~ \nu_{\vec{D}}
+ c_4 - w / 2 + i\cdot w,~ \nu_{\vec{D}})
\end{array} \right.
\end{equation}