Answers: second synthetic image added

Expes/Analyses/PerfSynth/essaiRandom2/readme.txt

+Random shot data published on github. July 6th, 2019.
+randimage_noframe.png -> Images/randimage2.png
+randout_old_noframe.png -> Images/randold2.png
+randout_new_noframe.png -> Images/randnew2.png
+
+Obtention :
+- Ctrl-E to detect both line sides
+- w -> 7 to set the initial assigned thickness
+- g -> 50 to set the gradient threshold (sensitivity)
+- m to detect the segments
+- Ctrl-B to set a whte background
+- c to paint segments in black
+- d to display the DSS
+- Ctrl X to switch between new and old detectors (ADS and ATC)
+- P to grab the image
+- selection of 256x256 windows starting from (10,10) point to remove frame

Expes/Analyses/PerfSynth/essaiRandom6/randin.txt

+10
+124 245
+257 42
+4
+53 192
+62 158
+4
+204 147
+20 166
+3
+191 190
+74 201
+3
+148 229
+76 254
+3
+99 97
+211 48
+4
+110 246
+127 78
+2
+179 34
+214 167
+3
+22 102
+66 194
+3
+46 32
+105 133
+2

Expes/Analyses/PerfSynth/essaiRandom6/randout_new.txt

+56 segment searches (local min)
+16 provided segments
+10 provided long segments
+0 undetected segments
+0.0108273 % of points found more than once (redetections)
+0.0957801 % of false points produced
+0.903926 : precision
+0.901166 : recall
+0.902544 : F-measure
+4.25583 : Biased width / matched segment
+3.0257 : Width / matched segment
+0.229201 : Width difference / matched segment
+0.455418 : Absolute width difference / matched segment
+0.556786 : Angle difference / matched segment
+0.667906 : Absolute angle difference / matched segment
+0.10276 : Absolute long edge angle difference / matched segment

Expes/Analyses/PerfSynth/essaiRandom6/randout_old.txt

+51 segment searches (local min)
+17 provided segments
+9 provided long segments
+0 undetected segments
+0.00444198 % of points found more than once (redetections)
+0.155469 % of false points produced
+0.852825 : precision
+0.900888 : recall
+0.876198 : F-measure
+4.19938 : Biased width / matched segment
+2.98413 : Width / matched segment
+0.2336 : Width difference / matched segment
+0.527664 : Absolute width difference / matched segment
+-0.0733165 : Angle difference / matched segment
+0.155291 : Absolute angle difference / matched segment
+0.044027 : Absolute long edge angle difference / matched segment

Expes/Analyses/PerfSynth/essaiRandom7/randin.txt

+10
+86 41
+109 232
+4
+217 62
+65 25
+3
+247 66
+81 97
+4
+71 36
+64 84
+4
+193 88
+119 156
+3
+218 122
+175 109
+2
+230 124
+180 36
+4
+251 123
+42 143
+4
+169 169
+173 231
+2
+226 99
+233 31
+4

Expes/Analyses/PerfSynth/essaiRandom7/randout_new.txt

+66 segment searches (local min)
+19 provided segments
+11 provided long segments
+0 undetected segments
+0.0464396 % of points found more than once (redetections)
+0.0632095 % of false points produced
+0.933604 : precision
+0.888803 : recall
+0.910653 : F-measure
+4.65694 : Biased width / matched segment
+3.36998 : Width / matched segment
+0.188391 : Width difference / matched segment
+0.478199 : Absolute width difference / matched segment
+-0.101964 : Angle difference / matched segment
+0.421574 : Absolute angle difference / matched segment
+0.320088 : Absolute long edge angle difference / matched segment

Expes/Analyses/PerfSynth/essaiRandom7/randout_old.txt

+63 segment searches (local min)
+18 provided segments
+11 provided long segments
+0 undetected segments
+0.0779154 % of points found more than once (redetections)
+0.0694014 % of false points produced
+0.927824 : precision
+0.892157 : recall
+0.909641 : F-measure
+4.69488 : Biased width / matched segment
+3.3468 : Width / matched segment
+0.104756 : Width difference / matched segment
+0.333628 : Absolute width difference / matched segment
+-0.00859411 : Angle difference / matched segment
+0.453103 : Absolute angle difference / matched segment
+0.184265 : Absolute long edge angle difference / matched segment

Expes/Analyses/PerfSynth/essaiRandom8/randin.txt

+10
+81 245
+212 103
+4
+30 214
+101 16
+4
+158 241
+132 45
+4
+210 207
+46 126
+3
+158 230
+53 250
+3
+85 19
+14 27
+2
+250 208
+45 55
+2
+62 85
+233 94
+2
+243 217
+161 39
+2
+101 187
+161 222
+3

Expes/Analyses/PerfSynth/essaiRandom8/randout_new.txt

+66 segment searches (local min)
+23 provided segments
+17 provided long segments
+0 undetected segments
+0.00754717 % of points found more than once (redetections)
+0.141038 % of false points produced
+0.868802 : precision
+0.933962 : recall
+0.900205 : F-measure
+4.2323 : Biased width / matched segment
+2.99502 : Width / matched segment
+0.309035 : Width difference / matched segment
+0.455026 : Absolute width difference / matched segment
+-0.00370164 : Angle difference / matched segment
+0.138019 : Absolute angle difference / matched segment
+0.0851053 : Absolute long edge angle difference / matched segment

Expes/Analyses/PerfSynth/essaiRandom8/randout_old.txt

+74 segment searches (local min)
+25 provided segments
+17 provided long segments
+0 undetected segments
+0.0160377 % of points found more than once (redetections)
+0.126887 % of false points produced
+0.878032 : precision
+0.913443 : recall
+0.895388 : F-measure
+4.21463 : Biased width / matched segment
+2.94276 : Width / matched segment
+0.245262 : Width difference / matched segment
+0.436874 : Absolute width difference / matched segment
+0.119276 : Angle difference / matched segment
+0.274648 : Absolute angle difference / matched segment
+0.0945319 : Absolute long edge angle difference / matched segment

Expes/Analyses/PerfSynth/essaiRandom9/randin.txt

+10
+190 68
+91 181
+2
+262 65
+236 65
+3
+95 243
+56 102
+3
+103 138
+125 64
+4
+14 65
+261 222
+2
+246 167
+91 136
+3
+256 217
+213 216
+4
+33 172
+165 108
+3
+31 217
+29 96
+3
+99 50
+73 72
+2

Expes/Analyses/PerfSynth/essaiRandom9/randout_new.txt

+52 segment searches (local min)
+17 provided segments
+11 provided long segments
+0 undetected segments
+0.0197574 % of points found more than once (redetections)
+0.231889 % of false points produced
+0.792622 : precision
+0.886308 : recall
+0.836852 : F-measure
+4.5881 : Biased width / matched segment
+3.30876 : Width / matched segment
+0.374577 : Width difference / matched segment
+0.825649 : Absolute width difference / matched segment
+-0.523699 : Angle difference / matched segment
+0.928925 : Absolute angle difference / matched segment
+0.159961 : Absolute long edge angle difference / matched segment

Expes/Analyses/PerfSynth/essaiRandom9/randout_old.txt

+57 segment searches (local min)
+16 provided segments
+11 provided long segments
+0 undetected segments
+0.0187175 % of points found more than once (redetections)
+0.342461 % of false points produced
+0.719955 : precision
+0.880416 : recall
+0.792141 : F-measure
+4.82581 : Biased width / matched segment
+3.56485 : Width / matched segment
+0.556491 : Width difference / matched segment
+1.15398 : Absolute width difference / matched segment
+-0.835981 : Angle difference / matched segment
+1.283 : Absolute angle difference / matched segment
+0.511458 : Absolute long edge angle difference / matched segment

Methode/answerToReview.tex

@@ -34,7 +34,8 @@ We would like to thank the editors and reviewers for their work and
 for their constructive comments, questions and suggestions.
 Because the paper already reaches the 10 pages limit, and in order to
 avoid removal of possibly valuable contents for paper understanding,
-additional data are put on the github, that is referenced in the paper.
+additional data are put on the github, that is referenced in the paper
+({\tt https://github.com/evenp/FBSD}).
 A detailed list of the changes is given below with also some specific
 answers to raised questions.
 {\color{blue} \bf Our paper is attached to our answer and the proposed
@@ -95,11 +96,6 @@ Moreover, the code is written in Matlab. To ensure a fair comparison of time
 performance, it would require a complete re-programming in C-like language,
 that could produce possible rewritting bias. \\
 We briefly mention it at the beginning of section 4.
-\begin{todo}
-Done.
-Par contre pour que \c ca rentre adns les 11 pages, j'ai du sabrer la fin
-du paragraphe au dessus du tableau 1.
-\end{todo}
 \end{answer}
 
 Some notes are as belows:
@@ -117,9 +113,6 @@ observed line. \\
 The text was changed to precise the role of this half pixel margin.
 But of course, we have no space left to discuss all these discrete geometry
 considerations in the paper.
-\begin{todo}
-Done
-\end{todo}
 \end{answer}
 
 \item Could the authors present a couple of example for sythesized images
@@ -127,14 +120,11 @@ that were used in the experiments and the performance of both versions of
 the method obtained on them ?
 \begin{answer}
 Due to page limitations, we could not add any figure nor respective
-performance result in the paper. However, an example of synthesized image is
-already available in the mentioned github, and we have completed the
-table with associated results. Accordingly to the measured standard deviations
-obtained on the whole set of 1000 randomly generated images, observed results
-on individual images can largely change.
-\begin{todo}
-Done. Second example ?
-\end{todo}
+performance result in the paper. However, a couple of examples of synthesized
+images is already available in the mentioned github, and we have completed the
+table with associated results. In accordance to the measured standard
+deviations obtained on the whole set of 1000 randomly generated images,
+large variations can be observed in such results on individual images.
 \end{answer}
 
 \item What is understood from the paper is the performance results presented
@@ -158,9 +148,6 @@ assuming that achieved performance on all segments also impact the manual
 detection of one or several line segments. \\
 A sentence was added at the end of first paragraph of section 3.5 to refer
 to the former paper for more details on the supervised mode.
-\begin{todo}
-Done.
-\end{todo}
 \end{answer}
 
 \item It is not clearly mentioned and justified why the initial thickness
@@ -180,9 +167,6 @@ The other detectors aim at providing thin lines and may reject too
 scattered image lines. To adapt to this behavior, we retrict the detection
 to thin lines using the initial assigned thickness to 3 pixels. \\
 The text of the paper has been precised accordingly.
-\begin{todo}
-Done.
-\end{todo}
 \end{answer}
 
 \item I would like to see the performance of the previous version of the
@@ -199,9 +183,6 @@ We notice that achieved values have less meaning here, because as explained
 in the paper, the lines detected by the former method are more likely to
 incorporate spurious points, that artificially grow the width and length
 values.
-\begin{todo}
-Done.
-\end{todo}
 \end{answer}
 
 \item I would suggest to the authors to give the reference numbers for the
@@ -211,9 +192,6 @@ better to refer to the methods with citing those papers at the caption of
 Table 2.
 \begin{answer}
 Thanks for this relevant suggestion. The caption is now completed.
-\begin{todo}
-Done.
-\end{todo}
 \end{answer}
 \end{itemize}
 \end{itemize}