mirror of
https://github.com/jlengrand/jlengrand.github.io.git
synced 2026-03-10 08:31:22 +00:00
Removes all dropbox public links from the blog
This commit is contained in:
jll
@@ -192,7 +192,7 @@ A word about <a title="REGION_GROWING" href="http://en.wikipedia.org/wiki/Region
|
||||
|
||||
This approach to segmentation examines neighboring pixels of initial “seed points” and determines whether the pixel neighbors should be added to the region. The process is iterated on, in the same manner as general data clustering algorithms"
|
||||
Basically, region growing is an<strong> iterative method used to extract similar parts of an image</strong>. One or several points are chosen as a start. The region then grows until it is finally blocked by the<strong> stop criteria</strong>. This criteria is generally an inside/outside region comparison (energy, size, . . .).
|
||||
Region growing is massively used in medical imaging, and object detection. <a title="mine_hunting ECUA" href="http://dl.dropbox.com/u/4286043/00_Website/01_Publis/ATR_TNO_ECUA.pdf" target="_blank">Here is an example of application in automatic <strong>Mine Hunting</strong></a>, which I worked with last year at <a title="TNO" href="http://www.tno.nl/" target="_blank">TNO</a>.
|
||||
Region growing is massively used in medical imaging, and object detection. <a title="mine_hunting ECUA" href="https://drive.google.com/open?id=0B4bXocpgiAyxY1I3d2lIR2tvSHcf" target="_blank">Here is an example of application in automatic <strong>Mine Hunting</strong></a>, which I worked with last year at <a title="TNO" href="http://www.tno.nl/" target="_blank">TNO</a>.
|
||||
|
||||
The following method uses one seed point, defined by the user. The region grows by comparing with its neighbourhood. The chosen criteria is in this case a difference between outside pixel's intensity value and the region's mean.
|
||||
The pixel with minimum intensity in the region neighbouhood is chosen to be included. The growing stops as soon as the difference is larger than a threshold.
|
||||
|
||||
@@ -49,7 +49,7 @@ Hi all,
|
||||
|
||||
<strong>Long time no see !</strong>
|
||||
I stayed silent those last days for the simple reason that I relocated to the Netherlands.
|
||||
Two years ago, I spent some months working at <strong><a title="TNO website" href="http://www.tno.nl/index.cfm?Taal=2" target="_blank">TNO</a></strong> in underwater mine recognition. The internship took place in <a title="The Hague wiki" href="http://en.wikipedia.org/wiki/The_Hague" target="_blank">The Hague</a> and I discovered how fascinating life could be outside of your native country.I should write more soon about <a title="ECUA ATR" href="http://dl.dropbox.com/u/4286043/215.pdf" target="_blank">the results of this project</a>:).
|
||||
Two years ago, I spent some months working at <strong><a title="TNO website" href="http://www.tno.nl/index.cfm?Taal=2" target="_blank">TNO</a></strong> in underwater mine recognition. The internship took place in <a title="The Hague wiki" href="http://en.wikipedia.org/wiki/The_Hague" target="_blank">The Hague</a> and I discovered how fascinating life could be outside of your native country.I should write more soon about <a title="ECUA ATR" href="https://drive.google.com/open?id=0B4bXocpgiAyxY1I3d2lIR2tvSHc" target="_blank">the results of this project</a>:).
|
||||
|
||||
Back in France, I realized that each day I was missing international life more and more and my girlfriend and me finally took the decision to relocate abroad as soon as possible
|
||||
|
||||
|
||||
@@ -153,7 +153,7 @@ As a researcher, part of your job consists in being an expert in your field and
|
||||
Basically speaking, <strong><a title="mendeley" href="http://www.mendeley.com/" target="_blank">Mendeley</a></strong> is a publication management tool. It would help you keep track of your publications by extracting meda-data from the pdfs, and sort them out for you. For each document, you can access its authors, abstract, . . . And you can also set these meta-data and add keywords or tags.
|
||||
While keywords are often already filled by the authors of the pdfs, <strong>tags have become my very secret weapon</strong>.
|
||||
|
||||
<center><a href="http://dl.dropbox.com/u/4286043/mendeley.jpg"><img class=" " title="mendeley desktop" src="http://dl.dropbox.com/u/4286043/mendeley.jpg" alt="mendeley desktop" width="552" height="301" /></a></center>
|
||||
<center><a href="https://drive.google.com/open?id=0B4bXocpgiAyxQ01JZW9ZWWE2V1U"><img class=" " title="mendeley desktop" src="https://drive.google.com/open?id=0B4bXocpgiAyxQ01JZW9ZWWE2V1U" alt="mendeley desktop" width="552" height="301" /></a></center>
|
||||
|
||||
There are<strong> 3 major things</strong> I want to show you here that can help you efficiently handle tons of information.
|
||||
|
||||
|
||||
@@ -42,17 +42,17 @@ In this paper, I present a new method that merge a <strong>feature based class
|
||||
As a basis for the region based algorithm, I used the<a title="level sets wikipedia" href="http://en.wikipedia.org/wiki/Level_set_method" target="_blank"> level-sets method</a>.
|
||||
With one part of the algorithm searching for homogen zones and the other searching for limits, one can hope to get nice results once merged !
|
||||
|
||||
<strong><a title="GESMA_EGC" href="http://dl.dropbox.com/u/4286043/00_Website/01_Publis/Fusion_GESMA_EGC.pdf" target="_blank">Here is a link</a></strong> to the french version of the paper, presented at the <a title="EGC2010" href="http://www.projets.rnu.tn/egc2010/" target="_blank">"10ème Conférence Internationale Francophone sur l'Extraction et la Gestion des Connaissances (EGC)"</a>
|
||||
<strong><a title="GESMA_EGC" href="https://drive.google.com/open?id=0B4bXocpgiAyxN05ycllBT1RMOEk" target="_blank">Here is a link</a></strong> to the french version of the paper, presented at the <a title="EGC2010" href="http://www.projets.rnu.tn/egc2010/" target="_blank">"10ème Conférence Internationale Francophone sur l'Extraction et la Gestion des Connaissances (EGC)"</a>
|
||||
|
||||
<strong><a title="GESMA_ECUA" href="http://dl.dropbox.com/u/4286043/00_Website/01_Publis/Fusion_GESMA_ECUA.pdf" target="_blank">The english version</a></strong> was presented one year later at<a title="ECUA 2010" href="http://www.eaa-fenestra.org/event-calendar/list_of_events/2010/event.2009-06-30" target="_blank"> "10th European Conference on Underwater Acoustics (ECUA) 2010"</a>.
|
||||
<strong><a title="GESMA_ECUA" href="https://drive.google.com/open?id=0B4bXocpgiAyxMmxoelY4Y0Vpdm8" target="_blank">The english version</a></strong> was presented one year later at<a title="ECUA 2010" href="http://www.eaa-fenestra.org/event-calendar/list_of_events/2010/event.2009-06-30" target="_blank"> "10th European Conference on Underwater Acoustics (ECUA) 2010"</a>.
|
||||
Just for the beauty of it, I want to quickly present some results :
|
||||
Here is an example of sonar image manually segmented by two different experts. Observe how the results are similar, but also different at the same time.
|
||||
|
||||
<center><a href="http://dl.dropbox.com/u/4286043/expert.png"><img class="aligncenter" src="http://dl.dropbox.com/u/4286043/expert.png" alt="" border="0" /></a></center>
|
||||
<center><a href="https://drive.google.com/open?id=0B4bXocpgiAyxcEpIazJyMk5mb3M"><img class="aligncenter" src="https://drive.google.com/open?id=0B4bXocpgiAyxcEpIazJyMk5mb3M" alt="" border="0" /></a></center>
|
||||
|
||||
Here are the results I got using my fully automated method :
|
||||
|
||||
<center><a href="http://dl.dropbox.com/u/4286043/algo.png"><img class="aligncenter" src="http://dl.dropbox.com/u/4286043/algo.png" alt="" border="0" /></a></center>
|
||||
<center><a href="https://drive.google.com/open?id=0B4bXocpgiAyxWHkyemFBT2VuY28"><img class="aligncenter" src="https://drive.google.com/open?id=0B4bXocpgiAyxWHkyemFBT2VuY28" alt="" border="0" /></a></center>
|
||||
|
||||
Results are actually<strong> quite promising</strong>, given the amount of time I have been working on the subject! (You can have some precise results in the paper)
|
||||
I just hope that this work will be used later and lead to even more interesting results !
|
||||
|
||||
@@ -40,7 +40,7 @@ As an example, the <a title="Cartesian coordinate system" href="https://en.wik
|
||||
|
||||
In <em><a title="Le discours de la méthode" href="https://fr.wikipedia.org/wiki/Discours_de_la_m%C3%A9thode" target="_blank">Le discours de la méthode</a></em> , Descartes describes 4 principles that (in his mind) people should follow to eventually find a solution to their (scientific) problems.
|
||||
|
||||
<img title="Le discours de la méthode" src="https://dl.dropbox.com/u/4286043/00_Website/03_Images/Descartes_Discours_de_la_Methode.jpg" alt="Cover of le discours de la Méthode" width="250" height="340" />
|
||||
<img title="Le discours de la méthode" src="https://drive.google.com/open?id=0B4bXocpgiAyxbjBINnhIblNIVmM" alt="Cover of le discours de la Méthode" width="250" height="340" />
|
||||
|
||||
Here is the <strong>original (and french) version</strong> of those principles:
|
||||
<blockquote>
|
||||
|
||||
@@ -22,7 +22,7 @@ comments: []
|
||||
---
|
||||
A really quick tip today : I am completely fond of <strong><a title="Llama" href="http://www.appbrain.com/app/llama-location-profiles/com.kebab.Llama" target="_blank">Llama </a></strong>on my Android phone.
|
||||
|
||||
<center><img title="Llama application" src="https://dl.dropbox.com/u/4286043/00_Website/03_Images/llama.png" alt="Llama application icon " width="705" height="345" /></center>
|
||||
<center><img title="Llama application" src="https://drive.google.com/open?id=0B4bXocpgiAyxTklldHNIYU8tOGc" alt="Llama application icon " width="705" height="345" /></center>
|
||||
|
||||
Actually, it the very first application I would install on a new device.
|
||||
|
||||
|
||||
@@ -49,7 +49,7 @@ Hopefully, all this work is not lost! The perspective of a contest gave me a big
|
||||
<div></div>
|
||||
<div>
|
||||
|
||||
<center><a href="https://dl.dropbox.com/u/4286043/ivolution_gtk.png"><img title="Ivolution interface" src="https://dl.dropbox.com/u/4286043/ivolution_gtk.png" alt="" width="294" height="547" /></a></center>
|
||||
<center><a href="https://drive.google.com/open?id=0B4bXocpgiAyxbjJGVmY4dnlINlk"><img title="Ivolution interface" src="https://drive.google.com/open?id=0B4bXocpgiAyxbjJGVmY4dnlINlk" alt="" width="294" height="547" /></a></center>
|
||||
|
||||
</div>
|
||||
<div></div>
|
||||
|
||||
Reference in New Issue
Block a user