WIP added INF574 project

Author: 3rdCore

data/INF574.pdf

@@ -232,20 +232,26 @@ <h2>News</h2>
 
 		</td>
 	</tr>
-	<td width="25%" valign="center" align="center"><img src="" alt="nthu" width="140" height="150"></td>
+	<td width="25%" valign="center" align="center"><img src="images/sketch.png" alt="nthu" width="180" height="180"></td>
 		<td style="padding:20px;width:75%;vertical-align:middle">
-		<a class="tog" href="" target="_blank">
+		<a class="tog" href="https://github.com/3rdCore/Shape_Retrieval/" target="_blank">
 			<papertitle>Sketch-based Shape Retrieval</papertitle>
 		</a>
 		<br>
 		Sep' 20 – Dec' 20
 		<br>
 		<br>
-		To Complete
+		The objective of our project is to enable an efficient search in a 3D model bank models from simple hand drawings. The project is based on <a class="tog" href="https://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=&ved=2ahUKEwjR2cDUto36AhXUGlkFHaB1A5wQFnoECA0QAQ&url=https%3A%2F%2Fcybertron.cg.tu-berlin.de%2Feitz%2Fpdf%2F2012_siggraph_sbsr.pdf&usg=AOvVaw1ubNbM8eL7juourwr9P-9N" target="_blank">this paper</a> SIGGRAPH2012. 
 		<br>
 		<br>
-		<p></p>
-		
+		The project lies on differents techniques such Suggestive Contouring (Canny filter), Gabor filtering (gaussian convolution on Fourier Transformation of the input image) and histogram representation using Visual Vocabulary. 
+		<br>
+		Looking back at this project, I saw that <a class="tog" href="https://arxiv.org/abs/1504.03504" target="_blank">another paper</a> with much more impressive results came out a few years later using <strong>Siamese convolutional Neural Networks</strong> for feature extraction. 
+		<br>
+		<p style="padding:0%;text-align:center">
+			<a href="data/INF574.pdf" target="_blank">Report</a> &nbsp/&nbsp
+			<a href="https://github.com/3rdCore/Shape_Retrieval/" target="_blank">GitHub</a>
+		  </p>		
 		</td>
 	</tr>