--- a/writeup/ml.bib	Thu Apr 29 17:21:48 2010 -0400
+++ b/writeup/ml.bib	Thu Apr 29 18:26:30 2010 -0400
@@ -25691,3 +25691,31 @@
 publisher = {IEEE Computer Society},
 address = {Los Alamitos, CA, USA},
 }
+
+
+@inproceedings{SimardSP03,
+  author    = {Patrice Simard and
+               David Steinkraus and
+               John C. Platt},
+  title     = {Best Practices for Convolutional Neural Networks Applied
+               to Visual Document Analysis},
+  booktitle = {ICDAR},
+  year      = {2003},
+  pages     = {958-962},
+  ee        = {http://csdl.computer.org/comp/proceedings/icdar/2003/1960/02/196020958abs.htm},
+  crossref  = {DBLP:conf/icdar/2003},
+  bibsource = {DBLP, http://dblp.uni-trier.de}
+}
+
+@proceedings{DBLP:conf/icdar/2003,
+  title     = {7th International Conference on Document Analysis and Recognition
+               (ICDAR 2003), 2-Volume Set, 3-6 August 2003, Edinburgh,
+               Scotland, UK},
+  booktitle = {ICDAR},
+  publisher = {IEEE Computer Society},
+  year      = {2003},
+  isbn      = {0-7695-1960-1},
+  bibsource = {DBLP, http://dblp.uni-trier.de}
+}
+
+

--- a/writeup/techreport.tex	Thu Apr 29 17:21:48 2010 -0400
+++ b/writeup/techreport.tex	Thu Apr 29 18:26:30 2010 -0400
@@ -93,7 +93,7 @@
 
 \subsection{Local Elastic Deformations}
 
-This filter induces a "wiggly" effect in the image. The description here will be brief, as the algorithm follows precisely what is described in .
+This filter induces a "wiggly" effect in the image. The description here will be brief, as the algorithm follows precisely what is described in \cite{SimardSP03}.
 
 The general idea is to generate two "displacements" fields, for horizontal and vertical displacements of pixels. Each of these fields has the same size as the original image.
 
@@ -119,7 +119,9 @@
 
 This is another GIMP filter we used. The filter is in fact named "Whirl and pinch", but we don't use the "whirl" part (whirl is set to 0). As described in GIMP, a pinch is "similar to projecting the image onto an elastic surface and pressing or pulling on the center of the surface".
 
-Mathematically, think of drawing a circle of radius $r$ around a center point $C$. Any point (pixel) $P$ belonging to that disk (region inside circle) will have its value recalculated by taking the value of another "source" pixel in the original image. The position of that source pixel is found on the line thats goes through $C$ and $P$, but at some other distance $d_2$. Define $d_1$ to be the distance between $P$ and $C$. $d_2$ is given by $d_2 = sin(\frac{\pi{}d_1}{2r})^{-pinch}$, where $pinch$ is a parameter to the filter. 
+Mathematically, for a square input image, think of drawing a circle of radius $r$ around a center point $C$. Any point (pixel) $P$ belonging to that disk (region inside circle) will have its value recalculated by taking the value of another "source" pixel in the original image. The position of that source pixel is found on the line thats goes through $C$ and $P$, but at some other distance $d_2$. Define $d_1$ to be the distance between $P$ and $C$. $d_2$ is given by $d_2 = sin(\frac{\pi{}d_1}{2r})^{-pinch} \times d_1$, where $pinch$ is a parameter to the filter. 
+
+If the image is not square
 
 The actual value is given by bilinear interpolation considering the pixels around the (non-integer) source position.
 
@@ -136,11 +138,11 @@
 
 The next step is to select a destination position in the occluded image. Vertical and horizontal displacements $y\_arrivee$ and $x\_arrivee$ are selected according to Gaussian distributions of mean 0 and of standard deviations of, respectively, 3 and 2. Then an horizontal placement mode, $endroit$ (meaning location), is selected to be of three values meaning left, middle or right.
 
-If $endroit$ is "middle", the occlusion will be horizontally centered around the horizontal middle of the occluded image, then shifted according to $x_\arrivee$. If $endroit$ is "left", it will be placed on the left of the occluded image, then displaced right according to $x_\arrivee$. The contrary happens if $endroit$ is $right$.
+If $endroit$ is "middle", the occlusion will be horizontally centered around the horizontal middle of the occluded image, then shifted according to $x\_arrivee$. If $endroit$ is "left", it will be placed on the left of the occluded image, then displaced right according to $x\_arrivee$. The contrary happens if $endroit$ is $right$.
 
 In both the horizontal and vertical positionning, the maximum position in either direction is such that the selected occlusion won't go beyond the borders of the occluded image.
 
-This filter has a probability of not being applied, at all, of 60%.
+This filter has a probability of not being applied, at all, of 60\%.
 
 \subsection{Background Images}