# HG changeset patch # User Xavier Glorot # Date 1272659357 14400 # Node ID a7fab59de174ac12868434e5616aad7f7775b77d # Parent c06a3d9b5664689a4e4047477f30bcda6716b8c3 change order of transformations diff -r c06a3d9b5664 -r a7fab59de174 writeup/techreport.tex --- a/writeup/techreport.tex Fri Apr 30 16:24:35 2010 -0400 +++ b/writeup/techreport.tex Fri Apr 30 16:29:17 2010 -0400 @@ -118,13 +118,6 @@ $\sigma$ and $\alpha$ were linked to complexity through the formulas $\alpha = \sqrt[3]{complexity} \times 10.0$ and $\sigma = 10 - 7 \times \sqrt[3]{complexity}$. -\subsection{Motion Blur} - -This is a GIMP filter we applied, a "linear motion blur" in GIMP terminology. The description will be brief as it is a well-known filter. - -This algorithm has two input parameters, $length$ and $angle$. The value of a pixel in the final image is the mean value of the $length$ first pixels found by moving in the $angle$ direction. An approximation of this idea is used, as we won't fall onto precise pixels by following that direction. This is done using the Bresenham line algorithm. - -The angle, in our case, is chosen from a uniform distribution over $[0,360]$ degrees. The length, though, depends on the complexity; it's sampled from a Gaussian distribution of mean 0 and standard deviation $\sigma = 3 \times complexity$. \subsection{Pinch} @@ -138,12 +131,13 @@ The value for $pinch$ in our case was given by sampling from an uniform distribution over the range $[-complexity, 0.7 \times complexity]$. +\subsection{Motion Blur} -\subsection{Distorsion gauss} -This filter simply adds, to each pixel of the image independently, a gaussian noise of mean $0$ and standard deviation $\frac{complexity}{10}$. +This is a GIMP filter we applied, a "linear motion blur" in GIMP terminology. The description will be brief as it is a well-known filter. -It has has a probability of not being applied, at all, of 70\%. +This algorithm has two input parameters, $length$ and $angle$. The value of a pixel in the final image is the mean value of the $length$ first pixels found by moving in the $angle$ direction. An approximation of this idea is used, as we won't fall onto precise pixels by following that direction. This is done using the Bresenham line algorithm. +The angle, in our case, is chosen from a uniform distribution over $[0,360]$ degrees. The length, though, depends on the complexity; it's sampled from a Gaussian distribution of mean 0 and standard deviation $\sigma = 3 \times complexity$. \subsection{Occlusion} @@ -161,6 +155,14 @@ This filter has a probability of not being applied, at all, of 60\%. + +\subsection{Distorsion gauss} + +This filter simply adds, to each pixel of the image independently, a gaussian noise of mean $0$ and standard deviation $\frac{complexity}{10}$. + +It has has a probability of not being applied, at all, of 70\%. + + \subsection{Background Images} This transformation adds a random background behind the letter. The background is chosen by first selecting, at random, an image from a set of images. Then we choose a 32x32 subregion of that image as the background image (by sampling x and y positions uniformly while making sure not to cross image borders). @@ -178,6 +180,7 @@ This filter also has a probability of not being applied, at all, of 75\%. \subsection{Spatially Gaussian Noise} + The aim of this transformation is to filter, with a gaussian kernel, different regions of the image. In order to save computing time we decided to convolve the whole image only once with a symmetric gaussian kernel of size and variance choosen uniformly in the ranges: $[12,12 + 20 \times complexity]$ and $[2,2 + 6 \times complexity]$. The result is normalized between $0$ and $1$. @@ -191,8 +194,9 @@ \subsection{Color and Contrast Changes} + This filter changes the constrast and may invert the image polarity (white on black to black on white). The contrast $C$ is defined here as the difference -between the maximum and the minimum pixel value of the image. A contrast value is sampled uniformly between $1$ and $1-0.85 \times complexity}$ +between the maximum and the minimum pixel value of the image. A contrast value is sampled uniformly between $1$ and $1-0.85 \times complexity$ (this insure a minimum constrast of $0.15$). We then simply normalize the image to the range $[\frac{1-C}{2},1-\frac{1-C}{2}]$. The polarity is inverted with $0.5$ probability.