[Gzz-commits] gzz/Documentation/Manuscripts/Paper paper.tex

[Tuomas J. Lukka]

CVSROOT:        /cvsroot/gzz
Module name:    gzz
Changes by:     Tuomas J. Lukka <address@hidden>        02/11/29 03:25:47

Modified files:
        Documentation/Manuscripts/Paper: paper.tex 

Log message:
        Reorg, shorten

CVSWeb URLs:
http://savannah.gnu.org/cgi-bin/viewcvs/gzz/gzz/Documentation/Manuscripts/Paper/paper.tex.diff?tr1=1.88&tr2=1.89&r1=text&r2=text

Patches:
Index: gzz/Documentation/Manuscripts/Paper/paper.tex
diff -u gzz/Documentation/Manuscripts/Paper/paper.tex:1.88 
gzz/Documentation/Manuscripts/Paper/paper.tex:1.89
--- gzz/Documentation/Manuscripts/Paper/paper.tex:1.88  Fri Nov 29 02:06:19 2002
+++ gzz/Documentation/Manuscripts/Paper/paper.tex       Fri Nov 29 03:25:47 2002
@@ -19,7 +19,7 @@
 \title{Representing Identity 
 %in Focus+Context Views 
 %Hardware-Accelerated 
-by Unique Backgrounds}
+by Unique Background Textures}
 
 \newauthor{tjl}{\censor{Tuomas J. Lukka}}{}
 \newauthor{jvk}{\censor{Janne V. Kujala}}{}
@@ -278,38 +278,64 @@
 Distinguishing a particular texture from a large set
 depends on the distribution of the textures in the set;
 therefore, the problem is one of defining a suitable
-{\em distribution} of textures
+{\em distribution} of distinguishable textures.
 
-The seed for randomly choosing
-an easily distinguishable unique background from a
-distribution based on a qualitative model of visual perception.
+It is intuitively clear that textures with independently
+random texel values would be a very bad choice: all such
+textures would look alike. 
+In order to design distinguishable textures,
+we have to take into account the properties of the human
+visual system.
+
+% The seed for randomly choosing
+% an easily distinguishable unique background from a
+% distribution based on 
+
+We use a very rough, qualitative model of visual perception,
 %providing an infinite source of unique backgrounds.
 %generating textures based on seed numbers [identity]
 The basic assumption of the model is that an image
 is perceived as a set of features (see Fig.~\ref{fig-perceptual}).
 
-Current knowledge of visual perception (see, 
e.g.~\cite{bruce96visualperception})
-explains early visual processing very accurately.
-In visual cortex, there are cells sensitive to different 
-frequencies, orientations, and locations in the visual field.
-A good mathematical model for the excitatory and inhibitory
-sensitivities of the receptive fields is
-Gabor function, i.e., a two-dimensional Gaussian-modulated sinusoid.
+\begin{figure}
+\centering
+%\fbox{\vbox{\vskip 3in}}
+\includegraphics{perceptual-model}
+\caption{
+\label{fig-perceptual}
+The qualitative model of visual perception used to create
+the algorithm.
+}
+\end{figure}
 
+Current knowledge of the first stages
+of visual perception (see, e.g.~\cite{bruce96visualperception})
+supports this view:
+in the visual cortex, there are cells sensitive to different 
+frequencies, orientations, and locations in the visual field.
 On a higher level, correlating local features are combined 
-to global perception. 
-For example, contours are formed from consistent directions 
-of adjacent receptive fields and different objects are 
-perceived.
-The higher levels of visual processing are no longer hierarchical
-and not throughly understood.
-Theories of structural object perception (e.g. \cite{biederman87})
-propose certain primitive shapes whose structure facilities recognition.
-We simply assume that the intensities of different features,
-such as local and global shapes and colors, form a \emph{feature vector},
+to global perception, by forming contours and possibly
+other higher-level constructions. 
+These higher levels are not yet thoroughly understood;
+theories of structural object perception (e.g. \cite{biederman87})
+propose certain primitive shapes whose 
+structure facilities recognition.
+
+We make the assumption
+that the intensities of different features,
+such as local and global shapes and colors, 
+form a \emph{feature vector},
 which facilitates recognition and memorization of images.
 % The structure of the features is assumed to be irrelevant.
 
+% A good mathematical model for the excitatory and inhibitory
+% sensitivities of the receptive fields is
+% Gabor function, i.e., a two-dimensional Gaussian-modulated sinusoid.
+
+% For example, contours are formed from consistent directions 
+% of adjacent receptive fields and different objects are 
+% perceived.
+
 For the backgrounds to be distinguishable, they should produce
 distinct feature vectors in brain. 
 To achieve this, the model should maximize the entropy of the feature vector.
@@ -334,17 +360,6 @@
 
 %distinguishability: should produce random vector in brain 
 %    (perception model in Fig.~\ref{fig-perceptual}) -- saving of bits
-
-\begin{figure}[h]
-\centering
-%\fbox{\vbox{\vskip 3in}}
-\includegraphics{perceptual-model}
-\caption{
-\label{fig-perceptual}
-The qualitative model of visual perception used to create
-the algorithm.
-}
-\end{figure}
 
 The model explains easily why uniformly random texels (white noise)
 would not make easily distinguishable patterns: different instances