[Gzz-commits] manuscripts/Paper paper.tex

[Tuomas J. Lukka]

CVSROOT:        /cvsroot/gzz
Module name:    manuscripts
Changes by:     Tuomas J. Lukka <address@hidden>        03/03/31 09:59:46

Modified files:
        Paper          : paper.tex 

Log message:
        Shorten

CVSWeb URLs:
http://savannah.gnu.org/cgi-bin/viewcvs/gzz/manuscripts/Paper/paper.tex.diff?tr1=1.97&tr2=1.98&r1=text&r2=text

Patches:
Index: manuscripts/Paper/paper.tex
diff -u manuscripts/Paper/paper.tex:1.97 manuscripts/Paper/paper.tex:1.98
--- manuscripts/Paper/paper.tex:1.97    Mon Mar 31 09:53:32 2003
+++ manuscripts/Paper/paper.tex Mon Mar 31 09:59:46 2003
@@ -43,8 +43,6 @@
 
 % WHY HW ACCEL NEEDED - PIXELLATION - NO SAVING!
 
-NO SEMANTIC CORRELATIONS!!!!!!!
-
 TJL
 
 We present a perceptually designed hardware-accelerated
@@ -584,28 +582,30 @@
 objects, ... XXX SO!!! JVK
 
 \begin{figure}
+\centering
 %\fbox{\vbox{\vskip 3in}}
 \ifpics
-\def\visscal{.6}
-a)\\\includegraphics[scale=\visscal]{visper.1}\\\\\\
-b)\\\includegraphics[scale=\visscal]{visper.2}
+\def\visscal{.65}
+%a)\includegraphics[scale=\visscal]{visper.1}\\
+%b)%
+\includegraphics[scale=\visscal]{visper.2}
 \fi
 \caption{
 \label{fig-perceptual}
-a) The qualitative model of visual perception used to create
+The qualitative model of visual perception used to create
 the algorithm. 
 The visual input is transformed into a feature vector,
 which contains numbers (activation levels) corresponding to 
 e.g.~colors, edges, curves and small patterns.
-The feature vector is matched against the memorized textures
-with a simple model. 
-The simplicity of the pre-attentive feature matcher
-is the key feature of the model and is used in the text 
-to formulate principles
-about recognizability.
-b) In order to generate recognizable textures, 
-Key is also that producing a distribution of feature vectors
-with maximum entropy is...
+The feature vector is matched against the memorized textures.
+In order to generate recognizable textures, random seed
+values should produce 
+a distribution of feature vectors
+with maximum entropy.
+%The simplicity of the pre-attentive feature vector and matcher
+%is the key feature of the model and is used in the text 
+%to formulate principles
+%about recognizability.
 }
 \end{figure}