[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 11:46:19

Modified files:
        Paper          : paper.tex 

Log message:
        cuts

CVSWeb URLs:
http://savannah.gnu.org/cgi-bin/viewcvs/gzz/manuscripts/Paper/paper.tex.diff?tr1=1.113&tr2=1.114&r1=text&r2=text

Patches:
Index: manuscripts/Paper/paper.tex
diff -u manuscripts/Paper/paper.tex:1.113 manuscripts/Paper/paper.tex:1.114
--- manuscripts/Paper/paper.tex:1.113   Mon Mar 31 11:39:15 2003
+++ manuscripts/Paper/paper.tex Mon Mar 31 11:46:18 2003
@@ -638,23 +638,43 @@
 
 From the 
 model 
-we can formulate the following points:
-To be distinguishable, \label{secfeaturevec}
-\begin{itemize}
-\item A feature vector for a given texture should always be the
-    same.
+we can see that
+to be distinguishable, \label{secfeaturevec}
+a feature vector for a given texture should always be the
+same.
     Fragments of 
     a non-repeating texture will be slightly different,
     resulting in slightly different vectors even 
     if the local structure is the same.
     A repeating texture should thus be easier to recognize.
     Our anecdotal observations confirm this.
-% XXX: Why wouldn't it always be the same?
-% - seeing different parts of the texture?
-% - ambiguous perception?
-\item The entropy of the feature vectors
-    over the distribution of textures should be maximized.
-\end{itemize}
+
+Additionally,
+the entropy of the feature vectors
+over the distribution of textures should be maximized.
+\iftechreport
+    This means essentially
+    that if all square-like shapes were green, we would be 
+    wasting recognitive power.
+    There should also be as many possible features in the distribution
+    as possible. For example, if there were no yellow textures,
+    or if there were no curved lines, we would be wasting
+    recognition potential by leaving some elements
+    of the feature vector always zero. 
+
+    Generally, the entropy is maximized when the features are distributed
+    independently from each other.
+
+\else
+    The distribution should contain occurrences 
+    as many different features
+    as possible, and
+    the features should be distributed
+    independently from each other.
+\fi
+However, the results cited above\cite{olson02vstm}  also
+indicate that in any {\em single} texture, only a limited range
+of features should be used.
 
 % which facilitates recognition and memorization of images.
 % The structure of the features is assumed to be irrelevant.
@@ -672,34 +692,19 @@
 % To achieve this, the model should maximize the entropy of the feature vector.
 %We call this the principle of saving bits.
 
-\iftechreport
-The last part means essentially
-that if all square-like shapes were green, we would be \fi
-wasting recognitive power.
-There should also be as many possible features in the distribution
-    as possible. \iftechreport For example, if there were no yellow textures,
-    or if there were no curved lines, we would be wasting
-    recognition potential by leaving some elements
-    of the feature vector always zero. \fi
-    However, the results cited above\cite{olson02vstm}  also
-    indicate that in any {\em single} texture, only a limited range
-    of features should be used.
-
 
-Generally, the entropy is maximized when the features are distributed
-independently from each other:
-features orthogonal to human perception 
-(e.g.,~color, direction of fastest luminance change)
+In a sense, the model of perception should be {\em inverted}
+in order to produce a unique background from 
+a random vector.
+Features that are orthogonal for human perception 
+(e.g.,~color and  direction of fastest luminance change)
 should be independently random, and features not orthogonal 
 (e.g. colors of neighbouring pixels) 
 should be correlated so as to maximize the entropy.
-For example, pixels on a small area should correlate enough to
-facilitate perception of contours.
+%For example, pixels on a small area should correlate enough to
+%facilitate perception of contours.
 
-In a sense, the model of perception should be {\em inverted}
-in order to produce a unique background from 
-a random vector.
-This type of approach has been used 
+A type of inversion approach has been used 
 by Ware and Knight\cite{ware95texture}, for inverting 
 the earliest stage of the visual system, 
 the spatial frequency detectors, in order to place