[Gzz-commits] manuscripts/Paper paper.tex

[Janne V. Kujala]

CVSROOT:        /cvsroot/gzz
Module name:    manuscripts
Changes by:     Janne V. Kujala <address@hidden>        03/05/03 15:15:00

Modified files:
        Paper          : paper.tex 

Log message:
        short expl in fig 3. caption

CVSWeb URLs:
http://savannah.gnu.org/cgi-bin/viewcvs/gzz/manuscripts/Paper/paper.tex.diff?tr1=1.141&tr2=1.142&r1=text&r2=text

Patches:
Index: manuscripts/Paper/paper.tex
diff -u manuscripts/Paper/paper.tex:1.141 manuscripts/Paper/paper.tex:1.142
--- manuscripts/Paper/paper.tex:1.141   Sat May  3 15:08:30 2003
+++ manuscripts/Paper/paper.tex Sat May  3 15:15:00 2003
@@ -597,9 +597,9 @@
 significantly impair the reading of black text drawn on top.
 
 Our approach is an extension of 
-the type of inversion approach that been used 
+the type of inversion approach that has been used 
 by Ware and Knight\cite{ware95texture} for inverting 
-the earliest stage of the visual system%, 
+the earliest stage of the visual system %, 
 %the spatial frequency detectors, 
 in order to place 
 a particular vector or scalar field of data
@@ -625,8 +625,8 @@
 a limited
 number of different features detected can be grouped into 
 objects, indicating that the spatial resolution of the feature
-vector is quite low - as a well-known example, conjunction
-coding is not preattentive - red squares are hard to find among
+vector is quite low -- as a well-known example, conjunction
+coding is not preattentive -- red squares are hard to find among
 green squares and red and green circles.
 
 The feature vector is then used to compute 
@@ -807,6 +807,7 @@
 \fi
 \caption{\label{figpipeline}
 The parameter hierarchy in our implementation.
+The arrows indicate dependencies of the randomly generated parameters.
 See text for explanations.
 }
 \end{figure}