[Gzz-commits] manuscripts/Paper paper.tex

[Janne V. Kujala]

CVSROOT:        /cvsroot/gzz
Module name:    manuscripts
Changes by:     Janne V. Kujala <address@hidden>        03/03/08 05:28:00

Modified files:
        Paper          : paper.tex 

Log message:
        texture perception reorg

CVSWeb URLs:
http://savannah.gnu.org/cgi-bin/viewcvs/gzz/manuscripts/Paper/paper.tex.diff?tr1=1.14&tr2=1.15&r1=text&r2=text

Patches:
Index: manuscripts/Paper/paper.tex
diff -u manuscripts/Paper/paper.tex:1.14 manuscripts/Paper/paper.tex:1.15
--- manuscripts/Paper/paper.tex:1.14    Sat Mar  8 05:12:22 2003
+++ manuscripts/Paper/paper.tex Sat Mar  8 05:27:59 2003
@@ -256,8 +256,21 @@
 $N$th order statistics of pixels and elaborate connectivity 
 structures of certain micropatterns.XXX
 
-Textons \cite{julesz81textons}: elongated blobs, line terminators,
-line crossings, etc.
+Statistical modeling of textures as samples from a probability 
+distribution on a random field as already seen in \cite{julesz62visualpattern}
+in a very simple form.
+The most popualar computational approach is Markov random fields
+\cite{cross83markov, geman84stochastic}, where a texture 
+is characterized by its local statistics.
+However, these approaches are often not feasible on large
+large neighborhoods, but essentially work on pixel scale.
+
+Attempt to explain texture perception by the densities of textons
+\cite{julesz81textons}, fundamental texture elements, such as
+elongated blobs, line terminators, line crossings, etc.  
+However, the textons are hard to define formally.
+
+Textures are continuous
 
 Of course, such models are not directly applicable on high-resolution
 textures; some kind of filtering would be required to obtain the input.  
@@ -265,14 +278,10 @@
 \cite{bergen88earlyvision}.XXX
 
 Filtering based approach, e.g., \cite{heeger95pyramid}.
+Essentially a bank of linear filters is applied to the texture followed
+by a nonlineary and then another set of filters.
 
-
-Statistical modeling of textures as samples from a probability 
-distribution on a random field as already seen in \cite{julesz62visualpattern}
-in a very simple form.
-The most popualar approach is Markov random fields
-\cite{cross83markov, geman84stochastic}, where a texture 
-is characterized by its local statistics.
+XXX: reviews
 
 \subsection{Focus+Context views}