/[gzz]/manuscripts/Paper/paper.tex
ViewVC logotype

Diff of /manuscripts/Paper/paper.tex

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 1.66 by jvk, Sat Mar 29 14:30:48 2003 UTC revision 1.67 by tjl, Sat Mar 29 18:38:08 2003 UTC
# Line 576  b)\\\includegraphics[scale=\visscal]{vis Line 576  b)\\\includegraphics[scale=\visscal]{vis
576  \fi  \fi
577  \caption{  \caption{
578  \label{fig-perceptual}  \label{fig-perceptual}
579  The qualitative model of visual perception used to create  a) The qualitative model of visual perception used to create
580  the algorithm.  the algorithm.
581  The visual input is transformed into a feature vector,  The visual input is transformed into a feature vector,
582  which contains numbers (activation levels) corresponding to  which contains numbers (activation levels) corresponding to
583  e.g.~colors, edges, curves and small patterns.  e.g.~colors, edges, curves and small patterns.
584  The feature vector is matched against the memorized textures  The feature vector is matched against the memorized textures
585  with a simple model.  with a simple model.
586  The simplicity of the feature matcher  The simplicity of the pre-attentive feature matcher
587  is the key feature of the model and is used in the text  is the key feature of the model and is used in the text
588  to formulate principles  to formulate principles
589  about recognizability.  about recognizability.
590    b) In order to generate recognizable textures,
591  Key is also that producing a distribution of feature vectors  Key is also that producing a distribution of feature vectors
592  with maximum entropy is...  with maximum entropy is...
593  }  }

Legend:
Removed from v.1.66  
changed lines
  Added in v.1.67

savannah-hackers-public@gnu.org
ViewVC Help
Powered by ViewVC 1.1.26