/[gzz]/gzz/Documentation/Manuscripts/Paper/paper.tex
ViewVC logotype

Diff of /gzz/Documentation/Manuscripts/Paper/paper.tex

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

revision 1.163 by tjl, Sun Dec 1 11:49:54 2002 UTC revision 1.164 by tjl, Sun Dec 1 11:54:30 2002 UTC
# Line 353  The qualitative model of visual percepti Line 353  The qualitative model of visual percepti
353  the algorithm.  the algorithm.
354  The visual input is transformed into a feature vector,  The visual input is transformed into a feature vector,
355  which contains numbers (activation levels) corresponding to  which contains numbers (activation levels) corresponding to
356  e.g. colors, edges, curves and small patterns.  e.g.~colors, edges, curves and small patterns.
357  The feature vector is matched against the memorized textures  The feature vector is matched against the memorized textures
358  with a simple model. The simplicity of the feature matcher  with a simple model. The simplicity of the feature matcher
359  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
# Line 382  rough, qualitative model Line 382  rough, qualitative model
382  we can formulate the following points:  we can formulate the following points:
383  To be distinguishable, \label{secfeaturevec}  To be distinguishable, \label{secfeaturevec}
384  \begin{itemize}  \begin{itemize}
385  \item A feature vector for a given texture should be always the  \item A feature vector for a given texture should always be the
386      same, and not a smudged distribution;      same.
387      therefore, a repeating texture should be easier to recognize      A non-repeating texture will always have slightly different
388      than one that does not repeat, even if local features      regions which result in a smudged distribution;
389      are similar. Our anecdotal observations confirm this.      a repeating texture should be easier to recognize.
390        Our anecdotal observations confirm this.
391  % XXX: Why wouldn't it always be the same?  % XXX: Why wouldn't it always be the same?
392  % - seeing different parts of the texture?  % - seeing different parts of the texture?
393  % - ambiguous perception?  % - ambiguous perception?

Legend:
Removed from v.1.163  
changed lines
  Added in v.1.164

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