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 |
} |
} |