299 |
assume certain primitive shapes whose |
assume certain primitive shapes whose |
300 |
structure facilitates recognition. |
structure facilitates recognition. |
301 |
|
|
|
The simple model we use here assumes |
|
|
that at some point, |
|
|
the results from the different pre-attentive feature detectors, |
|
|
such as different shapes and colors, |
|
|
are combined to form an abstract \emph{feature vector} |
|
|
(see Fig.~\ref{fig-perceptual}). |
|
|
The feature vector is then used to compute |
|
|
which concept the particular |
|
|
input corresponds to by comparing it to memorized models |
|
|
in a simple perceptron-like |
|
|
fashion\cite{rosenblatt62neurodynamics,widrow60adaptive}. |
|
|
This configuration is commonly used in neural computation. |
|
|
|
|
302 |
|
|
303 |
% In this article, we apply texture shading to synthesize a large number |
% In this article, we apply texture shading to synthesize a large number |
304 |
% of unique textures for distinguishing virtual objects. |
% of unique textures for distinguishing virtual objects. |
562 |
%providing an infinite source of unique backgrounds. |
%providing an infinite source of unique backgrounds. |
563 |
%generating textures based on seed numbers [identity] |
%generating textures based on seed numbers [identity] |
564 |
|
|
565 |
|
The simple model we use here assumes |
566 |
|
that at some point, |
567 |
|
the results from the different pre-attentive feature detectors, |
568 |
|
such as different shapes and colors, |
569 |
|
are combined to form an abstract \emph{feature vector} |
570 |
|
(see Fig.~\ref{fig-perceptual}). |
571 |
|
The feature vector is then used to compute |
572 |
|
which concept the particular |
573 |
|
input corresponds to by comparing it to memorized models |
574 |
|
in a simple perceptron-like |
575 |
|
fashion\cite{rosenblatt62neurodynamics,widrow60adaptive}. |
576 |
|
This configuration is commonly used in neural computation. |
577 |
|
|
578 |
\begin{figure} |
\begin{figure} |
579 |
%\fbox{\vbox{\vskip 3in}} |
%\fbox{\vbox{\vskip 3in}} |
580 |
\ifpics |
\ifpics |
604 |
% The basic assumption of the model is that an image |
% The basic assumption of the model is that an image |
605 |
% is perceived as a set of features |
% is perceived as a set of features |
606 |
|
|
607 |
This |
This rough, qualitative |
|
rough, qualitative |
|
608 |
model is able to explain why uniformly random texels |
model is able to explain why uniformly random texels |
609 |
do not make easily distinguishable background textures: |
do not make easily distinguishable background textures: |
610 |
after the ``pre-processing'', |
after the ``pre-processing'', |