202 |
% |
% |
203 |
% Used for |
% Used for |
204 |
% Aid to visualizing surfaces\cite{schweitzer83texturing}, |
% Aid to visualizing surfaces\cite{schweitzer83texturing}, |
205 |
|
% (simple local features in artificial %textures are used for |
206 |
|
% implying global surface shape) |
207 |
% various graphics operations\cite{haeberli93texture}, |
% various graphics operations\cite{haeberli93texture}, |
208 |
% |
% |
209 |
% Synthesized using |
% Synthesized using |
246 |
frequencies, orientations, and locations in the visual field. |
frequencies, orientations, and locations in the visual field. |
247 |
A good mathematical model for the sensitivity of the receptive fields is |
A good mathematical model for the sensitivity of the receptive fields is |
248 |
Gabor function, i.e., a two-dimensional Gaussian-modulated sinusoid. |
Gabor function, i.e., a two-dimensional Gaussian-modulated sinusoid. |
249 |
|
|
250 |
On a higher level, correlating local feature are combined |
On a higher level, correlating local feature are combined |
251 |
to global perception. |
to global perception. |
252 |
For example, contours are formed from consistent directions |
For example, contours are formed from consistent directions |
253 |
of adjacent receptive fields. |
of adjacent receptive fields and different objects are |
254 |
|
perceived. |
|
In \cite{schweitzer83texturing}, simple local features in artificial |
|
|
textures are used for implying global surface shape. XXX |
|
|
|
|
255 |
The higher levels of visual processing are no longer hierarchical |
The higher levels of visual processing are no longer hierarchical |
256 |
and not throughly understood. |
and not throughly understood. |
257 |
|
Theories of structural object perception (e.g. \cite{biederman87}) |
258 |
|
propose certain primitive shapes whose structure facilities recognition. |
259 |
|
|
260 |
We simply assume that the intensities of different features, |
We simply assume that the intensities of different features, |
261 |
such as local and global shapes and colors, form a \emph{feature vector}, |
such as local and global shapes and colors, form a \emph{feature vector}, |
262 |
which facilitates recognition and memorization of images. |
which facilitates recognition and memorization of images. |