#include <Neuro/Retina.H>
Public Member Functions | |
| RetinaCT (OptionManager &mgr, const std::string &descrName="Cortical Transform", const std::string &tagName="RetinaCT") | |
| Constructor. | |
| Rectangle | getRawInputRectangle (const Dims &indims, const Dims &outdims) const |
| Get a rectangle delineating the raw input image area. | |
| virtual | ~RetinaCT () |
| Destructor. | |
Protected Member Functions | |
| virtual void | start1 () |
| Overridden so we can load our clip mask file, if any. | |
| virtual void | postInputFrame (SimEventQueue &q, InputFrame &ifr) |
| post a SimEventRetinaSpaceVariantmage | |
| virtual Image< PixRGB< byte > > | transform (const Image< PixRGB< byte > > &image) |
| Transform the image after it has already been shifted, cropped, foveated, etc. | |
Protected Attributes | |
| OModelParam< float > | itsSurrFac |
| OModelParam< SVChanLevels > | itsLevels |
Space variant transform using a foveated model. Could be used as a model of spatial input of retinal ganglion cell's, thalamus, colliculus or early visual cortex
Can do foveation, shifting, flipping, framing in log-polar coords.
Definition at line 293 of file Retina.H.
| RetinaCT::RetinaCT | ( | OptionManager & | mgr, | |
| const std::string & | descrName = "Cortical Transform", |
|||
| const std::string & | tagName = "RetinaCT" | |||
| ) |
Constructor.
See ModelComponent.H for details
Definition at line 504 of file Retina.C.
References ModelComponent::addSubComponent().
| Rectangle RetinaCT::getRawInputRectangle | ( | const Dims & | indims, | |
| const Dims & | outdims | |||
| ) | const [virtual] |
Get a rectangle delineating the raw input image area.
As the raw input may be embedded into a background, shifted, cropped by a field of view, etc., this function allows users to recover the boundaries of the original frames. Note that the rectangle will be possibly cropped to fit within the dims of the Retina's output. A border may be specified that will be used to shrink (if positive) or enlarge (if negative) the returned rectangle (and will be applied before the rectangle is cropped to dims). The default implementation in the base class is to just return a rectangle at (0,0) with dims of the raw input.
Reimplemented from RetinaAdapter.
Definition at line 526 of file Retina.C.
Referenced by postInputFrame().
| void RetinaCT::postInputFrame | ( | SimEventQueue & | q, | |
| InputFrame & | ifr | |||
| ) | [protected, virtual] |
post a SimEventRetinaSpaceVariantmage
Reimplemented from RetinaAdapter.
Definition at line 533 of file Retina.C.
References Image< T >::getDims(), getRawInputRectangle(), RetinaAdapter::getRawToRetinalOffset(), RetinaAdapter::itsRawInput, and SimEventQueue::post().
| void RetinaCT::start1 | ( | ) | [protected, virtual] |
Overridden so we can load our clip mask file, if any.
Reimplemented from RetinaAdapter.
Definition at line 519 of file Retina.C.
References ModelComponent::getRootObject(), MC_IGNORE_MISSING, MC_RECURSE, and ModelComponent::setModelParamVal().
| Image< PixRGB< byte > > RetinaCT::transform | ( | const Image< PixRGB< byte > > & | image | ) | [protected, virtual] |
Transform the image after it has already been shifted, cropped, foveated, etc.
In RetinaStd, this is a no-op
Implements RetinaAdapter.
Definition at line 545 of file Retina.C.
References SVChanLevels::getMaxVariance(), OModelParam< T >::getVal(), and ImageSet< T >::size().
1.6.3