The Machine Perception Toolbox

[Introduction]- [News]- [Download]- [Screenshots]- [Manual (pdf)]- [Forums]- [API Reference]- [Repository ]

 

LGN.cpp File Reference

#include <iostream.h>
#include <mpisearch.h>
#include <Magick++.h>

Include dependency graph for LGN.cpp:

Go to the source code of this file.

Namespaces
namespace	Magick
namespace	std
Classes
class	CenterSurround
	X cells in the cat and P cells in the monkey's retina and LGN behave like linear filters. More...
Functions
int	main ()

---

Function Documentation

int main (   )

Definition at line 374 of file LGN.cpp. References img, MPISearchObjectDetector::initStream(), and CenterSurround::search(). { // Load the image Image img("../../Media/ExampleImage.jpg"); // Image img("../../Media/spock.gif"); // Write the word "Hello" on the image // img.fontPointsize(100); // Geometry(width, height, xoffset, yoffset) // img.annotate("Hello2", Geometry(400,400, 0, 220) ); img.display(); // Construct an RImage, which is expected by MPISearch // This constructor sets the member variables for width, height, and // number of pixels and allocates memory for the member variable // "array", which is a vector of size npixels RImage< float > pixels(img.columns(), img.rows()); // Copy the pixels into an RImage, which is expected by MPISearch img.write(0,0, img.columns(), img.rows(), "I", FloatPixel, pixels.array); // The 'I' tells ImageMagick to take the intensity channel. I think // there are better ways to do this, but I haven't looked into them. CenterSurround CS; // stream is a data member of CenterSurround, of type // MPISearchStream MPISearchStream holds all the memory and caches // for the class MPISearchObjectDetector, which Provides an // architecture for performing operations on every sub-window of an // image at multiple scales. // CS.inistream calls stream.init(width,height,data,WINSHIFT) // were data is a data member of CenterSurround of type FeatureData // stream.init CS.initStream(pixels.width, pixels.height, 1.0f); // Now run over the image at multiple scales and compute the mean // pixel at that size CS.search(pixels); return 0; }

Here is the call graph for this function:

---