Feature Extraction

I'm still trying to figure out a webcam which is Linux compatible with a shutter speed that admits capturing motion in direct sunlight. Until then, more armchair computer vision 101 ...

Winn et. al. use a standard set of filters for extracting features from images: Gaussian, derivatives of Gaussian (aka DoG), and Laplacian of Gaussian (aka LoG). Here's what they look like:

Gaussian
Laplacian of Gaussian
Y-derivative of Gaussian
X-derivative of Gaussian

OpenCV has a method for computing GaussianBlur which is sufficiently flexible to reproduce Winn et. al., but to reproduce their usage of DoG and LoG I wrote my own OpenCV kernels (although maybe a combination of the GaussianBlur method with the Laplacian method and Sobel method would work?). It turns out separable filters are much faster and everything above except the LoG is separable; in addition the LoG can be written as the sum of two separable filters, the second derivative of Gaussian in x and y. Thus with something like

#include <string>
#include "cv.h"
#include "highgui.h"

#include "cyclopsutil.hh"

using namespace cv;
using namespace cyclops;

int main (int, char** argv)
{
  string file (argv[1]);
  Mat img = imread (file);
  vector<Mat> color (3);

  assert (! img.empty ());
  assert (img.channels () == 3);

  cvtColor (img, img, CV_BGR2Lab);

  split (img, color);

  imwrite (file + ".L.png", color[0]);
  imwrite (file + ".a.png", color[1]);
  imwrite (file + ".b.png", color[2]);

  for (int sigma = 1; sigma < 16; sigma *= 2)
    {
      string labels[3] = { string ("L"), string ("a"), string ("b") };
      Mat conv = color[0].clone ();
      Mat convtwo = color[0].clone ();
      std::stringstream out;
      out << sigma;

      GaussianBlur (color[0], conv, Size (6 * sigma + 1, 6 * sigma + 1), sigma, sigma, BORDER_REPLICATE);
      imwrite (file + "." + labels[0] + ".gauss." + out.str () + ".png", conv);

      sepFilter2D (color[0], conv, -1, dygauss_kernelx (sigma), dygauss_kernely (sigma), Point (-1, -1), 0, BORDER_REPLICATE);
      imwrite (file + "." + labels[0] + ".dygauss." + out.str () + ".png", conv);

      sepFilter2D (color[0], conv, -1, dxgauss_kernelx (sigma), dxgauss_kernely (sigma), Point (-1, -1), 0, BORDER_REPLICATE);
      imwrite (file + "." + labels[0] + ".dxgauss." + out.str () + ".png", conv);

      sepFilter2D (color[0], conv, -1, dyygauss_kernelx (sigma), dyygauss_kernely (sigma), Point (-1, -1), 0, BORDER_REPLICATE);
      imwrite (file + "." + labels[0] + ".dyygauss." + out.str () + ".png", conv);

      sepFilter2D (color[0], convtwo, -1, dxxgauss_kernelx (sigma), dxxgauss_kernely (sigma), Point (-1, -1), 0, BORDER_REPLICATE);
      imwrite (file + "." + labels[0] + ".dxxgauss." + out.str () + ".png", convtwo);

      imwrite (file + "." + labels[0] + ".lapgauss." + out.str () + ".png", conv + convtwo);
    }

  return 0;
}

applied to our awesome cop car picture's luminosity component we have:

Gaussian (sigma = 1)
Gaussian (sigma = 8)
DxGaussian (sigma = 1)
DxGaussian (sigma = 8)
DyGaussian (sigma = 1)
DyGaussian (sigma = 8)
Laplacian of Gaussian (sigma = 1)
Laplacian of Gaussian (sigma = 8)