Web-enabled image processing operators

Below you find web implementations of various (biologically motivated) image processing operators, which you can use with your own image material.

• COSFIRE filters for the detection of vascular bifurcations in retinal fundus images:


• automatically detect vascular bifurcations in retinal images
• use a slider to control the number of detected bifurcations
• Artistic edge and corner preserving smoothing:


• A colour photograph processed by this program results in an image that looks like an impressionist painting.
• Spatiotemporal Gabor filter for motion processing:


• interactively visualize spatiotemporal Gabor functions,
• learn about their relation to motion sensitive simple cells (in the visual cortex).
• Gabor functions as models of receptive fields of simple cells:


• interactively visualize spatial Gabor functions,
• learn about their relation to simple cells (in the visual cortex).
• Gabor filter for image processing and computer vision:
  
  • visualize Gabor functions,
  • use a Gabor filter and a Gabor-energy filter,
  • perform edge detection,
  • simulate simple and complex cells (visual cortex),
  • extract texture features,
  • simulate non-classical receptive field inhibition or surround suppression (visual cortex),
  • perform contour detection,
  • explain certain visual perception effects.

• Canny edge detector (Canny filter) for image processing and computer vision:
  
  • apply the Canny edge detector on-line on your own images,
  • visualize a derivative of a Gaussian function,
  • simulate non-classical receptive field inhibition or surround suppression,
  • perform contour detection.

• Centre-Surround cell (DoG) operator and Dot-pattern selective cell operator:
  
  • visualize Difference of Gaussian (DoG) functions,
  • simulate retinal-ganglion and LGN cells,
  • compute the convolution of an input image with a DoG (center-surround cell responses),
  • detect intensity spots,
  • detect groups of intensity spots,
  • detect dot-pattern texture.

• Grating cell operator:
  
  • detect gratings and oriented texture.

  Databases

  • Contour database - 40 images (512x512, PGM format) with associated ground truth contour maps.
  • Traffic sign database - 48 images (360x270, PNG format).
  • ICR test database (incomplete contour images).
  • Supplementary illustrations for the paper
    G. Papari, P. Campisi, N. Petkov and A. Neri: A biologically motivated multiresolution approach to contour detection, EURASIP Journal on Advances in Signal Processing, Vol. 2007, Article ID 71828, 28 pages, 2007.
    [bibTex], [pdf 13 MB ©  2007 G. Papari, P. Campisi, N. Petkov and A. Neri; DOI 10.1155/2007/71828]
  • Ground truth data of vascular bifurcations in retinal fundus images of the DRIVE database - 40 images (565x584 pixels) with marked ground truth in PNG format and 40 ascii files that include the locations (row,col) of vessel bifurcations.
  • Dermatology database used in MED-NODE - 170 images of melanoma (70) en nevocellular nevi (100) cases (hair removal already applied).

  ---

  Last changed: 2011-10-13.