Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Cellular Edge Detection

6d6790f55590467fb978d520cba285b0?s=47 kathleensaz
October 25, 2017
25

Cellular Edge Detection

6d6790f55590467fb978d520cba285b0?s=128

kathleensaz

October 25, 2017
Tweet

Transcript

  1. CELLULAR EDGE DETECTION FOR GRAYSCALE & BINARY IMAGES

  2. None
  3. None
  4. CELLULAR AUTOMATON BINARY IMAGE

  5. CELLULAR AUTOMATON GREYSCALE IMAGE

  6. LEARNING AUTOMATON Von-neumann Moore

  7. 50% 50% LEARNING AUTOMATON Von-neumann Moore

  8. 10% 90% LEARNING AUTOMATON Von-neumann Moore

  9. None
  10. 1200x800 Original 1200x800 Output image Cellular automata 1200x800 Learning automata

    1200x800
  11. 1200x800 Output image Cellular automata 1200x800 Learning automata 1200x800 ..update

    output image every generation Execute rules for N generations..
  12. Final 1200x800 1200x800 Output image

  13. EXPERIMENTS

  14. None
  15. None
  16. CED CANNY PREWITT

  17. None
  18. CED CANNY PREWITT

  19. CED CANNY PREWITT MSE PSNR (dB) MSE PSNR (dB) MSE

    PSNR (dB) 1.368 6.8011 1.369 6.8075 1.367 6. 8017 3.493 6.7320 3.491 6.7346 3.488 6.7382 1.804 5.6016 1.802 5.6056 1.800 5.6120
  20. LIMITATIONS

  21. Manual adjustment of threshold Defeats the purpose (maybe) Slow for

    big images
  22. None
  23. SUPPORTING SLIDES

  24. Pseudocode

  25. Reinforcement signal