1 / 35

Evolving Edge detection

Evolving Edge detection. Final project by Rubshtein Andrey (303468490). Introduction. Is it possible for a living creature to evolve vision? Is it possible for a living creature to evolve at least an edge detector?. Simulates an environment in which there are “living creatures”

sreber
Download Presentation

Evolving Edge detection

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Evolving Edge detection Final project by Rubshtein Andrey (303468490)

  2. Introduction • Is it possible for a living creature to evolve vision? • Is it possible for a living creature to evolve at least an edge detector?

  3. Simulates an environment in which there are “living creatures” They are called Genomes. Each Genome has some parameters There exists a global fitness function which tells how successful a Genome is. There exists a Population of some Genomes There are many Generations A bit about Genetic Algorithms

  4. More about Genetic Algorithms Each generation consist of 3 stages: • Selection – The more fit are chosen. • Crossover – Some genomes are crossed, while inheriting their parents properties. • Mutation – Some Genomes are randomly changed, with a slight variation. • We hope that after some generations, we get more fitted Genomes.

  5. The Goal Assumptions: • Each living creature can perform a convolution, with a constant mask, which is coded into his Genome. • The creatures that detect edges better, survive better. • There exists an ideal edge detector.

  6. More about the Goals • Is it possible to develop, by means of natural selection, a good edge detector? • Is it possible to achieve that using only convolution type edge detectors, while the perfect edge picture is not?

  7. Ideal edge detector • Canny’s edge detector was chosen as an ideal edge detector. • Why Canny? Has an impressive results, and uses much more advanced techniques than convolutions • So it’s challenging to try to evolve to it.

  8. About the simulation The genome structure • A 3x3 Matrix • Each of the cells is in the range [-255,255] • A threshold value in the range [0,255]

  9. Fitness

  10. About similarity Measure • Both images are binary after threshold • The measure is : Similarity[x,y]=Sum[x OR y] / Sum[ x AND y]

  11. Why this measure is good? • It is symmetric : Sim[x,y]=Sim[y,x] • It has the range of [0,1] • It is simple to implement • It is “reflexive” – Sim[x,x]=1 • It doesn’t give extra points for pictures which have a common non-edge (0 ) pixel. • It reduces points for false positive edges, and false negative edges.

  12. Why this measure isn’t good • A small movement in the picture results in a low similarity rate • The measure takes into account single pixels, which isn’t the goal in edge detection • A better measure would have been perhaps one that takes into account the shape of the edges (Geshtalt)

  13. The Test Subjects

  14. The numbers (The simplest)

  15. The Guitar (Medium)

  16. The dog (Hardest)

  17. The results • After a few generations, the Genomes learn to somehow detect edges. • Yet even in the easy pictures, the evolution fails to get a good ratio of similarity ( Usually less than 0.3) • But, we see an impressive results, when looking with our eyes.

  18. Evolution of numbers (The ideal)

  19. Generation 5Sim=0.11

  20. Generation 10Sim=0.13

  21. Generation 20Sim=0.23

  22. Generation 30Sim=0.25

  23. Generation 40 Sim=0.27

  24. Generation 80Sim=0.28

  25. Generation 100Sim=0.29

  26. Generation 110Sim=0.32

  27. Results for easy pictures • It is amazing that we’ve managed to evolve something close to the ideal • Then again, the similarity rate is low

  28. Evolution of Dog (The ideal)

  29. Generation 10 Sim=0.05

  30. Generation 100 Sim=0.10

  31. Generation 300 Sim=0.16

  32. Results for hard pictures • The evolution finds some solution, yet it isn’t as good as wanted • The similarity rate is very low

  33. Conclusions • It is easy to evolve some kind of edge detector • It is hard to evolve a good edge detector, in terms of similarity • It seems that an edge detector evolved from one picture isn’t good for another picture.

  34. Why the results are bad: • Canny is a very sophisticated edge detector. Perhaps it’s impossible to imitate it using only convolutions? • Perhaps the similarity measure isn’t suitable for this problem. Perhaps using another similarity it’s possible to get better results.

  35. The end Thank you for listening :-)

More Related