1 / 60

Biologically Inspired Intelligent Systems

Biologically Inspired Intelligent Systems. Lecture 05 Dr. Roger S. Gaborski. Quiz 1 second half of lecture. BACKGROUND: Spatial Filtering. Neighborhood processing Define center point (x,y) Perform operations involving only pixels in the neighborhood

jamal
Download Presentation

Biologically Inspired Intelligent Systems

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. Biologically Inspired Intelligent Systems Lecture 05 Dr. Roger S. Gaborski

  2. Quiz 1 second half of lecture Roger S. Gaborski

  3. BACKGROUND: Spatial Filtering • Neighborhood processing • Define center point (x,y) • Perform operations involving only pixels in the neighborhood • Result of operation is response to process at that point • Moving the pixel results in a new neighborhood • Repeat process for every point in the image Roger S. Gaborski

  4. Linear and Nonlinear Spatial Filtering • Linear operation • Multiply each pixel in the neighborhood by the corresponding coefficient and sum the results to get the response for each point (x,y) • If neighborhood is m x n , then mn coefficients are required • Coefficients are arranged in a matrix, called • Filter • Filter mask • Kernel • Template • Mask sizes are typically odd sizes (3x3, 5x5, etc.) • Larger the mask, greater the compute time Roger S. Gaborski

  5. Chapter 3 www.prenhall.com/gonzalezwoodseddins Roger S. Gaborski

  6. Correlation -- Convolution • Correlation • Place mask w on the image array f as previously described • Convolution • First rotate mask w by 180 degrees • Place rotated mask on image as described previously Roger S. Gaborski

  7. Example - Correlation • Assume w and f are one dimensional • Origin of f is its left most point • Place w so that its right most point coincides with the origin of f • Pad f with 0s so that there are corresponding f points for each w point (also pad end with 0s) • Multiply corresponding points and sum • In this case (example on next page) result is zero • More w to the right one value, repeat process • Continue process for whole length of f Roger S. Gaborski

  8. Chapter 3 www.prenhall.com/gonzalezwoodseddins ‘full’ is the result we obtain from the operations on the previous slide. If instead of aligning the left most element of f with the right most element of w we aligned the center element of w with the left most value of f we would obtain the ‘same’ result, same indicating the result is the same length of the original w Roger S. Gaborski

  9. ‘Full’ correlation Roger S. Gaborski

  10. Roger S. Gaborski

  11. Roger S. Gaborski

  12. ‘Same’ correlation etc. Roger S. Gaborski

  13. Example - Convolution • Convolution is the same procedure, but the filter is first rotated 180 degrees. • If the filter is symmetric, correlation and convolution results are the same Roger S. Gaborski

  14. Chapter 3 www.prenhall.com/gonzalezwoodseddins Can simply extend to images Roger S. Gaborski

  15. Linear Filtering in MATLAB • g = imfilter(f, w, filtering mode, boundary_options, size_options) • f is the input filter • w is filter mask • g is filtered output • filtering mode specifies either corr or conv • boundary_options deals with padding issues • size_options is either full or same Roger S. Gaborski

  16. MATLAB function for filtering: imfilter • g = imfilter(f, w, ‘replicate’) • Correlation is the default . • If filters are pre-rotated 180 degrees, can simply use default • If filter is symmetric, doesn’t matter Roger S. Gaborski

  17. Chapter 3 www.prenhall.com/gonzalezwoodseddins Roger S. Gaborski

  18. Basic Neuron Models Output function Neuron Firing Rate Value (Output Spikes) Filter Output Fires strongest when Image matches linear filter Linear Filter Non-linear Function Roger S. Gaborski

  19. %Dog128Filter.m %Generates difference of Gaussians 128x128 imageSize = 128; sigmaex= .095*imageSize; sigmainh = .19*imageSize; [x,y] = meshgrid(-63:64 -63:64); %First Term exp1 = exp( -1*( x .* x + y .* y)./(2*sigmaex*sigmaex)); FirstTerm = 7.5 *exp1; %SecondTerm exp2 = exp( -1*( x .* x + y .* y)./(2*sigmainh*sigmainh)); SecondTerm = 1.95*exp2; Dog128 = .0013*(FirstTerm - SecondTerm); Roger S. Gaborski

  20. 128 x 128 Receptive field Roger S. Gaborski

  21. 128 x 128 Receptive field Roger S. Gaborski

  22. 128x128 – 1D Roger S. Gaborski

  23. Code example D64 = imresize(Dog128,.5, 'bilinear'); figure, surf(D64), title('DoG64') Roger S. Gaborski

  24. Roger S. Gaborski

  25. Roger S. Gaborski

  26. Roger S. Gaborski

  27. Roger S. Gaborski

  28. Roger S. Gaborski

  29. Roger S. Gaborski

  30. Color Flag Image Roger S. Gaborski

  31. Small Gray Flag Image Roger S. Gaborski

  32. Roger S. Gaborski

  33. Roger S. Gaborski

  34. Roger S. Gaborski

  35. Roger S. Gaborski

  36. Roger S. Gaborski

  37. Roger S. Gaborski

  38. Roger S. Gaborski

  39. Homework #2 Assigned Roger S. Gaborski

  40. Four Lobes of Neocortex- Lateral view Dorsal Caudal Rostral Ventral Roger S. Gaborski

  41. Cortex Roger S. Gaborski

  42. Visual Cortex http://www.thebrain.mcgill.ca Roger S. Gaborski

  43. V1- Receptive fields sensitive to spatial frequency, orientation, motion, direction, speed coded in terms of local contrast • V2 – Receptive fields sensitive to orientation, spatial frequency, and color. Roger S. Gaborski

  44. V3, V4, V5 (MT) and IT • V3- receives connections from V2 and sends information to MT. RFs sensitive to orientation and some sensitivity to color and movement. • V4 – larger receptive fields, RFs sensitive to both color and orientation. • V5 – complex motion processing • IT - Inferotemporal cortex –receives connections from V4 and respond to a wide range of colors and simple geometric shapes. Key for object recognition Roger S. Gaborski

  45. Primary Cortex and Secondary Cortexes • Hierarchical relationships between a primary cortex and secondary cortexes • Secondary areas of these various cortexes then converge onto what are called associative areas • Associative areas perform a more global level of information processing. They progressively associate signals from other sensory modalities to create an integrated, multisensory representation of the world See: http://www.thebrain.mcgill.ca Roger S. Gaborski

  46. Processing Streams- Computational Function • Visual – ‘what’ and ‘where’ streams • Taste • Olfaction • Touch • Hearing Roger S. Gaborski

  47. Processing Streams • Ventral Stream (the ‘what’ stream’) • V1  V2 V4  posterior then anterior inferior temporal visual cortex • What is the object being viewed, independent of location or size on the retina Roger S. Gaborski

  48. What Happens in the Ventral Stream? • Build a representation of the object • Invariance • Interface visual representation with other sensory systems to form associations • Amygdala- learn associations between sight of food and its taste Roger S. Gaborski

  49. Processing StreamsDorsal Stream • Dorsal Stream (the ‘where stream’) • V1  MT, MST, then parietal cortex • Where is the object with respect to the animal • What is the motion of the object • Outputs: • control eye movements • Prefrontal cortex short term memory Roger S. Gaborski

  50. philosophy.hku.hk/courses/cogsci/ncc.php Roger S. Gaborski

More Related