1 / 52

Color2Gray: Salience-Preserving Color Removal

Color2Gray: Salience-Preserving Color Removal. Amy Gooch Sven Olsen Jack Tumblin Bruce Gooch Northwestern University. Grayscale. Color. New Algorithm. Color Space. Volume of displayable CIE L*a*b* Colors. Isoluminant Colors. Color. Grayscale. Converting to Grayscale…. In Color Space

quamar-riley
Download Presentation

Color2Gray: Salience-Preserving Color Removal

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. Color2Gray: Salience-Preserving Color Removal Amy GoochSven OlsenJack TumblinBruce Gooch Northwestern University

  2. Grayscale Color New Algorithm

  3. Color Space Volume of displayable CIE L*a*b* Colors

  4. Isoluminant Colors Color Grayscale

  5. Converting to Grayscale… • In Color Space • Linear • Nonlinear • In Image Space • Pixels (RGB) • Using colors in the image • Different gray for different color • Relative difference • Using colors in the image and their position in image space • Colors can map to same gray…..

  6. Traditional Methods: Luminance Channels Problem can not be solved by simply switching to a different space CIE CAM 97 Photoshop LAB CIE XYZ YCrCb

  7. Simple Linear Mapping Luminance Axis

  8. Luminance Axis Principal Component Analysis (PCA)

  9. Contemporaneous Research • Rasche et al. [2005, IEEE CG&A and EG] Color Image Luminance Only Rasche et al.'s Method

  10. Goals • Dimensionality Reduction • From tristimulus values to single channel Loss of information • Maintain salient features in color image • Human perception

  11. Challenge 1:Influence of neighboring pixels

  12. Challenge 2:Dimension and Size Reduction 120, 120 100 0 -120, -120

  13. Challenge 3:Many Color2Gray Solutions Original . . .

  14. color2gray L1 + e1,2 L2 1 2 L1 + e1,2 L2 + e2,1 L2 + e2,1 L1 L1 L1 L1 L2 L2 L2 Algorithm Intuition Look at DC i = 1, j = 2 luminance Look at DC

  15. Algorithm Overview • Convert to Perceptually Uniform Space • CIE L*a*b* • Adjust g to incorporate both luminance and chrominance differences • Initialize image, g, with L channel • For every pixel • Compute Luminance distance • Compute Chrominance distance dij

  16. Color2Grey Algorithm Optimization: minSS ( (gi - gj) - di,j)2 i+m i j=i-m

  17. Parameters Map chromatic difference to increases or decreases in luminance values m : Radius of neighboring pixels a : Max chrominance offset q :

  18. m : Neighborhood Size • = 300o a = 10 m = 2 m = 16 • = entire image • = 49o a = 10

  19. m : Neighborhood Size m = 16 • = entire image

  20. a: Chromatic variation maps to luminance variation a -a crunch(x) = a * tanh(x/a) a = 5 a = 10 a = 25

  21. Perceptual Distance DLij = Li - Lj • Luminance Distance: • Chrominance Distance: ||DCij|| Problem: ||DCij|| is unsigned

  22. Map chromatic difference to increases or decreases in luminance values +b* C2 -a* +a* Color Space C1

  23. +Db* Color Difference Space +DC1,2 vq= (cos q, sin q) + - vq q -Da* +Da* + - sign(||DCi,j||) = sign(DCi,j .vq ) -Db*

  24. q = 45 q = 225 Photoshop Grayscale

  25. q = 135 q = 45 q = 0 Grayscale

  26. How to CombineChrominance and Luminance dij = DLij (Luminance)

  27. How to CombineChrominance and Luminance (Luminance) if |DLij| > ||DCij|| DLij dij = ||DCij|| (Chrominance)

  28. a -a crunch(x) = a * tanh(x/a) How to CombineChrominance and Luminance DLij if |DLij| > crunch(||DCij||) d (a)ij = crunch(||DCij||)

  29. Grayscale . . . How to CombineChrominance and Luminance DLij if |DLij| > crunch(||DCij||) d(a,q)ij = if DCij . nq ≥ 0 crunch(||DCij||) otherwise crunch(-||DCij||)

  30. Color2Grey Algorithm Optimization: minSS ( (gi - gj) - di,j)2 i+m i j=i-m If dij == DL then ideal image is g Otherwise, selectively modulated by DCij

  31. Color2Gray + Color Results Photoshop Gray Original Color2Gray

  32. Original PhotoshopGray Color2Gray Color2Gray+Color

  33. Original Photoshop Gray Color2Gray

  34. Original PhotoshopGrey Color2Grey

  35. Implementation Performance • Image of size S x S • O(m2 S2) or O(S4) for full neighborhood case • 12.7s 100x100 image • 65.6s 150x150 image • 204.0s 200x200 image • GPU implementation • O(S2) ideal, really O(S3) • 2.8s 100x100 • 9.7s 150x150 • 25.7s 200x200 Athlon 64 3200 CPU NVIDIA GeForce GT6800

  36. Future Work • Faster • Multiscale • Animations/Video • Smarter • Remove need to specify q • Image complexity measures

  37. Validate "Salience Preserving" Original PhotoshopGrey Color2Grey

  38. Validate "Salience Preserving" Original PhotoshopGray Color2Gray

  39. Thank you www.color2gray.info • SIGGRAPH Reviewers • NSF • Helen and Robert J. Piros Fellowship • Northwestern Graphics Group • MidGraph2004 Participants • especially Feng Liu • (sorry I spelled your name wrong in the acknowledgements)

  40. Original Color2Gray Color2Gray+Color

  41. Original Color2Gray Color2Gray+Color

  42. Color2Gray Original Color2Gray+Color

  43. Original Photoshop Gray Color2Gray

  44. Original Color2Gray Color2Gray+Color

  45. Original Photoshop Gray Color2Gray

  46. Original Color2Gray Color2Gray+Color

  47. Photoshop Grayscale

  48. Photoshop Grayscale

  49. Rasche et al. Photoshop Grayscale

  50. Rasche et al. Photoshop Grayscale

More Related