1 / 52

Isoluminant Colors

Color2Gray: Salience-Preserving Color Removal Amy A. Gooch Sven C. Olsen Jack Tumblin Bruce Gooch. Visually important image features often disappear when color images are converted to grayscale . Isoluminant Colors. Color. Grayscale. Photoshop Grayscale. Traditional Methods.

acacia
Download Presentation

Isoluminant Colors

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-PreservingColorRemovalAmy A. GoochSven C. OlsenJackTumblinBruceGooch

  2. Visually important image features often disappear when color images are converted to grayscale.

  3. Isoluminant Colors Color Grayscale

  4. Photoshop Grayscale Traditional Methods • Contrast enhancement & Gamma Correction • Doesn’t help with isoluminant values PSGray + Auto Contrast New Algorithm

  5. Simple Linear Mapping Luminance Axis

  6. Luminance Axis Principal Component Analysis (PCA)

  7. Problem with PCA Worst case: Isoluminant Colorwheel

  8. Non-linear mapping

  9. we want digital images to preserve a meaningful visual experience, even in grayscale.

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

  11. Challenge:Many Color2Gray Solutions Original . . .

  12. preserve the salient features of the color image The algorithm introduced here reduces such losses by attempting to preserve the salient features of the color image. The Color2Gray algorithm is a 3-step process: • convert RGB inputs to a perceptually uniform CIE L∗a∗b∗ color space, • use chrominance and luminance differences to create grayscale target differences between nearby image pixels, and • solve an optimization problem designed to selectively modulate the grayscalerepresentation as a function of the chroma variation of the source image. The Color2Gray results offer viewers salient information missing from previous grayscale image creation methods.

  13. Parameters • θ: controls whether chromatic differences are mapped to increases or decreases in luminance value (Figure 5). • α: determines how much chromatic variation is allowed to change the source luminance value (Figure 6). • μ: sets the neighborhood size used for chrominance estimation and luminancegradients (Figure 7).

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

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

  16. q = 45 q = 225 Photoshop Grayscale

  17. q = 135 q = 45 q = 0 Grayscale

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

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

  20. 120, 120 100 a -a crunch(x) = a * tanh(x/a) 0 -120, -120 How to CombineChrominance and Luminance DLij if |DLij| > crunch(||DCij||) d (a)ij = crunch(||DCij||)

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

  22. 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

  23. Validate "Salience Preserving" Original PhotoshopGrey Color2Grey Apply Contrast Attention model by Ma and Zhang 2003

  24. Validate "Salience Preserving" Original PhotoshopGrey Color2Grey

  25. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 32, NO. 9, SEPTEMBER 2010Color to Gray: Visual Cue PreservationMingli Song, Member, IEEE, DachengTao, Member, IEEE, ChunChen,Xuelong Li, Senior Member, IEEE, and Chang Wen Chen, Fellow, IEEE • algorithm based on a probabilistic graphical model with the assumption that the image is defined over a Markov random field. • color to gray procedure can be regarded as a labeling process to preserve the newly well-defined visual cues of a color image in the transformed gray-scale image • three cues are defined namely, color spatial consistency, image structure information, and color channel perception priority • visualcuepreservation procedure based on a probabilistic graphical model and optimize the model based on an integral minimization problem.

  26. Colorization: History • Hand tinting • http://en.wikipedia.org/wiki/Hand-colouring

  27. Colorization: History • Film colorization • http://en.wikipedia.org/wiki/Film_colorization Colorization in 2004 Colorization in 1986

  28. Colorization by example • Colorization using “scribbles”

  29. R.Irony, D.Cohen-Or, D.Lischinski EurographicsSymposium on Rendering (2005) Colorization by example

  30. Motivation • Colorization, is the process of adding color to monochrome images and video. • Colorization typically involves segmentation + tracking regions across frames - neither can be done reliably– user intervention required– expensive + time consuming • Colorization by example – no need for accurate segmentation/region tracking

  31. The method • Colorize a grayscale image based on a user provided reference. Reference Image

  32. Naïve MethodTransferring color to grayscale images [Walsh, Ashikhmin, Mueller 2002] • Find a good match between a pixel and its neighborhood in a grayscale image and in a reference image.

  33. By Example Method

  34. Overview • training • classification • color transfer

  35. Training stage Input: 1. The luminance channel of the reference image 2. The accompanying partial segmentation Construct a low dimensional feature space in which it is easy to discriminate between pixels belonging to differently labeled regions, based on a small (grayscale) neighborhood around each pixel.

  36. Training stage Create Feature Space (get DCT cefficients)

  37. Classification stage For each grayscale image pixel, determine which region should be used as a color reference for this pixel. One way: K-Nearest –Neighbor RuleBetter way: KNN in discriminating subspace.

  38. KNN in discriminating subspace Originaly sample point has a majority of Magenta

  39. KNN in discriminating subspace Rotate Axes in the direction of the intra-difference vector

  40. KNN in discriminating subspace Project Points onto the axis of the inter-difference vector Nearest neigbors are now cyan

  41. KNN Differences Classification Matching Use a median filter to create a cleaner classification Simple KNN Discriminating KNN

  42. Color transfer Using YUV color space

More Related