Color2Gray: Salience-Preserving Color Removal

1
Color2Gray Salience-Preserving Color Removal

• Amy Gooch
• Sven Olsen
• Jack Tumblin
• Bruce Gooch

2
(No Transcript)
3
Problem
Volume of displayable CIE Lab 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
Traditional Methods

• Contrast enhancement Gamma Correction
• Doesnt help with isoluminant values

PSGray Auto Contrast
New Algorithm
8
Simple Linear Mapping
Luminance Axis
9
Principal Component Analysis (PCA)
10
Problem with PCA
Worst case Isoluminant Colorwheel
11
Non-linear mapping
12
Contemporaneous Research

• Rasche et al. 2005, IEEE CGA and EG

Color Image
Luminance Only
Rasche et al.'s Method
13
Goals

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

14
Relative differences
Color Illusion by Lotto and Purves
http//www.lottolab.org
15
Challenge 1Influence of neighboring pixels
16
Challenge 2Dimension and Size Reduction
120, 120
100
0
-120, -120
17
Challenge 3Many Color2Gray Solutions
Original
. . .
18
Algorithm Intuition
Look at DC
. . .
i 1, j 2
luminance
Look at DC
19
Algorithm Overview

• Convert to Perceptually Uniform Space
• CIE Lab

• Initialize image, g, with L channel

• For every pixel
• Compute Luminance distance
• Compute Chrominance distance

dij

• Adjust g to incorporate both luminance and
  chrominance differences

20
Color2Grey Algorithm

• Optimization
• min S S ( (gi - gj) - di,j )2

im
i
ji-m
21
Parameters
m
Radius of neighboring pixels
a

• Max chrominance offset

q

• Map chromatic difference to increases or
  decreases in luminance values

22
m Neighborhood Size

• 300o
• a 10

m 2
m 16

• entire image

• 49o
• a 10

23
m Neighborhood Size
m 16

• entire image

24
a Chromatic variation maps to luminance
variation
a
-a
crunch(x) a tanh(x/a)
a 5
a 10
a 25
25
Perceptual Distance
DLij Li - Lj

• Luminance Distance

• Chrominance Distance DCij

Problem DCij is unsigned
26
Map chromatic difference to increases or
decreases in luminance values
b
C2
a
-a
Color Space
C1
27
Db
Color Difference Space
DC1,2
vq (cos q, sin q)

-
vq
q
Da
-Da

-
sign(DCi,j) sign(DCi,j . vq )
-Db
28
q 45
q 225
Photoshop Grayscale
29
q 45
q 135
q 0
Grayscale
30
How to CombineChrominance and Luminance
dij
(Luminance)
DLij
31
How to CombineChrominance and Luminance
(Luminance)
if DLij gt DCij
DLij
dij
DCij
(Chrominance)
32
How to CombineChrominance and Luminance
DLij
if DLij gt crunch(DCij)
d (a) ij
crunch(DCij)
33
How to CombineChrominance and Luminance
DLij
if DLij gt crunch(DCij)
d(a,q)ij
if DCij . nq 0
crunch(DCij)
otherwise
crunch(-DCij)
34
Color2Grey Algorithm

• Optimization
• min S S ( (gi - gj) - di,j )2

im
ji-m
i
If dij DL then ideal image is g Otherwise,
selectively modulated by DCij
35
Results
Photoshop Grey
Original
Color2Grey
36
(No Transcript)
37
Original
PhotoshopGrey
Color2Grey
38
Original
PhotoshopGrey
Color2Grey
39
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
40
Future Work

• Faster
• Multiscale

• Smarter
• Remove need to specify q
• New optimization function designed to match both
  signed and unsigned difference terms
• Image complexity measures

• Animations/Video

41
Validate "Salience Preserving"
Original
PhotoshopGrey
Color2Grey
Apply Contrast Attention model by Ma and Zhang
2003
42
Validate "Salience Preserving"
Original
PhotoshopGrey
Color2Grey
43
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)

44
(No Transcript)
45
Original
Color2Grey
Color2GreyColor
46
Original
Color2Grey
Color2GreyColor
47
Color2Grey
Original
Color2GreyColor
48
Original
PhotoshopGrey
Color2Grey
49
Original
Color2Grey
Color2GreyColor
50
Original
PhotoshopGrey
Color2Grey
51
Original
Color2Grey
Color2GreyColor
52
Photoshop Grayscale
53
Photoshop Grayscale
54
Rasche et al.
Photoshop Grayscale
55
Rasche et al.
Photoshop Grayscale
56
Rasche et al.
Photoshop Grayscale
57
Parameter a
a 5
a 15
a 25
a 35
a 45
a 55
a 65
a 75
a 85
a 95