close

Вход

Забыли?

вход по аккаунту

?

Salience-Preserving Color Removal

код для вставкиСкачать
Color2Gray:
Salience-Preserving Color Removal
Amy Gooch
Sven Olsen
Jack Tumblin
Bruce Gooch
New Algorithm
Color
Grayscale
Problem
Volume of displayable CIE L*a*b* Colors
QuickTimeв„ў and a
Sorenson Video 3 decompressor
are needed to see this picture.
Isoluminant Colors
Color
Grayscale
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…..
Traditional Methods:
Luminance Channels
Problem can not be solved by
CIE CAM
Photoshop
simply97switching to a different
spaceLAB
CIE XYZ
YCrCb
Traditional Methods
• Contrast enhancement &
Gamma Correction
– Doesn’t help with isoluminant values
Photoshop Grayscale
PSGray + Auto Contrast
New Algorithm
Simple Linear Mapping
Principal Component
Analysis (PCA)
Luminance Axis
Problem with PCA
Worst case:
Isoluminant Colorwheel
Non-linear mapping
Contemporaneous Research
• Rasche et al. [2005, IEEE CG&A and EG]
Color Image
Luminance Only
Rasche et al.'s Method
Goals
• Dimensionality Reduction
– From tristimulus values to single channel
Loss of information
• Maintain salient features in color image
– Human perception
Relative differences
Color Illusion by
Lotto and Purves
http://www.lottolab.org
Challenge 1:
Influence of neighboring pixels
Challenge 2:
Dimension and Size Reduction
120, 120
100
0
-120, -120
Challenge 3:
Many Color2Gray Solutions
Original
.
.
.
Algorithm Intuition
color2gray
For first pixel
Look
at DC
1
2
i = 1, j = 2
luminance
L1 L
+ 1e1,2
..
.
LL22
L1 + e1,2
For Nth pixel
Look
at DC
L1
L2
L1
L2L+2 e2,1
L2 + e2,1
Algorithm Overview
• Convert to Perceptually Uniform Space
– CIE L*a*b*
• 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
Color2Grey Algorithm
Optimization:
i+m
min
SS
i
j=i-m
2
( (gi - gj) - di,j )
Parameters
m : Radius of neighboring pixels
a : Max chrominance offset
q : Map chromatic difference to increases or decreases in
luminance values
m : Neighborhood Size
q= 300o
a = 10
m=2
m = 16
m= entire image
q= 49o
a = 10
m : Neighborhood Size
m = 16
m= entire image
a: Chromatic variation maps
to luminance variation
a
-a
a=5
crunch(x) = a * tanh(x/a)
a = 10
a = 25
Perceptual Distance
• Luminance Distance:
DLij = Li - Lj
• Chrominance Distance: ||DCij||
Problem: ||DCij|| is unsigned
Map chromatic difference to increases or
decreases in luminance values
+b*
C2
-a*
+a*
C1
Color
Space
Color
Difference
Space
+DC1,2
-
+Db*
vq = (cos q, sin q)
+
vq
q
-Da*
+Da*
-Db*
+
sign(||DCi,j||) = sign(DCi,j
.
vq )
q = 45
q = 225
Photoshop Grayscale
q = 135
q = 45
q=0
Grayscale
How to Combine
Chrominance and Luminance
dij =
DLij
(Luminance)
How to Combine
Chrominance and Luminance
DLij
(Luminance)
||DCij||
(Chrominance)
dij =
if |DLij| > ||DCij||
How to Combine
Chrominance and Luminance
DLij
if |DLij| > crunch(||DCij||)
d (a) ij =
crunch(||DCij||)
120, 120
100
a
-a
crunch(x) = a * tanh(x/a)
0
-120, -120
How to Combine
Chrominance and Luminance
d(a,q)ij =
DLij
if |DLij| > crunch(||DCij||)
crunch(||DCij||)
if DCij . nq ≥ 0
crunch(-||DCij||)
otherwise
.
.
.
Grayscale
Color2Grey Algorithm
Optimization:
i+m
min
SS
i
j=i-m
2
( (gi - gj) - di,j )
If dij == DL then ideal image is g
Otherwise, selectively modulated by DCij
Results
Original
Photoshop
Grey
Color2Grey
Color2Grey
+ Color
Original
PhotoshopGrey
Color2Grey
Color2Grey+Color
Original
PhotoshopGrey
Color2Grey
Original
PhotoshopGrey
Color2Grey
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
Athlon 64 3200 CPU
• 204.0s 200x200 image
– GPU implementation
• O(S2) ideal, really O(S3)
– 2.8s 100x100
– 9.7s 150x150
– 25.7s 200x200
NVIDIA GeForce GT6800
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
Validate "Salience Preserving"
Original
PhotoshopGrey
Color2Grey
Apply Contrast Attention model by Ma and Zhang 2003
Validate "Salience Preserving"
Original
PhotoshopGrey
Color2Grey
Thank you
• SIGGRAPH Reviewers
www.color2gray.info
• NSF
• Helen and Robert J. Piros Fellowship
• Northwestern Graphics Group
• MidGraph2004 Participants
– especially Feng Liu
• (sorry I spelled your name wrong in the acknowledgements)
Original
Color2Grey
Color2Grey+Color
Original
Color2Grey
Color2Grey+Color
Original
Color2Grey
Color2Grey+Color
Original
PhotoshopGrey
Color2Grey
Original
Color2Grey
Color2Grey+Color
Original
PhotoshopGrey
Color2Grey
Original
Color2Grey
Color2Grey+Color
Photoshop Grayscale
Photoshop Grayscale
Rasche et al.
Photoshop Grayscale
Rasche et al.
Photoshop Grayscale
Rasche et al.
Photoshop Grayscale
Parameter a
a=5
a = 55
a = 15
a = 65
a = 25
a = 35
a = 45
a = 75
a = 85
a = 95
Документ
Категория
Презентации
Просмотров
8
Размер файла
8 145 Кб
Теги
1/--страниц
Пожаловаться на содержимое документа