![Page 1: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/1.jpg)
Color
Based on Kristen Grauman's Slides for Computer Vision
![Page 2: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/2.jpg)
Today• Color Spaces
• Perception of color– Human photoreceptors– Environmental effects, adaptation
• Color in Graphics and Programming
![Page 3: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/3.jpg)
What is color?
• The result of interaction between physical light in the environment and our visual system.
• A psychological property of our visual experiences when we look at objects and lights, not a physical property of those objects or lights.
Slide credit: Lana Lazebnik
![Page 4: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/4.jpg)
Color and light
• Color of light arriving at camera depends on– Spectral reflectance of the surface light is leaving– Spectral radiance of light falling on that patch
• Color perceived depends on– Physics of light– Visual system receptors– Brain processing, environment
![Page 5: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/5.jpg)
Color and light
Newton 1665
Image from http://micro.magnet.fsu.edu/
White light: composed of almost equal energy in all wavelengths of the visible spectrum
![Page 6: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/6.jpg)
Image credit: nasa.gov
Electromagnetic spectrum
Human Luminance Sensitivity Function
Typical Grayscale conversion:Gray = 0.3 * R + 0.59 * G + .11 * BNOTGray = R / 3 + G / 3 + B / 3
![Page 7: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/7.jpg)
Measuring spectra
Foundations of Vision, B. Wandell
Spectroradiometer: separate input light into its different wavelengths, and measure the energy at each.
![Page 8: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/8.jpg)
The Physics of Light
Any source of light can be completely describedphysically by its spectrum: the amount of energy emitted (per time unit) at each wavelength 400 - 700 nm.
© Stephen E. Palmer, 2002
400 500 600 700
Wavelength (nm.)
# Photons(per ms.)
Relativespectral
power
![Page 9: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/9.jpg)
Spectral power distributions
.
# P
ho
ton
s
D. Normal Daylight
Wavelength (nm.)
B. Gallium Phosphide Crystal
400 500 600 700
# P
ho
ton
s
Wavelength (nm.)
A. Ruby Laser
400 500 600 700
400 500 600 700
# P
ho
ton
s
C. Tungsten Lightbulb
400 500 600 700
# P
ho
ton
s
Some examples of the spectra of light sources
© Stephen E. Palmer, 2002
![Page 10: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/10.jpg)
Spectral power distributions
More examples of the spectra of light sources
© Stephen E. Palmer, 2002
fluorescent bulb incandescent bulb
![Page 11: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/11.jpg)
Surface reflectance spectra
Some examples of the reflectance spectra of surfaces
Wavelength (nm)
% P
hoto
ns R
efle
cted
Red
400 700
Yellow
400 700
Blue
400 700
Purple
400 700
© Stephen E. Palmer, 2002
![Page 12: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/12.jpg)
Color mixing
Source: W. Freeman
![Page 13: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/13.jpg)
Additive color mixing
Colors combine by adding color spectra
Light adds to existing black.
Source: W. Freeman
![Page 14: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/14.jpg)
Examples of additive color systems
http://www.jegsworks.com
http://www.crtprojectors.co.uk/
CRT phosphors
multiple projectors
![Page 15: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/15.jpg)
Subtractive color mixing
Colors combine by multiplying color spectra.
Pigments remove color from incident light (white).
Source: W. Freeman
![Page 16: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/16.jpg)
Examples of subtractive color systems
• Printing on paper
• Crayons
• Photographic film
![Page 17: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/17.jpg)
STANDARD COLOR SPACES
![Page 18: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/18.jpg)
Standard Color Spaces
• Named Colors– Hundreds– About 800 on Wikipedia "List of Colors"
• Model or Color Space exists to handle the large number of colors possible
![Page 19: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/19.jpg)
Standard color spaces
• Linear color space– RGB (RED - GREEN - BLUE)
• Non-linear color space– HSV (HUE - SATURATION - VALUE)
![Page 20: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/20.jpg)
HSV color space• Hue, Saturation, Value• Nonlinear – reflects topology of colors by coding
hue as an angle• Java:
– public static Color getHSBColor(float h, float s, float b)– public static float[] RGBtoHSB(int r, int g, int b,
float[] hsbvals)– public Color(int r, int g, int b)
Kristen Grauman
![Page 21: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/21.jpg)
RGB color space• Single wavelength primaries• Good for devices (e.g., phosphors for monitor)
RGB color matching functions
![Page 22: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/22.jpg)
Defining RGB Colors forComputing
• specify intensity of red, green, and blue components
• typical range of intensity 0 - 255
• 256 * 256 * 256 = 16,777,216 potential colors, 24 bit color
• Additive color– (0, 0, 0) = Black– (255, 255, 255) = White– (255, 0 , 255) = ? (255, 140, 0) = ?
![Page 23: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/23.jpg)
RGB Colors• RGB values in a Color Picker• www.colorblender.com• www.colorpicker.com• Colors often expressed in hexadecimal• base 16
– digits, 0 - 9, A - F– 2 digits per color– Cardinal = C41E3A = (196, 30, 58)– 1E = 1 * 16 + 14 * 1 = 30
![Page 24: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/24.jpg)
Color In Java
• java.awt.Color• RGBa color model• 13 named constants• Multiple constructors• Also an alpha value
– Introduced by Alvy Ray Smith (member of LucasArts computer group)
– express level of transparency / opacity – 0 = transparent, 255 = fully opaque
![Page 25: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/25.jpg)
Color in Java
• 0 - 255 for intensity of RGB and Alpha
• additive color model
• bit packing, bitwise operators
![Page 26: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/26.jpg)
Sample Programs
• ColorExample– ColorPanel– AlphaColorPanel
• ColorChooserMain– Main - Frame - 2 Panels– JColorChooser class built in to Java– http://docs.oracle.com/javase/tutorial/uiswing/
components/colorchooser.html
![Page 27: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/27.jpg)
COLOR PERCEPTION
![Page 28: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/28.jpg)
Color and light
• Color of light arriving at camera depends on– Spectral reflectance of the surface light is leaving– Spectral radiance of light falling on that patch
• Color perceived depends on– Physics of light– Visual system receptors– Brain processing, environment
![Page 29: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/29.jpg)
The Eye
The human eye is a camera!• Iris - colored annulus with radial muscles
• Pupil - the hole (aperture) whose size is controlled by the iris
• Lens - changes shape by using ciliary muscles (to focus on objects at different distances)
• Retina - photoreceptor cells
Slide by Steve Seitz
![Page 30: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/30.jpg)
© Stephen E. Palmer, 2002
Cones cone-shaped less sensitive operate in high light color vision
Types of light-sensitive receptors
cone
rod
Rods rod-shaped highly sensitive operate at night gray-scale vision
Slide credit: Alyosha Efros
![Page 31: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/31.jpg)
• React only to some wavelengths, with different sensitivity (light fraction absorbed)
• Brain fuses responses from local neighborhood of several cones for perceived color
• Sensitivities vary per person, and with age
• Color blindness: deficiency in at least one type of cone
Wavelength (nm)
Sen
sitiv
ity
Three kinds of cones
Types of cones
![Page 32: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/32.jpg)
Possible evolutionary pressure for developing receptors for different wavelengths in primates
Osorio & Vorobyev, 1996
Types of cones
![Page 33: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/33.jpg)
Trichromacy
• Experimental facts:
– Three primaries will work for most people if we allow subtractive matching; “trichromatic” nature of the human visual system
– Most people make the same matches for a given set of primaries (i.e., select the same mixtures)
![Page 34: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/34.jpg)
Environmental effects & adaptation
• Chromatic adaptation:
– We adapt to a particular illuminant
• Assimilation, contrast effects, chromatic induction:
– Nearby colors affect what is perceived; receptor excitations interact across image and time
• Afterimages
Color matching != color appearance
Physics of light != perception of light
![Page 35: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/35.jpg)
Chromatic adaptation
• If the visual system is exposed to a certain illuminant for a while, color system starts to adapt / skew.
![Page 36: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/36.jpg)
Chromatic adaptation
http://www.planetperplex.com/en/color_illusions.html
![Page 37: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/37.jpg)
Brightness perception
Edward Adelson
http://web.mit.edu/persci/people/adelson/illusions_demos.html
![Page 38: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/38.jpg)
Edward Adelson
http://web.mit.edu/persci/people/adelson/illusions_demos.html
![Page 39: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/39.jpg)
Edward Adelson
http://web.mit.edu/persci/people/adelson/illusions_demos.html
![Page 40: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/40.jpg)
• Content © 2008 R.Beau Lotto • http://www.lottolab.org/articles/illusionsoflight.asp
Look at blue squares
Look at yellow squares
![Page 41: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/41.jpg)
• Content © 2008 R.Beau Lotto • http://www.lottolab.org/articles/illusionsoflight.asp
![Page 42: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/42.jpg)
• Content © 2008 R.Beau Lotto • http://www.lottolab.org/articles/illusionsoflight.asp
![Page 43: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/43.jpg)
• Content © 2008 R.Beau Lotto • http://www.lottolab.org/articles/illusionsoflight.asp
![Page 44: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/44.jpg)
• Content © 2008 R.Beau Lotto • http://www.lottolab.org/articles/illusionsoflight.asp
![Page 45: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/45.jpg)
• Content © 2008 R.Beau Lotto • http://www.lottolab.org/articles/illusionsoflight.asp
![Page 46: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/46.jpg)
After images• Tired photoreceptors send out negative
response after a strong stimulus
http://www.sandlotscience.com/Aftereffects/Andrus_Spiral.htm
Source: Steve Seitzhttp://www.michaelbach.de/ot/mot_adaptSpiral/index.html
![Page 47: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/47.jpg)
Name that color
High level interactions affect perception and processing.
![Page 48: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/48.jpg)
COLOR IN COMPUTER VISION
![Page 49: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/49.jpg)
Color as a low-level cue for CBIR
Blobworld systemCarson et al, 1999
Swain and Ballard, Color Indexing, IJCV 1991
![Page 50: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/50.jpg)
R G B• Color histograms:
Use distribution of colors to describe image
• No spatial info – invariant to translation, rotation, scale
Color intensity
Pix
el c
ou
nts
Color as a low-level cue for CBIR
Kristen Grauman
![Page 51: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/51.jpg)
Color-based image retrieval• Given collection (database) of images:
– Extract and store one color histogram per image
• Given new query image:– Extract its color histogram– For each database image:
• Compute intersection between query histogram and database histogram
– Sort intersection values (highest score = most similar)– Rank database items relative to query based on this
sorted order
Kristen Grauman
![Page 52: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/52.jpg)
Color-based image retrieval
Example database
Kristen Grauman
![Page 53: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/53.jpg)
Example retrievals
Color-based image retrieval
Kristen Grauman
![Page 54: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/54.jpg)
Example retrievals
Color-based image retrieval
Kristen Grauman
![Page 55: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/55.jpg)
![Page 56: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/56.jpg)
Color-based skin detection
M. Jones and J. Rehg, Statistical Color Models with Application to Skin Detection, IJCV 2002.
Kristen Grauman
![Page 57: Color Based on Kristen Grauman's Slides for Computer Vision](https://reader036.vdocuments.net/reader036/viewer/2022081515/56649dbf5503460f94ab3bbb/html5/thumbnails/57.jpg)
Color-based segmentation for robot soccer
Towards Eliminating Manual Color Calibration at RoboCup. Mohan Sridharan and Peter Stone. RoboCup-2005: Robot Soccer World Cup IX, Springer Verlag, 2006
http://www.cs.utexas.edu/users/AustinVilla/?p=research/auto_vis
Kristen Grauman