Color: CSE 803 Fall 2010 1
Color: CSE 803 Fall 2010 1
Used heavily in human vision Color is a pixel property, making some recognition problems easy Visible spectrum for humans is 400nm (blue) to 700 nm (red) Machines can see much more; ex. X-rays, infrared, radio waves
CSE 803 Fall 2010 1
Reflectance: ratio of reflected light to incoming light Specularity: Distance: Angle: * Sensitivity highly specular (shiny) vs. matte surface distance to the light source angle between surface normal and light source how sensitive is the sensor
CSE 803 Fall 2010 3
White light is composed of all visible frequencies (400-700) Ultraviolet and X-rays are of much smaller wavelength Infrared and radio waves are of much longer wavelength
CSE 803 Fall 2010
(Left) Image of food originating from a digital camera; (center) saturation value of each pixel decreased 20%; (right) saturation value of each pixel increased 40%.
CSE 803 Fall 2010 10
Separates out intensity I from the coding Two values (H & S) encode chromaticity Convenient for designing colors Hue H is defined by an angle Saturation S models the purity of the color S=1 for a completely pure or saturated color S=0 for a shade of gray
CSE 803 Fall 2010 11
Have better compression properties Luminance Y encoded using more bits than chrominance values I and Q; humans more sensitive to Y than I,Q NTSC TV uses luminance Y; chrominance values I and Q Luminance used by black/white TVs All 3 values used by color TVs YUV encoding used in some digital video and JPEG and MPEG compression
CSE 803 Fall 2010 12
13
Can cluster on color values and pixel locations Can use connected components and an approximate color criteria to find regions Can train an algorithm to look for certain colored regions for example, skin color
CSE 803 Fall 2010 14
16
Program learns white from training set of sample pixels. Aggregate similar neighbors to form regions. Components might be classified as characters. (Work contributed by David Moore.)
18
(left) input video frame (center) pixels classified according to RGB space (right) largest connected component with aspect similar to a face (all work contributed by Vera Bakic)
CSE 803 Fall 2010 19
Histogram is fast and easy to compute. Size can easily be normalized so that different image histograms can be compared. Can match color histograms for database query or classification.
CSE 803 Fall 2010
20
21
Make 3 histograms and concatenate them Create a single pseudo color between 0 and 255 by using 3 bits of R, 3 bits of G and 2 bits of B (which bits?) Can normalize histogram to hold frequencies so that bins total 1.0
CSE 803 Fall 2010 23
Separate HSI histograms for apples (left) and oranges (right) used by IBMs VeggieVision for recognizing produce at the grocery store checkout station (see Ch 16).
CSE 803 Fall 2010 24
Histograms: 8 x 16 x 16 = 2048 bins Intersection of image histogram and model histogram: intersection(h(I),h(M)) = min{h(I)[j],h(M)[j]}
j=1 numbins
numbins j=1
25
Models of Reflectance
We need to look at models for the physics of illumination and reflection that will 1. help computer vision algorithms extract information about the 3D world, and 2. help computer graphics algorithms render realistic images of model scenes. Physics-based vision is the subarea of computer vision that uses physical models to understand image formation in order to better analyze real-world images.
CSE 803 Fall 2010 26
27
28
29
Chrome car parts are very shiny/mirrorlike So are glass or ceramic objects And waxey plant leaves
30
Reasonable realism, reasonable computing Uses the following components (a) ambient light (b) diffuse reflection component (c ) specular reflection component (d) darkening with distance Components (b), (c ), (d) are summed over all light sources. Modern computer games use more complicated models.
CSE 803 Fall 2010
31
32
33