06-3 - Color image processing

06-3 - Color image processing - 4/28/2008 Color image...

Info iconThis preview shows pages 1–6. Sign up to view the full content.

View Full Document Right Arrow Icon
4/28/2008 1 C o l o r image processing: Color transformations Spring 2008 ELEN 4304/5365 DIP 1 by Gleb V. Tcheslavski: gleb@ee.lamar.edu http://ee.lamar.edu/gleb/dip/index.htm Formulation Here, a color transformation refers to processing of components of a color image within a single color model (opposing to converting images from one color model to another). We model color transformations as [ ] (, ) g x y T f x y = Processes (output) color image Input color image Here T is an operator on f over a spatial Spring 2008 ELEN 4304/5365 DIP 2 neighborhood of ( x , y ). Note that pixel values here are triplets or quartets from the color-space chosen.
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
4/28/2008 2 Formulation We restrict attention to color transformations of the form: 12 ( , ,. .., ), 1,2,. .., ii n s Trr r i n = = where r i and s i are the variables denoting the color components of f ( x,y ) and g ( x,y ) at any point ( x,y ); n is the number of color components; and { T 1 , T 2 , T n } is a set transformation ( color mapping ) functions that operate on r i to produce s i . The value of n is determined by the color-space chosen to describe Spring 2008 ELEN 4304/5365 DIP 3 the pixels of f and g . For instance, in the RGB space, n = 3 and r 1 , r 2 , and r 3 denote the red, green, and blue components of the input image. Formulation CMYK components: Black – 0, white – 1. RGB component images HSI component Spring 2008 ELEN 4304/5365 DIP 4 HSI component images: 1 is a discontinuity where 0 0 and 360 0 meet (berries)
Background image of page 2
4/28/2008 3 Useful processings color balance (after digitization) saturation enhancement (intensity boost) hue alteration (cool/warm) colorization (gray LUT > color LUT) restoration Spring 2008 ELEN 4304/5365 DIP 5 Formulation Any of the color-space components can be used with the transformation function. Theoretically, any transformation can be performed in any color model. In practice, some operations are better suited for a specific color model. Suppose, for instance, that we need to modify the intensity of a full-color image by (, ) gxy k f xy = where 0 < k < 1. In the HSI color space it can be done by 33 s kr = Spring 2008 ELEN 4304/5365 DIP 6 where s 1 = r 1 and s 2 = r 2 . Only the intensity component needs to be modified. In the RGB color-space: 1, 2, 3 ii sk r i = =
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
4/28/2008 4 Formulation (1 ) 1, 2, 3 ii sk r k i = + = In the CMY color-space: Although the HSI transformation involves much less operations, conversion of the image to HSI model requires considerable computations Regardless the color- Spring 2008 ELEN 4304/5365 DIP 7 model, the result must be the same: the original, the result of decreasing intensity ( k = 0.7), and the transformation functions. Color complements BTW: Transformations considered so far affect each color component independently and can be done on a per-color-component basis… The hues directly opposite one another on the color circle are called complements . Color complements are analogous to the gray-scale Spring 2008 ELEN 4304/5365 DIP 8 negatives and can be used for enhancing details embedded in dark regions of a color image.
Background image of page 4
4/28/2008 5 Color complements Original image, complement transformation functions, and color complements based on RGB and HSI mappings.
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 6
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 22

06-3 - Color image processing - 4/28/2008 Color image...

This preview shows document pages 1 - 6. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online