Color Image Processing

Transcription

1 Color Image Processing Dr. Praveen Sankaran Department of ECE NIT Calicut February 11, 2013 Winter 2013 February 11, / 23

2 Outline 1 Color Models 2 Full Color Image Processing Winter 2013 February 11, / 23

3 Color Models The Prism Perception of color depends on wavelength reected from the object + luminance wavelength. Winter 2013 February 11, / 23

4 Color Models Primary Colors No single wavelength may be called red, green or blue. Again approximation! Secondary colors magenta (red + blue), cyan (green + blue) and yellow (red + green). The above is for the light, the order is reversed for the pigment (which would absorb a primary and reect other two). Winter 2013 February 11, / 23

5 Color Models Quality of Chromatic Light 1 Radiance: total amount of energy that ows from the light source (Watts). 2 Luminance: amount of energy an observer perceives from a light source (Lumens). 3 Brightness: Intensity. Winter 2013 February 11, / 23

6 Color Models Distinguishing Color 1 Brightness 2 Hue: dominant wavelength in a mixture of light waves. Dominant wavelength as perceived by an observer. Color as we represent, red or yellow refers to the hue. 3 Saturation: the amount of white light mixed with a hue. degree of saturation inversely proportional to the amount of white light. Winter 2013 February 11, / 23

7 Color Models Chromaticity Amount of red (X), green (Y) and blue (Z) needed to form any color tristimulus values. Trichromatic coecients X x = X + Y + Z Y y = X + Y + Z Z z = X + Y + Z (1) (2) (3) x + y + z = 1 (4) Winter 2013 February 11, / 23

8 Color Models Chromaticity Diagram White point of equal energy, corresponds to equal fractions of the three primary colors. Winter 2013 February 11, / 23

9 Color Models RGB Based on Cartesian coordinate system. RGB primary values at 3 corners. Secondary values at other 3 corners. 24 bit cube = ( 2 8) 3 colors. Winter 2013 February 11, / 23

10 Color Models Generating RGB Image Winter 2013 February 11, / 23

11 Color Models CMY (Cyan, Magenta, Yellow) and CMYK (Black) Assume all color values in range [0,1]. C 1 R M = 1 G (5) Y 1 B CMYK has an additional color dene - black. Mostly for printing since mixing C, M, Y gives a muddy black. Winter 2013 February 11, / 23

12 Color Models HSI (Hue, Saturation, Brightness) Intensity: pass a perpendicular plane to the intensity axis joining [0,0,0] and [1,1,1]. The plane should contain the point under consideration. Hue: Form a plane with intensity axis as an edge and cyan point as one corner. The corner point in this plane can be moved around keeping the axis constant. All points contained in the plane has the same hue. Winter 2013 February 11, / 23

13 Color Models Color Spaces Example Winter 2013 February 11, / 23

14 Full Color Image Processing Classication Each component image separately. form a processed output color image from the individual components. use standard gray-scale image processing methods. Work with color pixels as vectors. R c = = G (6) B c R c G c B c R [x, y] R [x, y] c[x, y] = c G [x, y] = G [x, y] (7) c B [x, y] B [x, y] x = 0,1,, M 1; y = 0,1,, N 1 Winter 2013 February 11, / 23

15 Full Color Image Processing Are they same? Process has to be applicable to both scalars and vectors. Operation on each component of a vector must be independent of the other components. Any given process depending on the above criteria may produce same result or not for the two types of processing. Winter 2013 February 11, / 23

16 Full Color Image Processing Color Transformations s i and r i denote color components. i = 1,, n. n denotes the number of channels. RGB n = 3. s i = T i (r i ) (8) The type of transformation to obtain the same result varies in dierent color models. have to take into account the model you are working in and then choose your transformation function. some functions easier and better in some models. Winter 2013 February 11, / 23

17 Full Color Image Processing Example - Adjust Intensity HSI s 3 = kr 3 (9) RGB: Modify all three components s i = kr i (10) CMY 0 < k < 1 s i = kr i + (1 k) (11) Winter 2013 February 11, / 23

18

19 Full Color Image Processing Histogram Processing Dierent color components NOT independent. Approach Convert to HSI model. Leave Hue as such. Change intensity. Adjust Saturation. Winter 2013 February 11, / 23

20

21 Full Color Image Processing Color Image Smoothing 1 Refer equation 6. 2 Recall spatial ltering in gray scale image. Averaging Consider neighborhood S xy, c [x, y] = 1 c[s, t] = K s,t S xy 1 K 1 K 1 K R [s, t] s,t S xy G [s, t] s,t S xy B [s, t] s,t S xy (12) Independently smoothing each plane of the RGB image using conventional gray scale neighborhood processing. Winter 2013 February 11, / 23

22 Full Color Image Processing Color Image Sharpening Laplacian 2 R [x, y] 2 [c[x, y]] = 2 G [x, y] (13) 2 B [x, y] Winter 2013 February 11, / 23

23 Assignment 5 OpenCV has a function to convert between BGR to HSV. Image read in is in the BGR format. Note here the usage order of channels. You can make use of this function to convert between color models. 1 Perform image smoothing using an averaging 5 5 window. You will perform spatial averaging in two ways on a color image. 1 Apply lter on the three separate channels, then display the resulting image. 2 Apply lter on the intensity channel (third one) of the HSV model. Diplay the image. 3 Now compute the dierence between the two images and display the dierence image. 2 Perform image sharpening with a 3 3 Laplacian lter. 1 Apply lter on the three separate channels, then display the resulting image. 2 Apply lter on the intensity channel (third one) of the HSV model. Diplay the image. 3 Now compute the dierence between the two images and display the dierence image.