ECE 563 Assignment 6

Images and m-files for this assignment may be downloaded from impro6.zip.

Individual Work

  1. Take your scanned photograph from previous assignments and display its components as shown in these examples.

  2. Use rgb2hsv and hsv2rgb to rotate the hues of your scanned color photograph by 120-degrees (both directions).

  3. Change your scanned image from RGB to BRG. That is display red as green, green as blue, and blue as red. Compare the resulting false color image to those produced in the previous problem.

  4. Convert your color photograph to XYI coordinates. Plot the co-histogram of the XY coordinates.

Group Projects

  1. Do problems 6-15, 6-16, 6-17, and 6-19 from the textbook.

  2. Do problems 6-21, 6-23, and 6-26 from the textbook.

  3. Compose the principal components images of the Landsat bands of Washington DC from the last assignment. Choose the three components with the largest eignevalues and generate a color (rgb) image from these images. Let the eigenvector with positive coefficients be the I component and the other eigenvectors be X and Y. Convert from XYI to RGB, and then rotate the hue to produce the most realistic looking pseudo-color image.

  4. Convert the Macbeth chart images to XYI coordinates. Plot the co-histogram of the XY coordinates. Partition the XY plane to identify regions for the 18 colored squares.

  5. Extract cropped portions of the Prang color wheel image and combine them into a single image. Convert this image to XYI coordinates, and plot the co-histogram of the XY coordinates. Do the color samples still form a "wheel"?

  6. Use D65 as a standard white, and the following set of NTSC primaries to find a conversion matrix between CIE (X,Y,Z) and NTSC (R,G,B).


    		xyz
    red0.670.330.00
    green0.210.710.08
    blue0.140.080.78

  7. Investigate the YCbCr color system, for which conversions are provided in Matlab. Describe the formulas behind the matlab program rgb2ycbcr.m. What assumptions are made about the RGB primaries? Look up YCbCr in the literature (check out the color FAQ for a start). Where is YCbCr used in current technology? Finally, display the Y, Cb, and Cr components of an RGB image. Note that Cb and Cr are bipolar.

  8. Convert the following images of fruit to XYI, plot the co-histogram (and grayscale histogram). Now pick a characteristic color (perhaps by averaging the colors in a small region) of an apple and an orange. Generate grayscale images for the Euclidian distance and Mahalanobis distance from those characteristic colors. Find the best threshold that selects the regions most "apple-like" or "orange-like".

    fruit2441.jpgfruit2442.jpg

  9. Given the program colorseg from DIPUM, apply the algorithm to the problem of distinguishing apples and oranges in the previous exercise.

Maintained by John Loomis, last updated 14 Feb 2005