A quiz on image representation and processing in software

Adrian F. Clark

1. OpenCV was initially developed in

   • Australia

   • Russia

   • UK
   • USA

   Perhaps surprisingly to some, the early versions of OpenCV were developed in Russia, at Intel's research center in Nizhny Novgorod.

2. What range of values can be stored in an unsigned byte?

   • -127 -- +127
   • 0 -- 256

   • 0 -- 255

   • -128 -- +127

   An unsigned byte represents 256 distinct values, namely 0, 1,... 255.

3. Why are digital images usually rectangularly-sampled?

   • because of the way images are formed on photographic film
   • because it is impossible to make hexagonally-spaced CCDs
   • because that is a better match for the human eye's rods and cones

   • because they are easier to process with a computer

   Digital images are most easily processed by computer if they are rectangularly-sampled, as ordinary 2D arrays can be used. The rods and cones in the human eye are tightly-packed, which makes them approximately hexagonally-sampled. Hexagonally-sampled CCDs are entirely feasible and are used, for example, on some Fujifilm digital cameras. Finally, photographic film forms images in a purely analogue way, so there is no sampling involved at all.

4. After contrast-stretching, an over-exposed image which has only a few grey levels occupied will have a histogram that

   • has all grey-level bins roughly equally occupied

   • tends to show small spikes across the entire range of grey levels

   • has a concentration of large values near high grey-level values
   • has a nice peak of grey levels in its middle region

   A poorly-exposed image (either under- or over-exposed) which is contrast-stretched will normally exhibit only a few occupied bins, and they will be equally-spaced across the entire range of grey levels, giving it a `spiky' appearance.

5. Which is the following image formats is least suitable for computer vision?

   • PNG
   • TIFF
   • BMP

   • JPEG

   JPEG is a lossy file format and typically discards high-frequency information, i.e. the detail around edges.

6. Which of the following popular image processing packages provides a menu-based interface?

   • ImageJ

   • OpenCV
   • EVE
   • Matlab

   OpenCV and EVE are libraries to be used by a programmer, while Matlab has a GUI into which one typically types `commands'. However, ImageJ provides menus from which the image processing and analysis operations are chosen.

7. How are the colours of an image normally represented in OpenCV?

   • hue, saturation, value

   • blue, green, red

   • blue, red, green
   • red, green, blue

   For reasons known only to its authors, colour images in OpenCV ignore the red, green, blue convention used everywhere else and normally represent images as blue, green, red. Crazy!

8. Why is the order of subscripts into an image important?

   • it affects the run-time of an algorithm

   • it makes mapping code onto a GPU easier
   • it makes the code easier to read
   • it affects the amount of memory used

   When the subscripts are indexed in the right order, adjacent pixels in the image are adjacent in memory. This reduces the number of cache hits, allows auto-increment instructions to be used, and so on.

9. How does histogram equalization work?

   • histogram bins with low occupancy are deleted

   • histogram bins with low occupancy are spread out

   • histogram bins with low occupancy are doubled
   • histogram bins with low occupancy are merged

   Histogram equalization spreads out low-occupancy parts of a histogram. It is inhereently non-linear in nature and generally a very silly thing to do for computer vision. Your lecture can count on the fingers of one foot the number of times it has helped him develop vision algorithms.

10. If a histogram has most of its values bunched together at its left, how does the image appear?

    • equally-exposed

    • under-exposed

    • over-exposed
    • well-exposed

    If the majority of pixels are are the left of a histogram, they have low values and so the image is dark and that normally means it is under-exposed.