A short quiz on low-level vision

Adrian F. Clark

  1. A system for identifying broken custard cream biscuits looks for rectangular regions that are aligned with the edges of images. Why might this be a bad idea?

  2. An image of a room contains a computer with a display. What feature or features would help you detect the display?

  3. Which of the following is a sensible region descriptor?

  4. Why is a recursive region labelling algorithm poor in practice?

  5. Why is simple thresholding not especially effective at locating light features in an image?

  6. In a real-time implementation of the Sobel operator, it is important to keep the number of multiplications as small as possible. What is the smallest number of multiplications that are required to convolve each image region with one of the Sobel masks?

  7. Which is the easiest way to identify broken digestive biscuits on a production line?

  8. If a histogram has two peaks, where is the best place to put a threshold to separate foreground from background?

  9. What are grey-level co-occurrence matrices?

  10. In the broken biscuit identifier explored in lectures, what is its most serious problem?

  11.