A short quiz on low-level vision

Adrian F. Clark

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

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

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

  4. 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?

  5. How are GLCMs normally used to identify similar textures?

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

  7. 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?

  8. What does Otsu's method do?

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

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

  11.