A short quiz on intermediate-level vision

Adrian F. Clark

1. What is the purpose of the lower threshold in hysteresis thresholding?

   • Pixels with values below this threshold are not parts of edges

   • Edge segments with values below this threshold are joined to edge segments known to be correct
   • To identify dark lines in images
   • To identify dark regions in images

   Pixels whose values lie below this threshold are rejected as edges, while pixels whose values lie above this threshold are potentially edges, depending on the values of their neighbbouring pixels.

2. Which of the following can a Hough transform not be used to identify?

   • Straight lines

   • Faces

   • Circles
   • Ellipses

   Alas, the Hough transform cannot be used to identify faces because a face does not have a (small enough) set of parameters that describe it in an image.

3. The first stage of the Canny edge detector involves smoothing with what?

   • a 3 x 3 blur mask
   • a Laplacian mask
   • a Sobel mask

   • a Gaussian

   The first stage of the Canny edge detector is to smooth the image (in the hope of reducing the number of false edges) with a Gaussian mask.

4. What is the underlying principle of the Moravec corner detector?

   • moving away from a uniform region introduces a large change
   • moving along an edge introduces a large change

   • moving away from a corner introduces a large change

   • moving away from a corner introduces a small change

   The Moravec corner detector attempts to identify regions where a movement in any direction increases the response.

5. What is the underlying principle of the FAST corner detector?

   • it produces fewer false negatives than alternative algorithms

   • there is a contiguous span of more than half a circle of pixels that are either light or dark

   • it runs quickly
   • it produces fewer false positives than alternative algorithms

   FAST works on the principle that more than half the pixels around a circle are all either light or dark. It does run pretty quickly (but that isn't a principle) but notoriously produces oodles of false positives.

6. The Canny edge detector represents more or less the state of the art in detecting edges in images. Why is its output still of limited use?

   • it is too slow

   • edges are of limited value in practice

   • the edges are still too noisy to be useful
   • it doesn't find all edges

   In most cases, identifying the edges of objects is useful for segmenting them from the background; but edges are not much help in (say) identifying the object. For that task, it is much better to use the corners of features in the image.

7. What is the purpose of the higher threshold in hysteresis thresholding?

   • Edge segments with magnitudes higher than the higher threshold are definitely edges

   • Edge segments with magnitudes lower than the higher threshold are definitely edges
   • To identify light-coloured edges in an image
   • To identify light-coloured regions in an image

   Eddge segments with magnitudes larger than the higher threshold are definitely edges, and hysteresis thresholding then attempts to join together these edge segments.

8. Which of the following transformations is not handled by SIFT?

   • scale changes

   • reflections

   • contrast changes
   • rotations

   SIFT is designed to handle moderate changes in scale and orientation, and is reasonably independent of contrast changes. However, it does not handle reflections.

9. What type of feature is LBP best at identifying?

   • edges
   • faces
   • corners

   • different types of texture

   LBP, Local Binary Patterns, is normally used to describe texture.

10. SURF is a speeded-up version of which feature detector and descriptor?

    • BRIEF
    • FAST
    • ORB

    • SIFT

    SURF is modelled on SIFT but uses operators that are intended to be faster to compute.