A short quiz on intermediate-level vision

Adrian F. Clark

1. How many thresholds are employed in hysteresis thresholding?

   • 2

   • 3
   • 1
   • 4

   Hysteresis thresholding employs a pair of thresholds.

2. What is the purpose of the Hough transform?

   • To join together edges in images
   • To calculate an accumulator array

   • To find the parameters of lines, etc

   • To find edges in images

   The purpose of the Hough transform is to estimate the parameters that describe some image feature -- though we have looked only at straight lines in this module.

3. What is the basis of a LBP descriptor?

   • the histogram of edges orientations around the centre pixel
   • whether a $N$ pixels at random locations near the centre pixel are greater than the centre pixel or not
   • the histogram of corner angles in the region around the centre pixel

   • whether or not the values of eight neighbouring pixels are greater than the centre pixel

   LBP 'walks' around eight neighbouring pixels and, at each location, works out whether or not their values are greater than the centre pixel. The resulting 8-bit number is used to identify the 'bin' of a histogram to be incremented.

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

   • BRIEF

   • SIFT

   • ORB
   • FAST

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

5. What is hysteresis thresholding?

   • Using two thresholds to partition an image into two levels
   • Using two thresholds to partition an image into three levels
   • Using hysteresis to choose the value of a threshold

   • Joining together edge segments

   The last stage of the Canny edge detctor, hysteresis thresholding is a technique for joining together edge segments.

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?

   • the edges are still too noisy to be useful

   • edges are of limited value in practice

   • it doesn't find all edges
   • it is too slow

   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. In the parametric line Hough transform, what is the accumulator array indexed by?

   • end-points
   • gradient magnitude and direction
   • gradient and intercept

   • radius and angle

   The parametric form of a line is described by radius and angle, so these are what we use as the indices of the accumulator array.

8. What was the major advance in the Harris and Stephens corner detector compared to Moravec?

   • it works with shifted regions around the corner
   • it works more quickly
   • it avoids detecting more than one corner at a single image location

   • it considers the directions of the corner's derivatives

   Harris and Stephens used calculus to determine the derivates at a corner, and from these it is able to determine their directions

9. Which of the following is not really an edge detector?

   • Sobel

   • Laplacian

   • Canny
   • Harris and Stephens

   Sobel and Canny were designed as edge detectors. Although better known as a corner detector, Harris and Stephens also detects edges. On the other hand, the Laplacian is better at detecting isolated points.

10. What information does the Canny edge detector find about each piece of edge?

    • the direction
    • the magnitude

    • the magnitude and direction

    • the magnitude, direction and width

    Canny finds the magnitude and direction of each line by forming differences along each row and column.