A short quiz on intermediate-level vision

Adrian F. Clark

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

   • the magnitude and direction

   • the direction
   • the magnitude, direction and width
   • the magnitude

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

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

   • a Laplacian mask
   • a Sobel mask

   • a Gaussian

   • a 3 x 3 blur mask

   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.

3. Why is the parametric Hough transform preferred to the non-parametric one?

   • It avoids problems when the gradient becomes infinite

   • It avoids problems then sin and cos are zero
   • It is faster to calculate
   • It is more accurate

   The biggest problem with the non-parametric Hough transform is that a vertical line has an infinite gradient.

4. Which of the following is NOT an underlying principle of the Canny edge detector?

   • all edges should be found
   • edges should be located in the correct place
   • it should respond only to edges

   • a broad edge should produce a response at both sides

   One of the guiding principles that underlies Canny is that a single edge should produce a single response -- though, in reality, it does not work very well for broad edges.

5. What shape is the curve drawn in the parametric accumulator array of a Hough transform from a single pixel in an image?

   • an $x^2$ shape
   • a $1/x$ shape
   • a straight line

   • a sinusoid

   The parametric form of a straight line is a sinusoid, so that is what is drawn into the accumulator.

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

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

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

   • it produces fewer false negatives 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.

7. What is the purpose of the Hough transform?

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

   • 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.

8. Which of the following schemes is unsuitable for matching arbitrary features in images?

   • cross-correlation

   • the Laplacian

   • matched filtering
   • image differencing

   The Laplacian emphasizes isolated points in images, and is not suited to matching any other feature in an image.

9. What does one do with the Hough accumulator to find lines?

   • Each line in the accumulator is a line in the image
   • Each corner in the accumulator is a line in the image
   • Each 3 x 3 region in the accumulator is a line in the image

   • Each peak in the accumulator is a line in the image

   As the code in the notes illustrates clearly at the end of Chapter 5, peaks in the Hough accumulator correspond to lines in the image. This is because more image pixels have `voted' for that set of parameters than any other set.

10. Which of the following is suitable for matching SIFT features P and Q?

    • the expression P(x,y) x Q(x, y)
    • the expression sqrt{ P(x,y)^2 + Q(x, y)^2 }

    • the expression sqrt{ (P(x,y) - Q(x, y))^2}

    • the expression sqrt{ P(x,y) } - sqrt{ Q(x, y) }

    We take the difference between features in $P$ and $Q$. As this will contain both positive and negative values and we want to know how much they differ overall, we need to change negative values into positive ones; we normally do this by squaring this difference.