What is the underlying principle of the Moravec corner detector?

moving away from a corner introduces a large change

- moving away from a corner introduces a small change
- moving away from a uniform region introduces a large change
- moving along an edge introduces a large change

Which of the following schemes is unsuitable for matching corners in images?

- SUSAN
- Moravec
- Harris and Stephens
the Laplacean

Why does the last stage of the Canny edge detector perform hysteresis thresholding?

- to make the output image binary
- to make edge segments only one pixel wide
to connect together edge segments

- to reduce the effects of noise

What is characteristic that the Moravec corner detector uses to identify corners?

- it finds minima in the maximum gradient of a region
- it finds saddle points in the gradient of a region
it finds maxima in the minimum gradient of a region

- it finds regions where the gradients in all directions are almost the same

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

- matched filtering
- image differencing
- cross-correlation
the Laplacean

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

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

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

Why does the Canny edge detector perform non-maximum suppression?

- to stop the edges being too bright
to make each edge only one pixel wide

- to quantise the direction of the edge
- to stop the edges being maxima

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

- a Sobel mask
- a 3 x 3 blur mask
- a Laplacean mask
a Gaussian

Which of the following transformations is not handled by SIFT?

reflections

- scale changes
- contrast changes
- rotations