Edge Detection

Question 1

Gradient of an image

Answer 1

A measure of how an image is changing

Question 2

Gradient magnitude

Answer 2

sqrt(Ix^2 + Iy^2)

Question 3

Non maximum operation and its use in edge detection

Answer 3

An operation that finds the strongest point in a gradient i.e. the local maximum

Question 4

What are the high and low thresholds for in Canny edge detection

Answer 4

The high threshold is for definite edges, if a pixel a local maximum and is above the high threshold, it is a definite edge.
The low threshold is for probable edges, it will only be included if it is a neighbor to a definite edge

Question 5

Steps of Canny edge detection

Answer 5

1. Gaussian filter
2. Find intensity gradient in multiple directions
3. Non maximum operation
4. Double thresholding

Question 6

What is the Laplacian operator for

Answer 6

To find edges in a single convolution, it finds the zero crossings of the second derivative of the image

Question 7

Laplacian kernel

Answer 7

[0 -1 0]
[-1 4 -1]
[0 -1 0]