rest of w1 gemini

Question 1

definition of “Computer Vision” ?

Answer 1

Extracting information about the world from images.

Question 2

Describe what is meant by the term “inverse problem” when describing vision.

Answer 2

An inverse problem is one where we know the outcomes and want to infer the causes (e.g. we know where an object currently is and want to know how it got there).

Question 3

Describe the term “well-posed” as the opposite of “ill-posed”.

Answer 3

A well-posed problem is one which has one unique solution

Question 4

Describe the term “forward problem” as the opposite of “inverse problem”.

Answer 4

A forward problem is one where we know the causes and want to predict or model to outcomes (e.g. we know the forces acting on an object and want to calculate its acceleration).

Question 5

Why is vision described as an “inverse problem”?

Answer 5

Because we know the pixel intensities (the outcomes) and want to infer the causes (i.e. the objects in the scene

Question 6

Why is vision described as an “ill-posed problem”?

Answer 6

Because there are usually multiple solutions (i.e. multiple causes that could give rise to the same outcomes) given the pixel intensities.

Question 7

What is a “prior” in the context of computer vision?

Answer 7

A prior is an additional source of information that can help reduce the number of possible solutions.

Question 8

How do “priors” help solve the ill-posed

Answer 8

inverse problem of vision?

Question 9

Give examples of “priors” used in computer vision.

Answer 9

knowledge of the world and the image formation process