Image Representation

Question 1

When designing a computer system what do we use as an indication that a visual problem is solvable?

Answer 1

If a human can solve it

Question 2

What is the purpose of the retina?

Answer 2

Encode the nerve pattern into the nerve signals

Question 3

How can we see objects at different ranges?

Answer 3

Changing the refractive power of the eye’s lense

Question 4

Why does the iris dilate in dark conditions?

Answer 4

To enable us too see clearly in dark places

Question 5

What does the iris do?

Answer 5

Regulate amount of light entering eye

Question 6

What are spatial differences in an image?

Answer 6

Difference between data in nearby regions

Question 7

What computer vision concept is spatial difference related to?

Answer 7

Edge detection

Question 8

What are temporal differences?

Answer 8

Differences in the specific image data over ti,e

Question 9

How is RGB related to the human eye?

Answer 9

Cones (retina cells) red green or blue light sensitive

Question 10

What camera is used to capture most Computer Vision images?

Answer 10

Video

Question 11

Is the image we derive from a camera accurate?

Answer 11

No, inaccuracies in process

• radiant energy
• focus onto photosensitive detector
• absorbed
• measured digitally
• assemble measurements into image
• MEASUREMENT UNCERTAINTY ASSOCIATED WITH EACH PIXEL VALUE

Question 12

How is the uncertainty in an image quantified?

Answer 12

Signal/Noise

Question 13

Sources of degradation within camera?

Answer 13

• lens

- detector (suboptimal responce)

Question 14

What is the grey value (0-255) of pixels in overexposed regions of photographs?

Answer 14

255

Question 15

What do we define as noise in an imaging system?

Answer 15

Any deviation of the SIGNAL from its EXPECTED VALUE

Question 16

What are the two types of speckle effect seen?

Answer 16

Salt and pepper (uncommon)

Gaussian (common in all systems)

Question 17

What does an image histogram describe?

Answer 17

frequency of each grey level ocurrence

Question 18

What can the image histogram be used for?

Answer 18

a measdure of noise amplitude

Question 19

What is signal/noise measured in?

Answer 19

Decibel

Question 20

Equation for signal/noise?

Answer 20

SNR = 10* log(signal/noise)
signal = 255(max)

Question 21

When a vision system is being designed, is the resolution of the images to be processed relevant?

Answer 21

Yes, it is required

Question 22

What did Nyquist observe with his sampling theorem?

Answer 22

“to represent a periodic signal unambiguously requires at least two samples per second”

Question 23

How does the nyquist theorem translate to a spacial resolution requirement from a vision system?

Answer 23

“Two pixels must span the smallest dimension of an object in order for it to be seen in the image”

Question 24

What is another way to specify the spacial resolution?

Answer 24

θ = r/Z
r: smallest resolvable object
θ: field of view
Z: range, object distance

Question 25

What equations are used to measure distance in images?

Answer 25

• Euclidean

- City block

Question 26

Who formalized Young’s theory of rgb being combined to produce every colour?

Answer 26

CIE

Question 27

Name a few perceptual spaces

Answer 27

• HSV
• IHS
• HSB
• Lab

Question 28

What is YCrCb

Answer 28

Standard for video