Object Recognition

Question 1

Perception is more than information, what else does it involve?

Answer 1

Recognition and interpretation

Question 2

Perceptual Constancy

Answer 2

The idea that we perceive constant properties of the world.

Question 3

Unconscious inference

Answer 3

The idea that a stimulus can be perceived in more than one way

Question 4

Likelihood principle

Answer 4

The idea that when we perceive an object we do so in a manner that is most likely to have caused the pattern based on our experiences with similar situations in the past.

Question 5

Gestalt Laws of Organization

Answer 5

• Law of Good Continuation
• Law of Simplicity
• Law of Similarity
• Law of Familiarity

Question 6

Law of Good Continuation

Answer 6

Question 7

Law of Simplicity

Answer 7

Question 8

Law of Similarity

Answer 8

Question 9

Law of Familiarity

Answer 9

Question 10

True or False

Our brain first collects information and then interprets it.

Answer 10

False

Our brain collects information and interprets it in parallel.

Brain areas for simple features and large scale configuration work together and interact to achieve recognition.

Question 11

What do we mean when we say that Gestalt Laws are heuristic?

Answer 11

It means that Gestalt Laws are most of the time right but could be wrong.

Question 12

Physical Regularities

Answer 12

• Vertical and Horizontal lines are better recognised than oblique lines
• Light comes from above

Question 13

Semantic Regularities

Answer 13

The meaning

Question 14

Bottom-Up influences

Answer 14

Information that we get from the stimulus itself

Question 15

Top-Down influences

Answer 15

Information the perceiver brings to perception.

Question 16

Word Superiority Effect

Answer 16

Words are much easier to recognise than individual letters.

This tells us that it is easier to recognize things when they are in the correct context.

Question 17

True or False

If you are shown a nonsense word that slightly looks like an English word, you would be able to recognize it.

Answer 17

True

This is because of pronounceability work as context.

It could also be because of the probabilities of letter combination.

For example, TAS, RAF are more probable combinations than QWR, TKM

Question 18

Feature Net

Answer 18

A feature net is how you would break something into smaller components such that you can recognise it. For example, the word CLOCK you can break it into possible combinations of letters, then into individual letters and each individual letter can be broken into further component such as line segments with different orientations.

Question 19

Detectors

Answer 19

In our brain, we have multiple detectors that are responsible for detecting a different feature of the object to recognise. For example. if we want to recognize the word CLOCK we would first have detectors picking up the features composing each letter, then detectors picking up each letter and finally a word detector.

Question 20

How does a detector is activated?

Answer 20

Sufficiently strong signal or an accumulation of many smaller signals that will hit a response threshold and thus make the detector fire.

Question 21

True or False

Detectors are the same a neurons

Answer 21

False

Detectors do not refer to neurons

Question 22

What determines the starting activation level of detectors?

Answer 22

• recency: If a detector has fired recently
• familiarity: How frequently a detector has been used

Question 23

True or False

The bigram level in the feature net allows us to be more efficient when recognizing a combination of letters and will always be right

Answer 23

False

The bigram level in the feature net allows us to be more efficient when recognizing a combination of letters but it makes our recognition less accurate.

What our brain actually does is to read a few letters and then make some inferences on what the word could be.

Question 24

Recognition by Components (RBC) model

Answer 24

This is another model that can help us understand object recognition. In this model, we have geons or geometric ions which are basic geometric shapes that can compose any object.

Question 25

True or False

We only need three dozens of geons to compose any object in the world

Answer 25

True!

This was discovered by Irving Biedeman

Question 26

Is there a problem with the RCB model?

Answer 26

Yes, it is point view dependent

Question 27

Fusiform brain area

Answer 27

Area of the brain dedicated to processing faces and other very familiar objects.

Question 28

Mirror Neurons

Answer 28

Neurons that fire when we see someone performing an action as if we would be performing the action too.