Lecture 11 Flashcards

1
Q

-The ability to recognise and categorize objects is fundamental for survival and interaction with our environment
-It allows us to navigate our world, recognize dangers, find food, and plays a crucial role in social interactions

A

Why is recognising visual objects important?

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

-The variability of objects
-Their context
-Lighting conditions

A

What are the challenges in creating effective object recognition systems?

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Template Theory

A

The proposition that the visual system recognizes objects by matching the neural representation of the image with an internal representation of the same ‘‘shape’’ in the brain
-But it would be very difficult for our brains to hold a template for each different ‘‘a’’ or cow

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Exemplar Theory

A

Multiple stored examples
-Comparing new inputs to what you have already stored from the past

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Prototype Theory

A

A single, abstracted prototype per category
-Matching to the most representative prototype

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Generalized Context Model (Nosofsky)

A

You store many specific faces you’ve seen before. When seeing a new face, you compare it to stored examples and assign the category based on similarity to past faces

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

General Recognition Theory ( Ashby)

A

You rely on perceptual dimensions (e.g. face shape, jaw width, eye size) and make a decision based on statistical bounderies between the two categories

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Recognition by Components (Biederman)

A

-Alphabet of shapes
-36 geons
-With these geons, you can draw any object
-Does not explain the variability between objects

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Grandmother Cell Theory (Lettvin)

A

-Could a single neuron be responsible for recognizing your grandmother?
-This concept contributes to the ongoing debate between localized vs. distributed representation

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

A Jennifer Aniston Cell?

A

-Shown a picture of J.A. -> same cell keeps firing
-Didn’t work for look-alikes
-Didn’t work with others in pictures

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Deep Neural Network (DNN)

A

-Multilayer neural networks capable of being trained to recognize objects
-Numerous instances of an object are shown to the network, with feedback provided
-Over time, the network learns to recognize new instances of the object that it has never been explicitly trained on

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Retinal Ganglion Cells & LGN

A

Detect spots (localized contrast)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Primary Visual Cortex (V1)

A

Detect edges and bars (orientation selectivity)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Intermediate-Level Vision (V2, V3, V4, etc)

A

Grouping features into contours, textures, and surfaces

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

High-Level Vision (IT Cortex)

A

Recognizing complex shapes, objects, and categories

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Intermediate (mid) Level Vision

A

A loosely defined stage of visual processing that occurs after low-level feature extraction (e.g. edges, contrast) and before high-level object recognition and scene understanding

17
Q

Key Functions of Intermediate (mid) Level Vision

A

-Perception of edges and surfaces
-Determines which regions of an image should be grouped into objects
-Bridges low-level feature detection and high-level object recognition

18
Q

-Primary visual cortex (V1) neurons have small receptive fields that detect local edges and contrast
-These neurons are orientation-selective, responding to edges at specific angles

A

How do we detect object edges?

19
Q

The receptive fields of extrastriate cells respond to visual properties crucial for object perception

A

How do we know which edges belong together?

20
Q

Boundery Ownership

A

For a given edge or contour, these neurons determine which side belongs to the object and which side belongs to the background - a fundamental process in figure-ground segregation

21
Q

Computerized Edge Detectors

A

Not as effective as humans in detecting meaningful edges
-Miss edges that humans easily perceive because they rely purely on local contrast and intensity differences

22
Q

Illusory Contour

A

A contour that is perceived even though no physical edge exists between one side and the other

23
Q

Gestalt Theory

A

'’The whole is greater than the sum of its parts’’
-Opposes structuralism, which emphasizes breaking perception into basic elements
-Suggests that perception is holistic, meaning we naturally organize elements into meaningful wholes

24
Q

Gestalt Grouping Principles

A

A set of rules that describe when and how elements in an image appear grouped together

25
Q

Similarity

A

Similar objects (colour, shape, size) appear grouped

26
Q

Proximity

A

Elements close to each other tend to be grouped

27
Q

Good Continuation

A

Lines and edges are perceived as following the smoothest path

28
Q

Closure

A

The mind fills in missing information to perceive complete shapes

29
Q

Common Fate

A

Elements moving together are grouped

30
Q

Figure Ground

A

The brain seperates objects from the background

31
Q

Common Region

A

Elements located within a shared boundary or enclosed area are perceived as a group

32
Q

Connectedness

A

Elements visually connected by lines tend to be grouped

33
Q

Parallelism

A

Parallel contours are likely to belong to the same group

34
Q

Symmetry

A

Symmetrical regions are more likely to be perceived as a group

35
Q

Camouflage

A

Animals take advantage of Gestalt grouping principles to form groups in their environment

36
Q

Ambiguity & Perceptual Committees

A

What are these Gestalt rules good for?

37
Q

Perceptual Committees

A

-Committees must integrate conflicting inputs and reach a consencus
-Many different and sometimes competing principles influence perception
-Perception emerges as the result of the dominant interpretation agreed upon by these processes

38
Q

Five Principles of Intermediate Vision

A
  1. Grouping what should be grouped together
  2. Separate what should be separated
  3. Use prior knowledge
  4. Avoid accidents
  5. Seek consencus and minimize ambiguity