Download presentation
Presentation is loading. Please wait.
1
Pattern recognition (…and object perception)
2
Traditional Gestalt Psychology
Topic Outline: Traditional Gestalt Psychology Laws of Organization Problems with this stuff Solution to Pragnanz II. Identifying “Figures” Properties of figures/ground Intrinsic/extrinsic contours Illusory contours III. Models of object recognition a. Pandemonium Theory b. Identification by Components c. Marr’s Computational approach d. Gibson’s “direct perception” e. Connectionist/PDP models
3
Traditional Gestalt Psychology
-originated as a counter to structuralist viewpoint (Koffka, Wertheimer, Kohler) Structuralist: “the whole is equal to the sum of the parts” Koffka: “the whole is other than the sum of the parts” In other words, cannot fully explain object perception based solely on a description of the elements of that perception: emergent properties One of the first examples: Phi phenomenon
6
Emergent properties
7
Emergent properties
8
Emergent properties
9
Emergent properties
10
Emergent properties
11
Emergent properties
12
Emergent properties
13
Emergent properties
14
Emergent properties
15
Gestalt laws of Organization
16
Gestalt laws of Organization
Law of Proximity
17
Gestalt laws of Organization
Law of Similarity
18
Gestalt laws of Organization
Good Continuation
19
Gestalt laws of Organization
Closure
20
Gestalt laws of Organization
Common fate
21
Gestalt laws of Organization
Common fate
22
Gestalt laws of Organization
Common fate
23
Gestalt laws of Organization
Common fate
24
Gestalt laws of Organization
Common fate
25
Gestalt laws of Organization
Common fate
26
Gestalt laws of Organization
Common fate
27
Gestalt laws of Organization
All the other laws are subsumed under the Law of Pragnanz: -patterns will be perceived in such a way that the resulting structure is as simple as possible Problems: 1. Descriptive, with no indication of underlying mechanisms of how it is accomplished 2. Lack of predictive power
29
Gestalt laws of Organization
All the other laws are subsumed under the Law of Pragnanz: -patterns will be perceived in such a way that the resulting structure is as simple as possible Problems: 1. Descriptive, with no indication of underlying mechanisms of how it is accomplished 2. Lack of predictive power 3. No definition of “simplest”
30
More recent research tries to clear up that last one:
“simplest” = least amount of data/information required 2-d = 26 angles 3-d = 24 angles
31
More recent research tries to clear up that last one:
“simplest” = least amount of data/information required 2-d = 18 angles 3-d = 24 angles
32
II. Identifying “Figures”
33
II. Identifying “Figures”
Relative to “grounds”, figures are: -in front -a clearly defined shape -higher perceived contrast -processed in greater detail -the process involves distinguishing intrinsic from extrinsic contours
35
-can give rise to complex perceptions
II. Identifying “Figures” -subjective/illusory contours: -can give rise to complex perceptions
36
-can give rise to complex perceptions
II. Identifying “Figures” -subjective/illusory contours: -can give rise to complex perceptions
37
-can give rise to complex perceptions
II. Identifying “Figures” -subjective/illusory contours: -can give rise to complex perceptions
38
III. Models of object recognition
-bottom-up versus top-down distinction -earliest model: template matching -discarded due to lack of flexibility, too much storage needed
39
III. Models of object recognition
1. Selfridge’s Pandemonium model
40
III. Models of object recognition
1. Selfridge’s Pandemonium model
41
III. Models of object recognition
1. Selfridge’s Pandemonium model Problems: Defining a feature Overly data-driven (no room for context effects) Decision demon will need stored templates to compare to and recognize the object Was originally designed for language only
42
III. Models of object recognition
1. Selfridge’s Pandemonium model 2. Biederman’s identification by components model -another feature model, but the features are now “Geons” -small set of shapes that, in combination, can represent objects
43
III. Models of object recognition
1. Selfridge’s Pandemonium model 2. Biederman’s identification by components model -again, not much room for context to play a role -again, the job of actually identifying the object is left vague
44
III. Models of object recognition
1. Selfridge’s Pandemonium model 2. Biederman’s identification by components model 3. Marr’s computational approach -stages of processing from simple to complex -primal sketch: edges and boundaries identified based on intensity differences (called zero crossings) -2.5d sketch: that info is processed using grouping rules into larger groups, surfaces and distances interpolated into image (wire frame) -3d sketch: textures added and volume applied
45
III. Models of object recognition
1. Selfridge’s Pandemonium model 2. Biederman’s identification by components model 3. Marr’s computational approach 4. Gibson’s direct perception -question is, how do we perceive a constantly changing stimulus array with any consistency? -light array contains sufficient information that we don’t need internal models or deconstructions -changing array still has invariant properties -affordances can be directly perceived -deletion/accretion, optic flow, motion parallax -not enough detail to be taken seriously
46
III. Models of object recognition
1. Selfridge’s Pandemonium model 2. Biederman’s identification by components model 3. Marr’s computational approach 4. Gibson’s direct perception 5. Connectionist/PDP models -neural networks modeled via interconnected nodes -combinations of nodes converge to give rise to complex codings being programmed at higher layers
48
Different from Selfridge in several ways:
-connections can occur within a single level -connections can be excitatory or inhibitory -system can learn through back-propogation and application of delta rule -apply input, assign initial weights based on nodes firing at the same time (Hebb rule) -output compared with desired input to compute the degree of error -this difference is used to compute a delta rule for changing the weights -reapply the stimulus and recalculate delta, update weights again -keep cycling through until detection is accurate
49
Context effects
53
No matter how hungry you are, try not to….
55
Is there a sink in the picture?
57
Is there a sink in the picture?
60
Duncker Wheel
61
Duncker Wheel
62
McGurk Effect
63
Word superiority effect
GZQRM XXXXX What were the letters?
64
Word superiority effect
WORKS XXXXXX
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.