4: Object Recognition

studied byStudied by 0 people
0.0(0)
learn
LearnA personalized and smart learning plan
exam
Practice TestTake a test on your terms and definitions
spaced repetition
Spaced RepetitionScientifically backed study method
heart puzzle
Matching GameHow quick can you match all your cards?
flashcards
FlashcardsStudy terms and definitions

1 / 27

encourage image

There's no tags or description

Looks like no one added any tags here yet for you.

28 Terms

1

Apperceptive agnosia

perceive an objects features by not the object in its entirety

New cards
2

Viewpoint invariance

Humans can tell what an object is despite its perspective

New cards
3

Bottom-up processing

processes that are directly shapes by the stimulus

New cards
4

Top-down processing

processes shaped by knowledge

New cards
5

Visual search tasks

tasks in which participants examine a display and judge whether a particular target is present or not

New cards
6

Object recognition begins with what?

Feature detection

New cards
7

Tachistoscope

a device used to present stimuli for precise amounts of time

New cards
8

Word-superiority effect

it’s easier to perceive and recognize letters-in-context than if they appear in isolation

New cards
9

Well-formedness

how closely a letter sequence conforms to the typical patterns of spelling in the language

New cards
10

Activation level

how energized the detector is at any given moment

New cards
11

Each detector in the network has an ___ ___

activation level

New cards
12

Detectors fire when their ____ ____ is reached

response threshold

New cards
13

what does starting activation depend on?

recency and frequency

New cards
14

What is knowledge NOT?

locally represented

New cards
15

What do feature nets contain?

distributed knowledge

New cards
16

McCledlland and Rumelhart model

emphasizes the role of inhibitory connections among detectors

New cards
17

What is the difference between the feature net and the McClelland and Rumelhart model?

the McClelland and Rumelhart model includes excitatory connections and inhibitory connections

New cards
18

Recognition by components (RBC) model

applies the feature net model to the recognition of 3D models. The recognition by components model includes an intermediate level of detectors that is sensitive to geons

New cards
19

what is the hierarchy of detectors from bottoms to top?

  1. feature detectors

  2. geon detectors

  3. geon assemblies

  4. object model

New cards
20

object model

a representation of the complete, recognized object

New cards
21

viewpoint-dependent cells

only fired when an object is viewed from a specific viewpoint

New cards
22

viewpoint-independent cells

fires from any viewpoint of the object

New cards
23

what viewpoint cells trigger what?

viewpoint-dependent cells may trigger viewpoint-independent cells

New cards
24

prosopagnosia

an inability to recognize individual faces deposit otherwise normal vision

New cards
25

faces show a powerful ____ ____

inversion effect

New cards
26

what is the fusiform face area (FFA) responsive to?

faces

New cards
27

holistic perception

perception of the overall configuration rather than an assemblage of parts

New cards
28

what are limits of feature nets?

  1. some target objects depend on configurations, not individual features

  2. knowledge that is external to object recognition nevertheless influences recognition

New cards
robot