4: Object Recognition

Apperceptive agnosia

perceive an objects features by not the object in its entirety

Viewpoint invariance

Humans can tell what an object is despite its perspective

Bottom-up processing

processes that are directly shapes by the stimulus

Top-down processing

processes shaped by knowledge

Visual search tasks

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

Object recognition begins with what?

Feature detection

Tachistoscope

a device used to present stimuli for precise amounts of time

Word-superiority effect

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

Well-formedness

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

Activation level

how energized the detector is at any given moment

Each detector in the network has an ___ ___

activation level

Detectors fire when their ____ ____ is reached

response threshold

what does starting activation depend on?

recency and frequency

What is knowledge NOT?

locally represented

What do feature nets contain?

distributed knowledge

McCledlland and Rumelhart model

emphasizes the role of inhibitory connections among detectors

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

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

what is the hierarchy of detectors from bottoms to top?

1. feature detectors

2. geon detectors

3. geon assemblies

4. object model

object model

a representation of the complete, recognized object

viewpoint-dependent cells

only fired when an object is viewed from a specific viewpoint

viewpoint-independent cells

fires from any viewpoint of the object

what viewpoint cells trigger what?

viewpoint-dependent cells may trigger viewpoint-independent cells

prosopagnosia

an inability to recognize individual faces deposit otherwise normal vision

faces show a powerful ____ ____

inversion effect

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

faces

holistic perception

perception of the overall configuration rather than an assemblage of parts

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