Recognition

Recognition

Visual recognition
1. 1.Description (construct internal representaion)
2. 2.processes to store information
3. 3.processes to compare object viewed with stored descriptions
4. 4.different angles (nature of mechanism)
5. generating & comparing descriptions of current object viewed with previous object descriptions seen.
Humphreys & Bruce (1989)
1. 5-step model
  1. PERCEPTUAL PROCESSING (what it is)
  2. SEMANTIC CLASSIFICATION (object specifics)
  3. NAMING (what object is)
  4. VIEWPOINT-DEPENDANT OBJECT DESCRIPTIONS (similar to Marr's 2 1/2D sketch)
  5. EARLY VISUAL PROCESSING (similar to Marr's full primal sketch)
2. humans CLASSIFY between items
  1. 'object' (an apple)
    1. class of object
  2. specific (eg, Sigmund Freud)
    1. specific instance
  3. BETWEEN CATEGORY v's WITHIN CATEGORY
    1. faces researched differently to object recognition
Pike et al. (2002)
1. can identify famous faces even if poorly presented (eg E-FIT)
2. recognition of unfamiliar faces is poor (eg, line-ups)
Young et al. (1993)
1. different cognitive functions used to recognise faces compared to emotions displayed
Gibson (1986)
1. Active processing (interact with environment)
2. recognition through touch
  1. feedback system = brain + touch receptors)
    1. where pressure applied is regulated by brain. Based on sensory information generated by touch
    2. location of limbs (KINESTHESIS) using touch receptors can guide hands
      1. exact position (kinesthesis) + what it feels like (touch receptors) = HAPTIC INFORMATION (generate description of object)
        haptic info good for recognition of object's weight. Yet visual more accurate for processing shape (esp. 3-D) & distance (out of reach)
        haptic is active perception. Not always passive, therefore, criticism of H & B model
    3. keep track of relative location on limbs (PROPRIOCEPTION)
Lederman & Klatzky (1987)
1. exploratory procedure (use of hands to gain haptic information.
2. (1990) each procedure gained particular type of info (shape, texture) by moving hands over contour/surface
recognising 2-D processing may use different cognitive processing than 3-D
Marr & Nishihara (1978) recognising 3-D objects
1. generalised cones (3-D images) generating an object-centred description. canonical coordinate frame.
2. multi-step process
  1. 1. derive the object shape. (identify central axis using 2 1/2 D sketch)
    1. has 3 assumptions, must accept all 3 to correctly identify.
  2. 2. locate object axis and derive 3-D description
    1. 1.area of concavity. 2.divide area in primitives. 3.find axis for each primitive. 4.link them to form 3-D
  3. 3. compare 3-D description to mental catalogue of objects
    1. 1. compare mental catalogue. 2. hierarchical levels. 3. once match found process ends
3. evaluation
  1. FOR
    1. locating central axis critical to recognition- supported by Lawson & Humphreys (1996)
    2. Warrington & Taylor (1978) patients with right hemisphere focal lesions- difficulty recognising from different viewpoints. eg. comparing photos of same object from different viewpoint.
      1. unable to convert 2-D to 3-D. Features needed to identify was obscured by different angle (rotation)
    3. Humphreys & Riddoch (1984) foreshortened images/ hidden features. foreshortened recognised less- suggesting major axis is important to forming 3-D model
    4. explains misinterpretation if contour generator is misidentified
  2. AGAINST
    1. within-category discrimination hard to explain- converting to generalised cones leads to same representations (cannot distinguish differences)
Pattern matching theories ( uses templates in memory) unlikely though as could have too many templates or large generic template
Feature recognition theories (key features of image extracted)
sturctural description theories ( key features & how they are organised with each other) compared to internal representations until match found
1. adapts to variety & ambiguity. describe in computer & human language. can recognise 3-D versions of 2-D images
3-D recognition must be able to occur independent of viewpoint. viewer-centred description change to object-centred description
Beiderman's Theory
1. agrees with Marr & Nishihara's theory
  1. Enter text here
2. complex objects represented as hierarchies of similar shapes
3. approx 36 geons used to represent objects
4. concavity used to sub-divide objects

Next up

Description

Resource summary

Similar

	Created by phoenixisis over 9 years ago