ZeePedia

OBJECT PERCEPTION (continued):Segmentation, Recognition of object

<< PATTERN RECOGNITION (continued):Queen Elizabeth’s vase, Palmer (1977)
ATTENTION & PATTERN RECOGNITION:Word Superiority Effect >>
img
Cognitive Psychology ­ PSY 504
VU
Lesson 19
OBJECT PERCEPTION (continued)
Biederman (1987) proposed three stages in recognition of an object as a configuration of simpler
components
Segmentation into sub-objects
Classify the category of each sub-object
Recognition as a pattern made of sub-objects
1. Segmentation
Sub-objects are defined by their line contours ­ Edge and bar detectors from David Marr.
Hoffman and Richards (1985) ­ Gestalt principles can be used to segment an outline
representation of an object into sub-objects. They observe that where one segment joins another
there is typically a concavity in the line outline.
2. Classification of sub-object categories
Second, once an object has been segmented into basic sub-objects, one can classify the
category of each sub-object. Biederman (1987) argues that there are 36 basic categories of sub-
objects, which he calls Geons which is abbreviation of geometric ions.
The five geons are showed in following figure. There are geons that are making different objects.
Like number 1 geon is a part of telephone. And geon number 5 is a receiver of telephone set. He
uses geons to explain the objects. He says we can vary the size of the shape and get different
objects. Same type of geons makes different things of different organization. Altogether
Biederman proposes there are 36 geons that can be generated in this manner and that they
serve as an alphabet for composing objects, much as letters or phonemes serve as the alphabet
for building up words.
60
img
Cognitive Psychology ­ PSY 504
VU
3. Recognition of object
Third, having identified the pieces out of which the object is composed and their configuration,
one recognizes the object as the pattern composed from these sub-objects or pieces. Thus,
recognizing an object is like recognizing a letter; the sub-objects become the features.
Minor details and variations don't matter. As in the case of letter recognition there are many small
variations on the underlying features geons that should not be critical for recognition. Edges are
more important than texture to define geons. Color, texture, and small detail should not matter.
This predicts that schematic line drawings of complex objects which allow the basic geons to be
identified should be recognized as quickly as detailed color photographs of the objects.
Biederman conducted an experiment to test his hypothesis. He showed different shapes to
subjects. They created two conditions.
Segment deletion
Component deletion
In that experiment some objects had whole components deleted while others had all the
components present but segments of these components were deleted. They presented these two
types of degraded figures to subjects for various brief intervals and asked them to identify the
objects.
Like in above figures, the components of elephants are separated and showed. In one figure the
components were deleted.
Biederman's evidence
The critical assumption is that object recognition is mediated by recognition of the components of
the object. The results showed, at very brief presentations (65-100 milliseconds) subjects were
61
img
Cognitive Psychology ­ PSY 504
VU
more accurate at the recognition of figures with component deletion than segment deletion. This
reversed for the longer 200 milliseconds presentations. Biederman reasoned that at the very
brief intervals subjects were not able to identify the components with segment deletion and so
had difficulty in recognizing the objects. With 200 milliseconds exposure, however, sub-objects
were able to recognize all the components in either condition. Since there were more components
in the condition with segment deletion they had more information as to object identity.
So, we can conclude it that we do not split reality in geon or anything else. We bring all the
information into our sensory store. There is difference between reality and representativeness,
reality and perception, and reality and recognition.
62
Table of Contents:
  1. INTRODUCTION:Historical Background
  2. THE INFORMATION PROCESSING APPROACH
  3. COGNITIVE NEUROPSYCHOLOGY:Brains of Dead People, The Neuron
  4. COGNITIVE NEUROPSYCHOLOGY (CONTINUED):The Eye, The visual pathway
  5. COGNITIVE PSYCHOLOGY (CONTINUED):Hubel & Wiesel, Sensory Memory
  6. VISUAL SENSORY MEMORY EXPERIMENTS (CONTINUED):Psychological Time
  7. ATTENTION:Single-mindedness, In Shadowing Paradigm, Attention and meaning
  8. ATTENTION (continued):Implications, Treisman’s Model, Norman’s Model
  9. ATTENTION (continued):Capacity Models, Arousal, Multimode Theory
  10. ATTENTION:Subsidiary Task, Capacity Theory, Reaction Time & Accuracy, Implications
  11. RECAP OF LAST LESSONS:AUTOMATICITY, Automatic Processing
  12. AUTOMATICITY (continued):Experiment, Implications, Task interference
  13. AUTOMATICITY (continued):Predicting flight performance, Thought suppression
  14. PATTERN RECOGNITION:Template Matching Models, Human flexibility
  15. PATTERN RECOGNITION:Implications, Phonemes, Voicing, Place of articulation
  16. PATTERN RECOGNITION (continued):Adaptation paradigm
  17. PATTERN RECOGNITION (continued):Gestalt Theory of Perception
  18. PATTERN RECOGNITION (continued):Queen Elizabeth’s vase, Palmer (1977)
  19. OBJECT PERCEPTION (continued):Segmentation, Recognition of object
  20. ATTENTION & PATTERN RECOGNITION:Word Superiority Effect
  21. PATTERN RECOGNITION (CONTINUED):Neural Networks, Patterns of connections
  22. PATTERN RECOGNITION (CONTINUED):Effects of Sentence Context
  23. MEMORY:Short Term Working Memory, Atkinson & Shiffrin Model
  24. MEMORY:Rate of forgetting, Size of memory set
  25. Memory:Activation in a network, Magic number 7, Chunking
  26. Memory:Chunking, Individual differences in chunking
  27. MEMORY:THE NATURE OF FORGETTING, Release from PI, Central Executive
  28. Memory:Atkinson & Shiffrin Model, Long Term Memory, Different kinds of LTM
  29. Memory:Spread of Activation, Associative Priming, Implications, More Priming
  30. Memory:Interference, The Critical Assumption, Limited capacity
  31. Memory:Interference, Historical Memories, Recall versus Recognition
  32. Memory:Are forgotten memories lost forever?
  33. Memory:Recognition of lost memories, Representation of knowledge
  34. Memory:Benefits of Categorization, Levels of Categories
  35. Memory:Prototype, Rosch and Colleagues, Experiments of Stephen Read
  36. Memory:Schema Theory, A European Solution, Generalization hierarchies
  37. Memory:Superset Schemas, Part hierarchy, Slots Have More Schemas
  38. MEMORY:Representation of knowledge (continued), Memory for stories
  39. Memory:Representation of knowledge, PQ4R Method, Elaboration
  40. Memory:Study Methods, Analyze Story Structure, Use Multiple Modalities
  41. Memory:Mental Imagery, More evidence, Kosslyn yet again, Image Comparison
  42. Mental Imagery:Eidetic Imagery, Eidetic Psychotherapy, Hot and cold imagery
  43. Language and thought:Productivity & Regularity, Linguistic Intuition
  44. Cognitive development:Assimilation, Accommodation, Stage Theory
  45. Cognitive Development:Gender Identity, Learning Mathematics, Sensory Memory