Skip to main content
Springer Nature Link
Log in

Geons

  • Reference work entry
  • First Online:
Computer Vision

  • 527 Accesses

Synonyms

Recognition-by-components (RBC) theory

Related Concepts

Object Class Recognition (Categorization)

Definition

Geons are a set of less than 50 qualitative 2-D or 3-D part classes derived from permuting a set of four dichotomous and trichotomous properties of a generalized cylinder (GC). The values of these properties are nonaccidental in that they can be resolved from a general viewpoint, e.g., whether the axis of a cylinder is straight or curved. Geons were originally introduced by Biederman [9, 10] as the foundation for his recognition-by-components (RBC) theory for human shape perception, whereby object-centered models are represented as concatenations of geons, and object recognition from a 2-D image proceeds by matching recovered parts, typically segmented at regions of matched concavity, and their relations to object models.

Background

The concept of modeling an object as a composition of generalized cylinders dates back to Binford [18], who spawned a generation of...

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Lazareva OF, abd Wasserman EA, Biederman I (2008) Pigeons and humans are more sensitive to nonaccidental than to metric changes in visual objects. Behav Processes 77:199–209

    Google Scholar 

  2. Kayaert G, Biederman I, Vogels R (2005) Representation of regular and irregular shapes in macaque inferotemporal cortex. Cereb Cortex 15:1308–1321

    Article  Google Scholar 

  3. Behrmann M, Peterson MA, Moscovitch M, Suzuki S (2006) Integrative agnosia: deficit in encoding relations between parts. J Exp Psychol Human Percept Perf 32(5):1169–1184

    Article  Google Scholar 

  4. Bergevin R, Levine MD (1988) Recognition of 3-D objects in 2-D line drawings: an approach based on geons. Technical report TR-CIM-88, Center for intelligent machines, McGill University, Nov 1988

    Google Scholar 

  5. Bergevin R, Levine MD (1989) Generic object recognition: building coarse 3D descriptions from line drawings. In: Proceedings, IEEE workshop on interpretation of 3D scenes, Austin, pp 68–74

    Google Scholar 

  6. Bergevin R, Levine MD (1992) Extraction of line drawing features for object recognition. Pattern Recognit 25(3): 319–334

    Article  Google Scholar 

  7. Bergevin R, Levine MD (1992) Part decomposition of objects from single view line drawings. CVGIP: Image Underst 55(1):73–83

    Article  MATH  Google Scholar 

  8. Bergevin R, Levine MD (1993) Generic object recognition: building and matching coarse 3D descriptions from line drawings. IEEE Trans Pattern Anal Mach Intell 15:19–36

    Article  Google Scholar 

  9. Biederman I (1985) Human image understanding: recent research and a theory. Comput Vis Graph Image Process 32:29–73

    Article  Google Scholar 

  10. Biederman I (1987) Recognition-by-components: a theory of human image understanding. Psychol Rev 94:115–147

    Article  Google Scholar 

  11. Biederman I (1990) Higher level vision. In: An invitation to cognitive science: visual cognition and action, vol 2. MIT, Cambridge, MA, pp 41–72

    Google Scholar 

  12. Biederman I (2000) Recognizing depth-rotated objects: a review of recent research and theory. Spat Vis 13:241–253

    Article  Google Scholar 

  13. Biederman I, Bar M (1999) One-shot viewpoint invariance in matching novel objects. Vis Res 39:2885–2899

    Article  Google Scholar 

  14. Biederman I, Cooper EE (1991) Priming contour-deleted images: evidence for intermediate representations in visual object recognition. Cognit Psychol 23:393–419

    Article  Google Scholar 

  15. Biederman I, Gerhardstein PC (1993) Recognizing depth-rotated objects: evidence and conditions for 3D viewpoint invariance. J Exp Psychol Hum Percept Perform 19: 1162–1182

    Article  Google Scholar 

  16. Biederman I, Ju G (1988) Surface vs. edge-based determinants of visual recognition. Cognit Psychol 20:38–64

    Article  Google Scholar 

  17. Biederman, I, Yue, X, Davidoff J (2009) Representation of shape in individuals from a culture with minimal exposure to regular simple artifacts: sensitivity to nonaccidental vs. metric properties. Psychol Sci 20:1437–1442

    Article  Google Scholar 

  18. Binford TO (1971) Visual perception by computer. In: Proceedings, IEEE conference on systems and control, Miami

    Google Scholar 

  19. Borges D, Fisher R (1997) Class-based recognition of 3d objects represented by volumetric primitives. Image Vis Comput 15(8):655–664

    Article  Google Scholar 

  20. Brooks R (1983) Model-based 3-D interpretations of 2-D images. IEEE Trans Pattern Anal Mach Intell 5(2): 140–150

    Article  Google Scholar 

  21. Cant JS, Goodale MA (2009) Asymmetric interference between the perception of shape and the perception of surface properties. J Vis 9(13):11–20

    Article  Google Scholar 

  22. Dickinson S (2009) The evolution of object categorization and the challenge of image abstraction. In: Dickinson S, Leonardis A, Schiele B, Tarr M (eds) Object categorization: computer and human vision perspectives. Cambridge University Press, New York, pp 1–37

    Chapter  Google Scholar 

  23. Dickinson S, Bergevin R, Biederman I, Eklundh J-O, Jain A, Munck-Fairwood R, Pentland A (1997) Panel report: the potential of geons for generic 3-D object recognition. Image Vis Comput 15(4):277–292

    Article  Google Scholar 

  24. Dickinson S, Christensen H, Tsotsos J, Olofsson G (1997) Active object recognition integrating attention and viewpoint control. Comput Vis Image Underst 67(3): 239–260

    Article  Google Scholar 

  25. Dickinson S, Metaxas D (1994) Integrating qualitative and quantitative shape recovery. Int J Comput Vis 13(3): 1–20

    Article  Google Scholar 

  26. Dickinson S, Metaxas D, Pentland A (1997) The role of model-based segmentation in the recovery of volumetric parts from range data. IEEE Trans Pattern Anal Mach Intell 19(3):259–267

    Article  Google Scholar 

  27. Dickinson S, Pentland A, Rosenfeld A (1990) A representation for qualitative 3-D object recognition integrating object-centered and viewer-centered models. In: Leibovic K (ed) Vision: a convergence of disciplines. Springer, New York, pp 398–421

    Google Scholar 

  28. Dickinson S, Pentland A, Rosenfeld A (1992) From volumes to views: an approach to 3-D object recognition. CVGIP: Image Underst 55(2):130–154

    Article  MATH  Google Scholar 

  29. Dickinson S, Pentland A, Rosenfeld A (1992) 3-D shape recovery using distributed aspect matching. IEEE Trans Pattern Anal Mach Intell 14(2):174–198

    Article  Google Scholar 

  30. Du L, Munck-Fairwood R (1993) A formal definition and framework for generic object recognition. In: Proceedings, 8th Scandinavian conference on image analysis, University of Tromsø, Norway

    Google Scholar 

  31. Eklundh J-O, Olofsson G (1992) Geon-based recognition in an active vision system. In: ESPRIT-BRA 3038, vision as process. Springer-Verlag ESPRIT Series

    Google Scholar 

  32. Fairwood R (1991) Recognition of generic components using logic-program relations of image contours. Image Vis Comput 9(2):113–122

    Article  Google Scholar 

  33. Ferrari V, Jurie F, Schmid C (2010) From images to shape models for object detection. Int J Comput Vis 87(3): 284–303

    Article  Google Scholar 

  34. Grill-Spector K, Kourtzi Z, Kanwisher N (2001) The lateral occipital complex and its role in object recognition. Vis Res 41(10–11):1409–1422

    Article  Google Scholar 

  35. Hayworth KJ, Biederman I (2006) Neural evidence for intermediate representations in object recognition. Vis Res 46:4024–4031

    Article  Google Scholar 

  36. Hayworth KJ, Lescroart MD, Biederman I (2011) Visual relation encoding in anterior LOC. J Exp Psychol Human Percept Perf 37(4):1032–1050

    Article  Google Scholar 

  37. Hummel JE, Biederman I (1992) Dynamic binding in a neural network for shape recognition. Psychol Rev 99: 480–517

    Article  Google Scholar 

  38. Hummel JE, Biederman I, Gerhardstein P, Hilton H (1988) From edges to geons: a connectionist approach. In: Proceedings, connectionist summer school, Carnegie Mellon University, pp 462–471

    Google Scholar 

  39. Jacot-Descombes A, Pun T (1992) A probabilistic approach to 3-D inference of geons from a 2-D view. In: Proceedings, SPIE applications of artificial intelligence X: machine vision and robotics, Orlando pp 579–588

    Google Scholar 

  40. Kayaert G, Biederman I, Op de Beeck H, Vogels R (2005) Tuning for shape dimensions in macaque inferior temporal cortex. Eur J Neurosci 22:212–224

    Article  Google Scholar 

  41. Kayaert G, Biederman I, Vogels R (2003) Shape tuning in macaque inferior temporal cortex. J Neurosci 23: 3016–3027

    Google Scholar 

  42. Lades M, Vorbruggen JC, Buhmann J, Lange J, von der Malsburg C, Wurtz RP, Konen W (1993) Distortion invariant object recognition in the dynamic link architecture. IEEE Trans Comput 42:300–311

    Article  Google Scholar 

  43. Lescroart MD, Biederman I, Yue X, Davidoff J (2010) A cross-cultural study of the representation of shape: sensitivity to underlying generalized-cone dimensions. Vis Cogn 18(1):50–66

    Article  Google Scholar 

  44. Marr D, Nishihara H (1978) Representation and recognition of the spatial organization of three-dimensional shapes. R Soc Lond B 200:269–294

    Article  Google Scholar 

  45. Nevatia R, Binford TO (1977) Description and recognition of curved objects. Artif Intell 8:77–98

    Article  MATH  Google Scholar 

  46. Pentland A (1986) Perceptual organization and the representation of natural form. Artif Intell 28:293–331

    Article  MathSciNet  Google Scholar 

  47. Pilu M, Fisher RB (1996) Recognition of geons by parametric deformable contour models. In: Proceedings, European conference on computer vision (ECCV), LNCS, Springer, Cambridge, UK, April 1996, pp 71–82

    Google Scholar 

  48. Raja N, Jain A (1992) Recognizing geons from superquadrics fitted to range data. Image Vis Comput 10(3):179–190

    Article  Google Scholar 

  49. Raja N, Jain A (1994) Obtaining generic parts from range images using a multi-view representation. CVGIP: Image Underst 60(1):44–64

    Article  Google Scholar 

  50. Sala P, Dickinson S (2010) Contour grouping and abstraction using simple part models. In: Proceedings, European conference on computer vision (ECCV) Crete, Greece, Sept 2010

    Google Scholar 

  51. Ulupinar F, Nevatia R (1993) Perception of 3-D surfaces from 2-D contours. IEEE Trans Pattern Anal Mach Intell 15:3–18

    Article  Google Scholar 

  52. Vogels R, Biederman I, Bar M, Lorincz A (2001) Inferior temporal neurons show greater sensitivity to nonaccidental than metric differences. J Cogn Neurosci 13:444–453

    Article  Google Scholar 

  53. Wu K, Levine MD (1997) 3-D shape approximation using parametric geons. Image Vis Comput 15(2):143–158

    Article  Google Scholar 

  54. Zerroug M, Nevatia R (1996) Volumetric descriptions from a single intensity image. Int J Comput Vis 20(1/2):11–42

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science, University of Toronto, Toronto, ON, Canada

    Sven J. Dickinson

  2. Departments of Psychology, Computer Science, and the Neuroscience Program, University of Southern California, Los Angeles, CA, USA

    Irving Biederman

Authors
  1. Sven J. Dickinson
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Irving Biederman
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Institute of Industrial Science, The University of Tokyo, Tokyo, Japan

    Katsushi Ikeuchi

Rights and permissions

Reprints and permissions

Copyright information

© 2014 Springer Science+Business Media New York

About this entry

Cite this entry

Dickinson, S.J., Biederman, I. (2014). Geons. In: Ikeuchi, K. (eds) Computer Vision. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-31439-6_431

Download citation

Publish with us

Policies and ethics