Advertisement

Detecting, Representing and Attending to Visual Shape

  • Antonio J. Rodríguez-Sánchez
  • Gregory L. Dudek
  • John K. Tsotsos
Part of the Advances in Computer Vision and Pattern Recognition book series (ACVPR)

Abstract

The importance of shape detection, representation and recognition is not disputed by any relevant discipline and is an integral part of visual perception by both animals and machines. However, to date, there is no comprehensive theoretical framework of how to deal with visual shape. Here, we present the beginnings of such a framework and attempt to integrate the means to detect, represent and recognize shapes, specifically two-dimensional silhouettes. Of note is the inclusion of an attentional scheme primarily because there is growing evidence that human perception involves such a capacity yet how this might occur is virtually unexamined. Secondarily, the ability to attend to shape and shape elements is central to our ability to not only recognize shapes and objects, but also to reason about shape, solve problems involving shape, manipulate shapes and perform spatial reasoning.

Keywords

Complex Cell Simple Cell Illusory Contour Shape Detection Selective Tuning 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Notes

Acknowledgements

This research was funded by the Natural Sciences and Engineering Research Council of Canada and Canada Research Chairs Program.

References

  1. 1.
    Attneave F (1954) Some informational aspects of visual perception. Psychol Rev 61:183–193 CrossRefGoogle Scholar
  2. 2.
    Bishop P, Kato H, Orban G (1980) Direction selective cells in complex family in cat striate cortex. J Neurophysiol 43:1266–1283 Google Scholar
  3. 3.
    Blum H (1962) An associative machine for dealing with the visual field and some of its biological implications. Air Force Cambridge Research Labs, L G Hanscom Field, Mass, Feb 1962 Google Scholar
  4. 4.
    Blum H (1967) A transformation for extracting descriptors of shape. In: Wathen-Dunn W (ed) Models for the perception of speech and visual forms. MIT Press, Cambridge, pp 362–380 Google Scholar
  5. 5.
    Booth M, Rolls E (1998) View-invariant representations of familiar objects by neurons in the inferior temporal visual cortex. Cereb Cortex 8(6):510–523 CrossRefGoogle Scholar
  6. 6.
    Boynton G, Hegde J (2004) Visual cortex: the continuing puzzle of area v2. Curr Biol 14(13):R523–R524 CrossRefGoogle Scholar
  7. 7.
    Brincat S, Connor C (2004) Underlying principles of visual shape selectivity in posterior inferotemporal cortex. Nat Neurosci 7(8):880–886 CrossRefGoogle Scholar
  8. 8.
    Cant JS, Goodale MA (2011) Scratching beneath the surface: new insights into the functional properties of the lateral occipital area and parahippocampal place area. J Neurosci 31(22):8248–8258 CrossRefGoogle Scholar
  9. 9.
    Clements DH, Sarama J (2000) What do Children Know about Shapes? In: Teaching children mathematics. April 2000, The National Council of Teachers of Mathematics, Inc, pp 482–488 Google Scholar
  10. 10.
    Corbetta M, Miezin F, Dobmeyer S, Shulman GL, Petersen SE (1991) Selective and divided attention during visual discriminations of shape, color, and speed: functional anatomy by positron emission tomography. J Neurosci 11(9):2393–2402 Google Scholar
  11. 11.
    Dobbins A (1992) Difference models of visual cortical Neurons. Doctoral dissertation, Department of Electrical Engineering, McGill University Google Scholar
  12. 12.
    Dudek G, Tsotsos JK (1997) Shape representation and recognition from multiscale curvature. Comput Vis Image Underst 68(2):170–189 CrossRefGoogle Scholar
  13. 13.
    Dudek G, Tsotsos JK (1991) Shape representation and recognition from curvature. In: Proc computer vision and pattern recognition, pp 35–41 Google Scholar
  14. 14.
    Dudek G, Tsotsos JK (1990) Recognizing planar curves using curvature-tuned smoothing. In: Proceedings 10th international conference on pattern recognition, vol 1, pp 130–135 CrossRefGoogle Scholar
  15. 15.
    Durand JB, Nelissen K, Joly O, Wardak C, Todd J, Norman F, Janssen P, Vanduffel W, Orban G (2007) Anterior regions of monkey parietal cortex process visual 3D shape. Neuron 55:493–505 CrossRefGoogle Scholar
  16. 16.
    Fergus R, Perona P, Zisserman A (2003) Object class recognition by unsupervised scale-invariant learning. In: CVPR, vol 2, p 264 Google Scholar
  17. 17.
    Fiser J, Aslin RN (2002) Statistical learning of new visual feature combinations by infants. Proc Natl Acad Sci USA 99:15822–15826 CrossRefGoogle Scholar
  18. 18.
    Fukushima K (1980) Neocognitron: a self organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol Cybern 36(4):193–202 MATHCrossRefGoogle Scholar
  19. 19.
    Gershfokk-Stowe L, Smith LB (2004) Shape and the first hundred nouns. Child Dev 75(4):1098–1114 CrossRefGoogle Scholar
  20. 20.
    Han X, Chen Y, Ruan X (2010) Image recognition by learned linear subspace of combined bag-of-features and low-level features. In: ICIP Google Scholar
  21. 21.
    Hawken M, Parker A (1987) Spatial properties of neurons in the monkey striate cortex. Proc R Soc Lond B, Biol Sci 231:251–288 CrossRefGoogle Scholar
  22. 22.
    Hopf J-M, Boehler CN, Schoenfeld MA, Heinze H-J, Tsotsos JK (2010) The spatial profile of the focus of attention in visual search: insights from MEG recordings. Vis Res 50(14):1312–1320 CrossRefGoogle Scholar
  23. 23.
    Hubel D, Wiesel T (1962) Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex. J Physiol 160:106–154 Google Scholar
  24. 24.
    Hubel D, Wiesel T (1968) Receptive fields and functional architecture of monkey striate cortex. J Physiol 195(1):215–243 Google Scholar
  25. 25.
    Hummel JE, Stankiewicz BJ (1998) Two roles for attention in shape perception: a structural description model of visual scrutiny. Vis Cogn 5:49–79 CrossRefGoogle Scholar
  26. 26.
    Ito M, Komatsu H (2004) Representation of angles embedded within contour stimuli in area v2 of macaque monkeys. J Neurosci 24(13):3313–3324 CrossRefGoogle Scholar
  27. 27.
    James TW, Stevenson RA, Kim S, VanDerKlok RM, James KH (2011) Shape from sound: evidence for a shape operator in the lateral occipital cortex. Neuropsychologia 49:1807–1815 CrossRefGoogle Scholar
  28. 28.
    Janssen P, Vogels R, Orban G (2000) Selectivity for 3D shape that reveals distinct areas within macaque inferior temporal cortex. Science 288:2054–2056 CrossRefGoogle Scholar
  29. 29.
    Janssen P, Vogels R, Liu Y, Orban G (2001) Macaque inferior temporal neurons are selective for three-dimensional boundaries and surfaces. J Neurosci 21:9419–9429 Google Scholar
  30. 30.
    Jones SS, Smith LB (1993) The place of perception in children’s concepts. Cogn Dev 8:113–139 CrossRefGoogle Scholar
  31. 31.
    Kato H, Bishop P, Orban G (1978) Hypercomplex and simple/complex cells classifications in cat striate cortex. J Neurophysiol 41:1071–1095 Google Scholar
  32. 32.
    Koenderink JJ, van Doorn AJ (1980) Photomettric invariants related to solid shape. Opt Acta 27(7):981–996 CrossRefGoogle Scholar
  33. 33.
    Kruijne W, Tsotsos JK (2011) Visuo-cognitive routines: reinterpreting the theory of visual routines as a framework for visual cognition. Technical Report CSE-2011-05, Dept of Computer Science & Engineering, York University Google Scholar
  34. 34.
    Leung B (2004) Component-based car detection in street scene IMages. PhD thesis, Massachusetts Institute of Technology, Dept of Electrical Engineering and Computer Science Google Scholar
  35. 35.
    Marcelja S (1980) Mathematical description of the responses of simple cortical cells. J Opt Soc Am 70(11):1297–1300 MathSciNetCrossRefGoogle Scholar
  36. 36.
    Merigan W, Pham H (1998) 4 lesions in macaques affect both single and multiple-viewpoint shape discriminations. Vis Neurosci 15:359–367 CrossRefGoogle Scholar
  37. 37.
    Orban G, Kato H, Bishop P (1979) Dimensions and properties of end-zone inhibitory areas of hypercomplex cells in cat striate cortex. J Neurophysiol 42:833–849 Google Scholar
  38. 38.
    Orban G, Kato H, Bishop P (1979) End-zone region in receptive fields of hypercomplex and other striate neurons in the cat. J Neurophysiol 42:818–832 Google Scholar
  39. 39.
    Orban G, Janssen P, Vogels R (2006) Extracting 3D structure from disparity. Trends Neurosci 29:466–473 CrossRefGoogle Scholar
  40. 40.
    Pasupathy A, Connor C (1999) Responses to contour features in macaque area V4. J Neurophysiol 82(5):2490–2502 Google Scholar
  41. 41.
    Pasupathy A, Connor C (2001) Shape representation in area V4: position-specific tuning for boundary conformation. J Neurophysiol 86(5):2505–2519 Google Scholar
  42. 42.
    Pasupathy A, Connor C (2002) Population coding of shape in area V4. Nat Neurosci 5(12):1332–1338 CrossRefGoogle Scholar
  43. 43.
    Rektorys K (1980) Variational methods in mathematics, science and engineering. Reidel, Dordrecht MATHGoogle Scholar
  44. 44.
    Riesenhuber M, Poggio T (1999) Hierarchical models of object recognition in cortex. Nat Neurosci 2(11):1019–1025 CrossRefGoogle Scholar
  45. 45.
    Rodríguez-Sánchez AJ, Simine E, Tsotsos JK (2007) Attention and visual search. Int J Neural Syst 17(4):275–288 CrossRefGoogle Scholar
  46. 46.
    Rodríguez-Sánchez A (2010) Intermediate visual representations for attentive recognition systems. PhD, York University Google Scholar
  47. 47.
    Rodriguez-Sanchez A, Tsotsos JK (2011) The importance of intermediate representations for the modeling of 2D shape detection: endstopping and curvature tuned computations. In: Proc IEEE computer vision and pattern recognition, Colorado Springs, CO Google Scholar
  48. 48.
    Rodríguez-Sánchez A, Tsotsos J (2012) The roles of endstopped and curvature tuned computations in a hierarchical representation of 2D shape. PLoS ONE 7(8):1–13 CrossRefGoogle Scholar
  49. 49.
    Samuelson LK, Smith LB (2005) They call it like they see it: spontaneous naming and attention to shape. Dev Sci 8(2):182–198 CrossRefGoogle Scholar
  50. 50.
    Sereno AB, Amador SC (2006) Attention and memory-related responses of neurons in the lateral intraparietal area during spatial and shape-delayed match-to-sample tasks. J Neurophysiol 95:1078–1098 CrossRefGoogle Scholar
  51. 51.
    Serre T, Wolf L, Bileschi S, Riesenhuber M (2007) Robust object recognition with cortex-like mechanisms. IEEE Trans Pattern Anal Mach Intell 29(3):411–426 CrossRefGoogle Scholar
  52. 52.
    Serre T, Wolf L, Poggio T (2005) Object recognition with features inspired by visual cortex. In: IEEE conference on computer vision and pattern recognition Google Scholar
  53. 53.
    Siddiqi K, Shokoufandeh A, Dickinson SJ, Zucker SW (1999) Shock graphs and shape matching. Int J Comput Vis 35(1):13–32 CrossRefGoogle Scholar
  54. 54.
    Sigurdardottir HM, Michalak SM, Sheinberg DL (2012) Shape beyond recognition: how object form biases spatial attention and motion perception. J Vis 12(9):665 CrossRefGoogle Scholar
  55. 55.
    Smith LB, Jones SS, Landau B, Gershkoff-Stowe L, Samuelson L (2002) Object name learning provides on-the-job training for attention. Psychol Sci 13(1):13–19 CrossRefGoogle Scholar
  56. 56.
    Spelke E (2000) Principles of object perception. Cogn Sci 14:29–56 CrossRefGoogle Scholar
  57. 57.
    Tanaka K (1996) Representation of visual features of objects in the inferotemporal cortex. Neural Netw 9(8):1459–1475 MATHCrossRefGoogle Scholar
  58. 58.
    Terzopoulos D (1986) Regularization of inverse visual problems involving discontinuities. IEEE Trans Pattern Anal Mach Intell 8(4):413–424 CrossRefGoogle Scholar
  59. 59.
    Todd JT (2004) The visual perception of 3D shape. Trends Cogn Sci 8(3):115–121 CrossRefGoogle Scholar
  60. 60.
    Tsotsos JK (2011) A computational perspective on visual attention. MIT Press, Cambridge Google Scholar
  61. 61.
    Ullman S (1984) Visual routines. Cognition 18(1–3):97–159 CrossRefGoogle Scholar
  62. 62.
    Verhoef BE, Vogels R, Janssen P (2010) Contribution of inferior temporal and posterior parietal activity to three-dimensional shape perception. Curr Biol 20(10):909–913 CrossRefGoogle Scholar
  63. 63.
    von der Heydt R, Peterhans E, Baumgartner G (1984) Illusory contours and cortical neuron responses. Science 224(4654):1260–1262 CrossRefGoogle Scholar
  64. 64.
    Yamane Y, Carlson E, Bowman K, Wang Z, Connor C (2008) A neural code for three-dimensional object shape in macaque inferotemporal cortex. Nat Neurosci 11:1352–1360 CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London 2013

Authors and Affiliations

  • Antonio J. Rodríguez-Sánchez
    • 1
  • Gregory L. Dudek
    • 2
  • John K. Tsotsos
    • 3
  1. 1.Intelligent and Interactive SystemsUniversity of InnsbruckInnsbruckAustria
  2. 2.Centre for Intelligent MachinesMcGill UniversityMontrealCanada
  3. 3.Dept. of Electrical Engineering and Computer Science, and Center for Vision ResearchYork UniversityTorontoCanada

Personalised recommendations