Skip to main content

Computational object recognition: a biologically motivated approach

Biological Cybernetics volume 100, Article number: 59 (2009) Cite this article

Abstract

We propose a conceptual framework for artificial object recognition systems based on findings from neurophysiological and neuropsychological research on the visual system in primate cortex. We identify some essential questions, which have to be addressed in the course of designing object recognition systems. As answers, we review some major aspects of biological object recognition, which are then translated into the technical field of computer vision. The key suggestions are the use of incremental and view-based approaches together with the ability of online feature selection and the interconnection of object-views to form an overall object representation. The effectiveness of the computational approach is estimated by testing a possible realization in various tasks and conditions explicitly designed to allow for a direct comparison with the biological counterpart. The results exhibit excellent performance with regard to recognition accuracy, the creation of sparse models and the selection of appropriate features.

This is a preview of subscription content, access via your institution.

Access options

Buy single article

Instant access to the full article PDF.

USD 39.95

Price includes VAT (USA)
Tax calculation will be finalised during checkout.

References

  • Abbott L, Rolls E, Tovee M (1996) Representational capacity of face coding in monkeys. Cereb Cortex 6(3): 498–505

    PubMed  Article  CAS  Google Scholar 

  • Adams R, Bischof L (1994) Seeded region growing. IEEE Trans Pattern Anal Mach Intell 16(6): 641–647

    Article  Google Scholar 

  • Ahissar M, Hochstein S (2004) The reverse hierarchy theory of visual perceptual learning. Trends Cogn Sci 8(10): 457–464

    PubMed  Article  Google Scholar 

  • Bar M (2003) A cortical mechanism for triggering top-down facilitation in visual object recognition. J Cogn Neurosci 15(4): 600–609

    PubMed  Article  Google Scholar 

  • Bichot N, Schall J, Thompson K (1996) Visual feature selectivity in frontal eye fields induced by experience in mature macaques. Nature 381(6584): 697–699

    PubMed  Article  CAS  Google Scholar 

  • Biederman I (1986) Human image understanding: recent research and a theory. Papers from the second workshop, vol 13 on Human and Machine Vision II table of contents, pp 13–57

  • Bishop C (1995) Neural networks for pattern recognition. Oxford University Press, Inc., New York

    Google Scholar 

  • Bojer T, Hammer B, Koers C (2003) Monitoring technical systems with prototype based clustering. European Symposium on Artificial Neural Networks, pp 433–439

  • 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

    PubMed  Article  CAS  Google Scholar 

  • Bradski G, Grossberg S (1995) Fast-learning VIEWNET architectures for recognizing three-dimensional objects from multiple two-dimensional views. Neural Netw 8(7): 1053–1080

    Article  Google Scholar 

  • Bülthoff H, Edelman S (1992) Psychophysical support for a two- dimensional view interpolation theory of object recognition. Proc Natl Acad Sci USA 89(1): 60–64

    PubMed  Article  Google Scholar 

  • Chun M, Marois R (2002) The dark side of visual attention. Curr Opin Neurobiol 12(2): 184–189

    PubMed  Article  CAS  Google Scholar 

  • Edelman S, Weinshall D (1991) A self-organizing multiple-view representation of 3d objects. Biol Cybern 64(3): 209–219

    PubMed  Article  CAS  Google Scholar 

  • Einhäuser W, Hipp J, Eggert J, Körner E, König P (2005) Learning viewpoint invariant object representations using a temporal coherence principle. Biol Cybern 93(1): 79–90

    PubMed  Article  Google Scholar 

  • Erickson C, Desimone R (1999) Responses of macaque perirhinal neurons during and after visual stimulus association learning. J Neurosci 19(23): 10404

    PubMed  CAS  Google Scholar 

  • Goldstone R (1998) Perceptual learning. Ann Rev Psychol 49

  • Goodale M (1993) Visual pathways supporting perception and action in the primate cerebral cortex. Curr Opin Neurobiol 3(4): 578–585

    PubMed  Article  CAS  Google Scholar 

  • Haider H, Frensch P (1996) The role of information reduction in skill acquisition. Cognit Psychol 30(3): 304–337

    PubMed  Article  Google Scholar 

  • Hu M (1962) Visual pattern recognition by moment invariants. IEEE Trans Inf Theory 8(2): 179–187

    Article  Google Scholar 

  • Jagadeesh B, Chelazzi L, Mishkin M, Desimone R (2001) Learning increases stimulus salience in anterior inferior temporal cortex of the macaque. J Neurophysiol 86(1): 290–303

    PubMed  CAS  Google Scholar 

  • Jugessur D, Dudek G (2000) Local appearance for robust object recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol 1, 2000

  • Kietzmann TC, Lange S, Riedmiller M (2008) Incremental GRLVQ: Learning relevant features for 3D object recognition. Neurocomputing 71: 2868–2879

    Article  Google Scholar 

  • Kirstein S, Wersing H, Korner E (2005) Rapid online learning of objects in a biologically motivated recognition architecture. 27th Pattern Recognition Symposium DAGM, pp 301–308

  • Kobatake E, Tanaka K (1994) Neuronal selectivities to complex object features in the ventral visual pathway of the macaque cerebral cortex. J Neurophysiol 71(3): 856–867

    PubMed  CAS  Google Scholar 

  • Kobatake E, Wang G, Tanaka K (1998) Effects of shape-discrimination training on the selectivity of inferotemporal cells in adult monkeys. J Neurophysiol 80(1): 324–330

    PubMed  CAS  Google Scholar 

  • Koenderink J, Doorn A (1979) The internal representation of solid shape with respect to vision. Biol Cybern 32(4): 211–216

    PubMed  Article  CAS  Google Scholar 

  • Lange S, Riedmiller M (2006) Appearance based robot discrimination using eigenimages. In: Nardi D, Riedmiller M, Sammut C, Santos-Victor J (eds) RoboCup-2004: Robot Soccer World Cup VIII. Springer, LCNS, Berlin 2005

    Google Scholar 

  • Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11): 2278–2324

    Article  Google Scholar 

  • Leibe B, Schiele B (2003) Analyzing appearance and contour based methods for object categorization. Proc IEEE Conf Comput Vis Pattern Recognit (CVPR’03)

  • Logothetis N, Pauls J, Poggio T (1995) Shape representation in the inferior temporal cortex of monkeys. Curr Biol 5(5): 552–563

    PubMed  Article  CAS  Google Scholar 

  • Lowe D (1985) Perceptual Organization and Visual Recognition. Kluwer Academic Publishers, Norwell

    Google Scholar 

  • Lowe D (1999) Object recognition from local scale-invariant features. In: The Proceedings of the Seventh IEEE International Conference on Computer Vision,vol 2

  • Lowe D (2000) Towards a computational model for object recognition in it cortex. Biol Motiv Comput Vis 1811: 20–31

    Google Scholar 

  • Luong Chi M (2006) Introduction To Computer Vision and Computer Graphics. Institute of Information Technology, Hanoi, Vietnam

  • Mareschal D, Plunkett K, Harris P (1999) A computational and neuropsychological account of object-oriented behaviours in infancy. Dev Sci 2(3): 306–317

    Article  Google Scholar 

  • Marr D, Nishihara H (1978) Representation and Recognition of the Spatial Organization of Three-Dimensional Shapes. Proc R Soc Lond Ser B Biol Sci 200(1140): 269–294

    CAS  Article  Google Scholar 

  • Massad A, Mertsching B, Schmalz S (1998) Combining multiple views and temporal associations for 3-d object recognition. Proc ECCV 98: 699–715

    Google Scholar 

  • Maunsell J, Treue S (2006) Feature-based attention in visual cortex. Trends Neurosci 29(6): 317–322

    PubMed  Article  CAS  Google Scholar 

  • Mel B (1997) SEEMORE: Combining color, shape, and texture histogramming in a neurally-inspired approach to visual object recognition. Neural Comput 9(4): 777–804

    PubMed  Article  CAS  Google Scholar 

  • Milner A, Goodale M (1993) Visual pathways to perception and action. Prog Brain Res 95: 317–337

    PubMed  Article  CAS  Google Scholar 

  • Milner A, Goodale M (1996) The visual brain in action. Oxford University Press, NY

    Google Scholar 

  • Miyashita Y (1988) Neuronal correlate of visual associative long-term memory in the primate temporal cortex. Nature 335(6193): 817–820

    PubMed  Article  CAS  Google Scholar 

  • Miyashita Y (1993) Inferior temporal cortex: Where visual perception meets memory. Ann Rev Neurosci 16(1): 245–263

    PubMed  Article  CAS  Google Scholar 

  • Murphy-Chutorian E, Aboutalib S, Triesch J (2005) Analysis of a biologically-inspired system for real-time object recognition. Cognit Sci Online 3(2): 1–14

    Google Scholar 

  • Murray S, Wojciulik E (2004) Attention increases neural selectivity in the human lateral occipital complex. Nature Neurosci 7: 70–74

    PubMed  Article  CAS  Google Scholar 

  • Mutch J, Lowe D (2006) Multiclass object recognition with sparse, localized features. In: Proceedings of the 2006 IEEE computer society conference on computer vision and pattern recognition, vol 1, pp 11–18

  • Mutch J, Lowe D (2007) Object class recognition and localization using sparse features with limited receptive fields. In IJCV

  • Nene S, Nayar S, Murase H (1996) Columbia object image library (COIL-100). Techn. Rep. No. CUCS-006-96, dept. Comp. Science, Columbia University

  • Nosofsky R (1984) Attention, Similarity, and the Identification-Categorization Relationship. Dissertation, Harvard University

  • Obdrzalek S, Matas J (2002) Object recognition using local affine frames on distinguished regions. BMVC 2002, pp 113–122

  • Oliva A (2005) Gist of a scene. Neurobiology of attention, pp 251–256

  • Paletta L, Pinz A (2000) Active object recognition by view integration and reinforcement learning. Rob Auton Syst 31(1-2): 71–86

    Article  Google Scholar 

  • Palmer S, Rosch E, Chase P (1981) Canonical perspective and the perception of objects. Attention and performance IX, pp 135–151

  • Perrett D, Hietanen J, Oram M, Benson P, Rolls E (1992) Organization and functions of cells responsive to faces in the temporal cortex. Philos Trans Biol Sci 335(1273): 23–30

    Article  CAS  Google Scholar 

  • Perrett D, Mistlin A, Chitty A (1987) Visual cells responsive to faces. Trends Neurosci 10: 358–364

    Article  Google Scholar 

  • Perrett D, Oram M, Ashbridge E (1998) Evidence accumulation in cell populations responsive to faces: An account of generalization of recognition without mental transformations. Cognition 67: 111–145

    PubMed  Article  CAS  Google Scholar 

  • Perrett D, Oram M, Harries M, Bevan R, Benson P, Thomas S (1991) Viewer centered and object centered coding of heads in the macaque temporal cortex. Exp Brain Res 86: 159–173

    PubMed  Article  CAS  Google Scholar 

  • Poggio T, Edelman S (1990) A network that learns to recognize three-dimensional objects. Nature 343: 263–266 34

    PubMed  Article  CAS  Google Scholar 

  • Rao R (1997) Dynamic appearance-based recognition. In: Proceedings of computer vision and pattern recognition

  • Riesenhuber M, Poggio T (1999) Hierarchical models of object recognition in cortex. Nat Neurosci 2: 1019–1025

    PubMed  Article  CAS  Google Scholar 

  • Riesenhuber M, Poggio T (2000) Models of object recognition. Nat Neurosci 3: 1199–1204

    PubMed  Article  CAS  Google Scholar 

  • Riesenhuber M, Poggio T (2003) How visual cortex recognizes objects: The tale of the standard model. Vis Neurosci 2: 1640–1653

    Google Scholar 

  • Roobaert D, Van Hulle M (1999) View-based 3d object recognition with support vector machines. Neural Networks for Signal Processing IX, 1999. In: Proceedings of the 1999 IEEE Signal Processing Society Workshop, pp 77–84

  • Sakai K, Miyashita Y (1991) Neural organization for the long-term memory of paired associates. Nature 354(6349): 152–155

    PubMed  Article  CAS  Google Scholar 

  • Schneider G, Wersing H, Sendhoff B, Korner E, Schneider G, Wersing H (2004) Evolution of hierarchical features for visual object recognition. Third Workshop on SelfOrganization of AdaptiVE Behavior (SOAVE 2004) Ilmenau, pp 104–113

  • Seibert M, Waxman A (1992) Adaptive 3-d object recognition from multiple views. IEEE Trans Pattern Anal Mach Intell 14(2): 107–124

    Article  Google Scholar 

  • Serre T, Wolf L, Poggio T (2005) Object recognition with features inspired by visual cortex. In: IEEE Computer society conference on Computer vision and pattern recognition, 2005. CVPR 2005, vol 2

  • Shokoufandeh A, Marsic I, Dickinson S (1999) View-based object recognition using saliency maps. Image Vis Comput 17(5): 445–460

    Article  Google Scholar 

  • Strickert M, Bojer T, Hammer B (2001) Generalized relevance LVQ for time series. Springer, Berlin, pp 677–683

    Google Scholar 

  • Suard F, Rakotomamonjy A, Bensrhair A (2006) Object categorization using kernels combining graphs and histograms of gradients. In: International conference on image analysis and recognition, vol 2, pp 23–34

  • Tanaka K (1992) Inferotemporal cortex and higher visual functions. Curr Opin Neurobiol 2(4): 502–505

    PubMed  Article  CAS  Google Scholar 

  • Tanaka K (1996) Inferotemporal cortex and object vision. Ann Rev Neurosci 19(1): 109–139

    PubMed  Article  CAS  Google Scholar 

  • Tarr M, Bülthoff H (1995) Is human object recognition better described by geon-structural-descriptions or by multiple-views. J Exp Psychol Human Percept Perform 21(6): 1494–1505

    Article  CAS  Google Scholar 

  • Tarr M, Bülthoff H (1998) Image-based object recognition in man, monkey and machine. Cognition 67(1): 1–20

    PubMed  Article  CAS  Google Scholar 

  • Tarr M, Pinker S (1989) Mental rotation and orientation-dependence in shape recognition. Cognit Psychol 21(2): 233–282

    PubMed  Article  CAS  Google Scholar 

  • Teynor A, Rahtu E, Setia L, Burkhardt H, Teynor A, Rahtu E, Setia L, Burkhardt H (2006) Properties of patch based approaches for the recognition of visual object classes. In: Pattern recognition, DAGM 2006 Proceedings, lecture notes in computer science, vol 4174, pp 284–293

  • Thompson D, Mundy J (1987) Three-dimensional model matching from an unconstrained viewpoint. In: Proceedings of the IEEE International Conference on Robotics and Automation, vol 4

  • Tuytelaars T, Van Gool L et al (1999) Content-based image retrieval based on local affinely invariant regions. International conference on visual information systems, pp 493–500

  • Ullman S, Basri R (1991) Recognition by linear combinations of models. IEEE Trans Pattern Anal Mach Intell 13(10): 992–1006

    Article  Google Scholar 

  • Ullman S, Vidal-Naquet M, Sali E (2002) Visual features of intermediate complexity and their use in classification. Nat Neurosci 5: 682–687

    PubMed  CAS  Google Scholar 

  • Voigtländer A, Lange S, Lauer M, Riedmiller M (2007) Real-time 3d ball recognition using perspective and catadioptric cameras. In ECMR 2007

  • Vuilleumier P, Henson R, Driver J, Dolan R (2002) Multiple levels of visual object constancy revealed by event-related fMRI of repetition priming. Nat Neurosci 5(5): 491–499

    PubMed  Article  CAS  Google Scholar 

  • Wallis G (1996) How neurons learn to associate 2d-views in invariant object recognition. Technical report, Technical Report No

  • Wallis G (1998) Temporal order in human object recognition learning. J Biol Syst 6(3): 299–313

    Article  Google Scholar 

  • Wallis G, Bülthoff H (1999) Learning to recognize objects. Trends Cognit Sci 3(1): 22–31

    Article  Google Scholar 

  • Wallis G, Bülthoff H (2001) Effects of temporal association on recognition memory. Proc Natl Acad Sci 98(8): 4800–4804

    PubMed  Article  CAS  Google Scholar 

  • Wallraven C, Bülthoff H (2001a) Automatic acquisition of exemplar-based representations for recognition from image sequences. In: Proceedings of the CVPR’01-workshop models versus exemplars, vol 28

  • Wallraven C, Bülthoff H (2001b) View-based recognition under illumination changes using local features. In: Proceedings of the CVPR’01-workshop on identifying objects across variations in lighting: psychophysics and computation, vol 3

  • Walther D, Fei-Fei L (2007) Task-set switching with natural scenes: Measuring the cost of deploying top-down attention. J Vis 7(11): 9

    PubMed  Article  Google Scholar 

  • Wersing H, Korner E (2002) Unsupervised learning of combination features for hierarchical recognition models. International conference on artificial neural network, ICANN. 11

  • Würtz R (1995) Multilayer dynamic link networks for establishing image point correspondences and visual object recognition. Verlag Harri Deutsch

  • Young M, Yamane S (1992) Sparse population coding of faces in the inferotemporal cortex. Science 256(5061): 1327

    PubMed  Article  CAS  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institute of Cognitive Science, University of Osnabrück, Osnabrück, Germany

    Tim C. Kietzmann

  2. Institute of Computer Science, University of Osnabrück, Osnabrück, Germany

    Sascha Lange & Martin Riedmiller

Authors
  1. Tim C. Kietzmann
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sascha Lange
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Martin Riedmiller
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Tim C. Kietzmann.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Kietzmann, T.C., Lange, S. & Riedmiller, M. Computational object recognition: a biologically motivated approach. Biol Cybern 100, 59 (2009). https://doi.org/10.1007/s00422-008-0281-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s00422-008-0281-6

Keywords

  • Biologically inspired computer vision
  • Object recognition
  • View-based object representations
  • Feature selection
  • Incremental learning