Skip to main content
Log in

3D Object Recognition Based on Some Aspects of the Infant Vision System and Associative Memory

  • Published:
Cognitive Computation Aims and scope Submit manuscript

Abstract

A view-based method for 3D object recognition based on some biological aspects of infant vision is proposed in this paper. The biological hypotheses of this method are based on the role of the response to low frequencies at early stages as well as some conjectures concerning how an infant detects subtle features (stimulating points) from an object. In order to recognize an object from different images of it (at different orientations from 0° to 360°), we make use of a dynamic associative memory (DAM). As the infant vision responds to low frequencies of the signal, a low-filter is first used to remove high frequency components from the image. Then, we detect subtle features in the image by means of a random feature selection detector. At last, the DAM is fed with this information for training and recognition. To test the accuracy of the proposed model, we use the Columbia Object Image Library (COIL 100) database.

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

Access this article

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

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

  1. Poggio T, Edelman S. A network that learns to recognize 3d objects. Nature. 1990;343:263–6.

    Article  CAS  PubMed  Google Scholar 

  2. Turk M, Pentland A. Eigenfaces for recognition. J Cogn Neurosci. 1991;3(1):71–86.

    Article  Google Scholar 

  3. Murase H, Nayar SK. Visual learning and recognition of 3-d objects from appearance. Int J Comput Vis. 1995;14:5–24.

    Article  Google Scholar 

  4. Nayar SK, Nene SA, Murase H. Real-time 100 object recognition system. In: Proceedings of IEEE international conference on robotics and automation; 1996. pp. 2321–5.

  5. Hotta K. Pose independent object classification from small number of training samples based on kernel principal component analysis of local parts. Image Vis Comput. 2009;27(9):1240–51.

    Article  Google Scholar 

  6. Nagabhushan P, Guru DS, Shekar BH. Visual learning and recognition of 3D objects using two-dimensional principal component analysis: a robust and an efficient approach. Pattern Recogn. 2006;39(4):721–5.

    Article  Google Scholar 

  7. Schölkopf B. Support Vector Learning. PhD thesis, Informatik der Technischen Universitat Berlin; 1997.

  8. Pontil M, Verri A. Support vector machines for 3d object recognition. IEEE Trans Pattern Anal Mach Intell. 1998;20(6):637–46. (1998).

    Article  Google Scholar 

  9. Roobaert D, Hulle MV. View-based 3d object recognition with support vector machines. In: Proceedings of IEEE international workshop on neural networks for signal processing; 1999. pp. 77–84.

  10. Kietzmann TC, Lange S, Riedmille M. Incremental GRLVQ: learning relevant features for 3D object recognition. Neurocomputing. 2008;71(13–15):2868–79.

    Article  Google Scholar 

  11. Yamashita W, Wang G, Tanaka K. View-invariant object recognition ability develops after discrimination, not mere exposure, at several viewing angles. Eur J Neurosci. 2010;31(2):327–35.

    Article  PubMed  Google Scholar 

  12. Ison MJ, Quiroga RQ. Selectivity and invariance for visual object perception. Front Biosci. 2008;13:4889–903.

    Article  PubMed  Google Scholar 

  13. Farivar R. Dorsal–ventral integration in object recognition. Brain Res Rev. 2009;61(2):144–53.

    Article  PubMed  Google Scholar 

  14. Stringer SM, Rolls ET. Invariant object recognition in the visual system with novel views of 3D objects. Neural Comput. 2002;14(11):2585–96.

    Article  PubMed  Google Scholar 

  15. Stringer SM, Rolls ET. Learning transform invariant object recognition in the visual system with multiple stimuli present during training. Neural Netw. 2008;21(7):888–903.

    Article  CAS  PubMed  Google Scholar 

  16. Hosoda K, Watanabe M, Wersing H, Körner E, Tsujino H, Tamura H, et al. A model for learning topographically organized parts-based representations of objects in visual cortex: topographic nonnegative matrix factorization. Neural Comput. 2009;21(9):2605–33.

    Article  PubMed  Google Scholar 

  17. Michler F, Eckhorn R, Wachtler T. Using spatiotemporal correlations to learn topographic maps for invariant object recognition. J Neurophysiol. 2009;102:953–64.

    Article  PubMed  Google Scholar 

  18. Hunnius S. The early development of visual attention and its implications for social and cognitive development. Prog Brain Res. 2007;164:187–209.

    Article  PubMed  Google Scholar 

  19. Banks MS, et al. Infant pattern vision: a new approach based on the contrast sensitivity function. J Exp Child Psychol. 1981;31:1–45.

    Article  CAS  PubMed  Google Scholar 

  20. Barlow H. Redundancy reduction revisited. Network: Comput Neural Syst. 2001;12:241–53.

    CAS  Google Scholar 

  21. Vazquez RA, Sossa H, Garro BA. Low frequency responses and random feature selection applied to face recognition. In: Kamel M, Campilho A, editors. ICIAR 2007. LNCS, vol. 4633. Heidelberg: Springer; 2007. p. 818–30.

    Google Scholar 

  22. Vazquez RA, Sossa H, Garro BA. 3D Object recognition based on low frequency responses and random feature selection. LNAI. 2007;4827:694–704.

    Google Scholar 

  23. Mondloch CJ, et al. Face perception during early infancy. Psychol Sci. 1999;10(5):419–22.

    Article  Google Scholar 

  24. Acerra F, Burnod Y, Schonen S. Modelling aspects of face processing in early infancy. Dev Sci. 2002;5(1):98–117.

    Article  Google Scholar 

  25. Slaughter V, Stone VE, Reed C. Perception of faces and bodies similar or different? Curr Dir Psychol Sci. 2004;13(9):219–23.

    Article  Google Scholar 

  26. Cuevas K, Rovee-Collier C, Learmonth AE. Infants form associations between memory representations of stimuli that are absent. Psychol Sci. 2006;17(6):543–9.

    Article  PubMed  Google Scholar 

  27. Nayar SK, Nene SA, Murase H Columbia Object Image Library (COIL 100). Tech. Report No. CUCS-006-96. Department of Comp. Science, Columbia University, 1996.

  28. Sossa H, Barrón R, Vázquez RA. Transforming Fundamental set of Patterns to a Canonical Form to Improve Pattern Recall. In: Lemaître C, Reyes CA, González JA, editors. IBERAMIA 2004. LNCS (LNAI), vol. 3315. Heidelberg: Springer; 2004. p. 687–96.

    Google Scholar 

  29. Sossa H, Barron R, Vazquez RA. Study of the influence of noise in the values of a median associative memory. In: Beliczynski B, et al., editors. ICANNGA 2007, Part II. LNCS, vol. 4432. Heidelberg: Springer; 2007. p. 55–62.

    Google Scholar 

  30. Laughlin SB, Sejnowski TJ. Communication in neuronal networks. Science. 2003;301:1870–4.

    Article  CAS  PubMed  Google Scholar 

  31. Vazquez RA, Sossa H. A new associative memory with dynamical synapses. Neural Process Lett. 2008;28(3):189–207.

    Article  Google Scholar 

  32. Vazquez RA, Sossa H. Associative memories applied to image categorization. In: Martínez-Trinidad JF, Carrasco Ochoa JA, Kittler J, editors. CIARP 2006. LNCS, vol. 4225. Heidelberg: Springer; 2006. p. 549–58.

    Google Scholar 

  33. Vazquez RA, Sossa H, Garro BA. A bidirectional hetero-associative memory for true-color patterns. Neural Process Lett. 2008;28(3):131–53.

    Article  Google Scholar 

  34. Vazquez RA, Sossa H. A computational approach for modeling the infant vision system in object and face recognition. J BMC Neurosci. 2007;8(suppl 2):P204.

    Article  Google Scholar 

  35. Carver L, et al. Associations between infant brain activity and recall memory. Devel Sci. 2001;3(2):234–46.

    Article  Google Scholar 

  36. Kraebel KS, Gerhardstein PC. Three-month old infants’ object recognition across changes in viewpoint using an operant learning procedure. Infant Behav Dev. 2006;29:11–23.

    Article  PubMed  Google Scholar 

  37. Gerhardstein PC, Shroff G, Dickerson K, Adler SA. The development of object recognition through infancy. In: Glenyn BC, Zini RP, editors. New directions in developmental psychobiology. Nova Science Publishers: New York; 2009.

    Google Scholar 

  38. Treisman A, Gelade G. A feature-integration theory of attention. Cogn Psychol. 1980;12(1):97–136.

    Article  CAS  PubMed  Google Scholar 

  39. Biederman I. Recognition-by-components: a theory of human image understanding. Psychol Rev. 1987;94(2):115–47.

    Article  CAS  PubMed  Google Scholar 

  40. Box GEP, Muller ME. A note on the generation of random normal deviates. Ann Math Stat. 1958;29(2):610–1.

    Article  Google Scholar 

  41. Vazquez R, Sossa H. A computational approach for modeling the role of the focus visual attention in an object categorization task. BMC Neurosci. 2009;10(Suppl 1):P310.

    Article  Google Scholar 

  42. Treisman A. How the deployment of attention determines what we see. Vis Cogn. 2006;14:411–43.

    Article  PubMed  Google Scholar 

Download references

Acknowledgments

The authors thank SIP-IPN for the economical support under grant number 20091421. H. Sossa thanks the SIP-IPN under grant 20091421 for the support. H. Sossa also thanks CINVESTAV-GDL for the support to do a sabbatical stay from December 1, 2009 to May 31, 2010. Authors thank the European Union, the European Commission and CONACYT for the economical support. This paper has been prepared by economical support of the European Commission under grant FONCICYT 93829. The content of this paper is an exclusive responsibility of the CIC-IPN and it cannot be considered that it reflects the position of the European Union. We thank also the reviewers for their comments for the improvement of this paper.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Roberto A. Vázquez.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Vázquez, R.A., Sossa, H. & Garro, B.A. 3D Object Recognition Based on Some Aspects of the Infant Vision System and Associative Memory. Cogn Comput 2, 86–96 (2010). https://doi.org/10.1007/s12559-010-9038-3

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12559-010-9038-3

Keywords

Navigation