Skip to main content
SpringerLink
Log in

A feature binding computational model for multi-class object categorization and recognition

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

We propose a feature binding computational model based on the cognitive research findings. Feature integration theory is widely approved on the principles of the binding problem, which supplies the roadmap for our computational model. We construct the learning procedure to acquire necessary pre-knowledge for the recognition network on reasonable hypothesis–maximum entropy. With the recognition network, we bind the low-level image features with the high-level knowledge. Fundamental concepts and principles of conditional random fields are employed to model the feature binding process. We apply our model to current challenging problems, multi-label image classification and object recognition, and evaluate it on the benchmark image databases to demonstrate that our model is competitive to the state-of-the-art method.

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

Access this article

Log in via an institution

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

Similar content being viewed by others

References

  1. Crick F (1984) Functions of the thalamic reticular complex: the searchlight hypothesis. Proc Natl Acad Sci USA 81:4586–4590

    Article  Google Scholar 

  2. Sejnowski TJ (1986) Open questions about computation in cerebral cortex. In: McClelland JL, Rumelhart DE (eds) Parallel distributed processing. MIT Press, Cambridge, pp 372–389

    Google Scholar 

  3. Treisman A, Gelede G (1980) A feature-integration theory of attention. Cognit Psychol 12:97–136

    Article  Google Scholar 

  4. Gray CM, König P, Engel AK et al (1989) Oscillatory responses in cat visual cortex exhibit inter-columnar synchronization which reflects global stimulus properties. Nature 338:334–337

    Article  Google Scholar 

  5. Damasio AR (1989) The brain binds entities and events by multiregional activation from convergence zones. Neur Comput 1:123–132

    Article  Google Scholar 

  6. Treisman A (1998) Feature binding, attention and object perception. Phil Trans R Soc Lond B 353:1295–1306

    Article  Google Scholar 

  7. Quinlan PT (2003) Visual feature integration theory: past, present, and future. Psycholog Bull 129(5):643–673

    Article  Google Scholar 

  8. Houck MR, Hoffman JE (1986) Conjunction of color and form without attention: evidence from an orientation-contingent color after-effect. J Exp Psychol Human Percept Perform 12:186–199

    Article  Google Scholar 

  9. Nakayama K (1990) The iconic bottleneck and the tenuous link between early visual processing and perception. In: Blakemore C (ed) Vision: coding and efficiency. Cambridge University Press, Cambridge, pp 411–422

    Google Scholar 

  10. Gman D, Geman S, Graffigne C, Dong P (1990) Boundary detection by constrained optimization. IEEE Trans Pattern Anal Mach Intel 12(7):609–628

    Article  Google Scholar 

  11. Wersing H, Jochen JS, Ritter H (2001) A competitive layer model for feature binding and sensory segmentation. Neural Comput 13(2):357–387

    Article  MATH  Google Scholar 

  12. Shi ZW, Shi ZZ, Liu X, Shi ZP (2008) A computational model for feature binding. Sci China Ser C: Life Sci 38(5):485–493

    MathSciNet  Google Scholar 

  13. Shutton J, Winn J, Rother C, Criminisi A (2009) Textonboost for image understanding: multi-class object recognition and segmentation by jointly modeling texture, layout, and context. IJCV 81:2–23

    Article  Google Scholar 

  14. Li T, Kweon IS (2008) A semantic region descriptor for local feature based image classification. In ICASSP

  15. Lafferty A, McCallum, Pereira FCN (2001) Conditional random fields: probabilistic models for segmenting and labelling sequence data. In: Proceedings of the eighteenth international conference on machine learning (ICML 2001), Williams town, MA, USA, pp 282–289

  16. Hanna Wallach (2003) Efficient training of conditional random fields, pp 31–32

  17. Sha F, Pereira F (2003) Shallow parsing with conditional random fields. Proc HLT-NAACL 213–220N

  18. Chen SF, Rosenfeld R (1999) A Gaussian prior for smoothing maximum entropy models. Technical Report CMU-CS-99-108, Carnegie Mellon University

  19. Byrd RH, Nocedal J, Schnabel RB (1994) Representations of quasi-newton matrices and their use in limited memory methods. Math Prog 63:129–156

    Article  MathSciNet  MATH  Google Scholar 

  20. Viterbi AJ (1967) Error bounds for convolutional codes and an asymptotical optimum decoding algorithm. IEEE Trans Inform Theory IT 13:260–269

    Article  MATH  Google Scholar 

  21. Xuan P, Minh Le N http://www.jaist.ac.jp/~hieuxuan/flexcrfs/flexcrfs.html

Download references

Acknowledgments

We would like to thank Shutton et al. for their open source code of their work in [13]. Our work is supported by the National Basic Research Priorities Programme (No. 2007CB311004), National Science and Technology Support Plan (No. 2006BAC08B06), and National Science Foundation of China (No.60775035, No. 60903141, No. 60933004, No. 60970088).

Author information

Authors and Affiliations

  1. The Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Graduate University of Chinese Academy of Sciences, Chinese Academy of Sciences, Beijing, 100190, China

    Xishun Wang, Xi Liu, Zhongzhi Shi & Hongjian Sui

Authors
  1. Xishun Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xi Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhongzhi Shi
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Hongjian Sui
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xishun Wang.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Wang, X., Liu, X., Shi, Z. et al. A feature binding computational model for multi-class object categorization and recognition. Neural Comput & Applic 21, 1297–1305 (2012). https://doi.org/10.1007/s00521-011-0562-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-011-0562-1

Keywords

Search

Navigation