Skip to main content
SpringerLink
Log in

A Perceptual Visual Feature Extraction Method Achieved by Imitating V1 and V4 of the Human Visual System

  • Published:
Cognitive Computation Aims and scope Submit manuscript

Abstract

In this paper, we present a new shape encoding method for object recognition. We first introduce a neuro-physiologically inspired visual part detector and shape encoder. The optimal form of the visual part detector is a combination of a circular symmetry detector and a corner-like structure detector. A perceptually novel shape descriptor, known as the curvature-orientation descriptor, is then discussed. This descriptor encodes the curvature as well as the dominant orientation. The perceptual shape encoder enhances the performance of feature matching and object recognition taken from standard test images. The results from the repeatability and object recognition tests validate the feasibility of the proposed perceptual feature extraction 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
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21
Fig. 22
Fig. 23
Fig. 24

Similar content being viewed by others

References

  1. Bay H, Tuytelaars T, Gool LV. SURF: speeded up robust features. In: Proceedings of European conference of computer vision (ECCV) 2006.

  2. Belongie S, Malik J, Puzicha J. Shape matching and object recognition using shape contexts. IEEE Trans Pattern Anal Mach Intell. 2002;24(24):509–22.

    Article  Google Scholar 

  3. Boynton G. Adaptation and attentional selection. Nat Neurosci. 2004;7(1):8–10.

    Article  PubMed  CAS  Google Scholar 

  4. Chomat O, de Verdière VC, Hall D, Crowley JL. Local scale selection for gaussian based description techniques. In: Proceedings of the European conference of computer vision (ECCV), 2000. p. 117–33.

  5. Connor CE, Brincat SL, Pasupathy A. Transformation of shape information in the ventral pathway. Curr Opin Neurobiol. 2007;17(2):140–7.

    Google Scholar 

  6. Deng H, Zhang W, Mortensen E, Dietterich T, Shapiro L. Principal curvature-based region detector for object recognition. In: IEEE conference on computer vision and patter recognition (CVPR), 2007. p. 1–8.

  7. Dobbins A, Zucker SW, Cynader MS. Endstopping and curvature. Vision Res. 1989;29(10):1371–87.

    Article  PubMed  CAS  Google Scholar 

  8. Donias M, Baylou P, Keskes N. Curvature of oriented patterns: 2-D and 3-D estimation from differential geometry. In: ICIP (1), 1998. p. 236–40.

  9. Gawne T, Martin J. Responses of primate visual cortical V4 neurons to simultaneously presented stimuli. J Neurophysiol 2002;88:1128–35.

    PubMed  Google Scholar 

  10. van Ginkel M, van de Weijer J, van Vliet LJ, Verbeek PW. Curvature estimation from orientation fields. In: SCIA, 1999. p. 545–51.

  11. Han JH, Poston T. Chord-to-point distance accumulatin and planar curvature: a new approach to discrte curvature. Patt Recognit Lett 2001;22:1133–44.

    Article  Google Scholar 

  12. Harris C, Stephens M. A combined corner and edge detector. In: Proceedings of the 4th alvey vision conference 1988.

  13. Hoffman DD. Visual intelligence: how to create what we see. New York, NY: Norton; 1998.

    Google Scholar 

  14. Hubel D, Wiesel T. Receptive fields and functional architecture in two nonstriate visual areas (18 and 19) of the cat. J Neurophysiol. 1965;28:229–89.

    PubMed  CAS  Google Scholar 

  15. Join C, Tabbone S. Robust curvature extrema detection based on new numerical derivation. Lect Notes Comput Sci. 2008;5259:485–93.

    Article  Google Scholar 

  16. Jones JP, Palmer L. An evaluation of the two-dimensional gabor filter model of simple receptive fields in cat striate cortex. J Neurophysiol. 1987;58:1233–58.

    PubMed  CAS  Google Scholar 

  17. Kass M, Witkin AP. Analyzing oriented patterns. Comput Vision Graph Image Process. 1987;37(3):362–85.

    Article  Google Scholar 

  18. Ke Y, Sukthankar R. PCA-SIFT: A more distinctive representation for local image descriptors. In: IEEE conference on computer vision and patter recognition (CVPR), 2004. p. 506–13.

  19. Kopf S, Haenselmann T, Effelsberg W. Enhancing curvature scale space features for robust shape classification. In: Proceedings of IEEE international conference on multimedia and expo (ICME), 2005. p. 1–8.

  20. Kouh M, Riesenhuber M. Investigating shape representation in area V4 with hmax: orientation and grating selectivities. Tech. Rep. AIM2003-021, Massachusetts Institute of Technology, 2003.

  21. Kuhnel W. Differential geometry: curves-surfaces-manifolds, vol. 2. Providence, RI: American Mathematical Society; 2002.

    Google Scholar 

  22. Latecki L, Lakämper R. Convexity rule for shape decomposition based on discrete contour evolution. Int J Comput Vision Image Underst. 1999;73(3):441–54.

    Article  Google Scholar 

  23. Lin WY, Chiu YL, R.Widder K, Hu YH, Boston N. Robust and accurate curvature estimation using adaptive line integrals. EURASIP J Adv Signal Process. 2010;2010:485–493.

    Google Scholar 

  24. Lowe D. Distinctive image features from scale-invariant keypoints. Int J Comput Vision. 2004;60(2):91–110

    Article  Google Scholar 

  25. Loy G, Zelinsky A. Fast radial symmetry transform for detecting points of interest. IEEE Trans Pattern Anal Mach Intell. 2003;25(8):959–73.

    Article  Google Scholar 

  26. Matas J, Chum O, Urban M, Pajdla T. Robust wide baseline stereo from maximally stable extremal regions. In: Proceedings of the British machine vision conference (BMVC), 2002.

  27. Mikolajcyk K, Schmid C. An affine invariant interest point detector. In: Proceedins of the international conference on computer vision (ICCV) 2002.

  28. Mikolajczyk K, Schmid C. Performance evaluation of local descriptors. IEEE Trans Pattern Anal Mach Intell 2005;27(10):1615–30.

    Article  PubMed  Google Scholar 

  29. Mokhtarian F, Suomela R. Robust image corner detection through curvature scale space. IEEE Trans Pattern Anal Mach Intell 1998;20(12):1376–81.

    Article  Google Scholar 

  30. Papacostas GA, Boutalis YS, Karras DA, Mertzios BG. A new class of zernike moments for computer vision applications. Inf Sci 2007;177:2802–19.

    Article  Google Scholar 

  31. Pasupathy A, Connor C. Shape representation in area V4: position-specific tuning for boundary conformation. J Neurophysiol. 2001;86(5):2505–19.

    PubMed  CAS  Google Scholar 

  32. Qi H, Li K, Shen Y, Qu W. An effective solution for trademark image retrieval by combining shape description and feature matching. Pattern Recognit. 2010;43(6):2017–27.

    Google Scholar 

  33. Qian G, Sural S, Gu Y, Pramanik S. Similarity between euclidean and cosine angle distance for nearest neighbor queries. In: Proceedings of 2004 ACM symposium on applied computing, 2004. p. 1232–7. New York: ACM Press.

  34. Raftopoulos KA, Kollias SD. Visual pathways for shape abstraction. Lect Notes Comput Sci. 2011;6791:291–8.

    Article  Google Scholar 

  35. Raftopoulos KA, Papadakis N, Ntalianis K, Kollias S. A visual pathway for shape-based invariant classification of gray scale images. Integr Comput Aided Eng. 2007;14(4):365–78.

    Google Scholar 

  36. Rao RPN, Ballard DH. Predictive coding in the visual cortex: a functional interpretation of some extra-classical receptive-field effects. Nat Neurosci. 1999;20(1):79–87.

    Article  CAS  Google Scholar 

  37. Reisfeld D, Wolfson H, Yeshurun Y. Context-free attentional operators: the generalized symmetry transform. Int J Comput Vision. 1995;14(2):119–30.

    Article  Google Scholar 

  38. Ringach D. Spatial structure and symmetry of simple-cell receptive field in macaque primary visual cortex. J Neurophysiol. 2002;88:455–63.

    PubMed  Google Scholar 

  39. Rosten E, Drummond T. Machine learning for high speed corner detection. In: Proceedings of the European conference of computer vision (ECCV) 2006.

  40. Schmid C, Mohr R, Bauckhage C. Evaluation of interest point detectors. Int J Comput Vision. 2000;37(2):151–72.

    Article  Google Scholar 

  41. Serre T, Wolf L, Poggio T. Object recognition with features inspired by visual cortex. In: IEEE conference on computer vision and patter recognition (CVPR) 2005.

  42. Stoker J. Differential geometry. New York: Wiley; 1969.

    Google Scholar 

  43. Tico M, Kuosmanen P. Fingerprint matching using an orientation-based minutia descriptor. IEEE Trans Pattern Anal Mach Intell. 2003;25(8):1009–14.

    Article  Google Scholar 

  44. Toews M, III WMW. Sift-rank: ordinal description for invariant feature correspondence. In: IEEE conference on computer vision and pattern recognition, 2009. p. 172–7.

  45. Winter JD, Wagemans J. Perceptual saliency of points along the contour of everyday objects: a large-scale study. Percept Psychophys. 2008;70(1):50–64.

    Article  PubMed  Google Scholar 

  46. Yau JM, Pasupathy A, Brincat SL, Connor CE. Curvature processing dynamics in macaque area V4. Cerebral Cortex, 2012.

  47. Zang D, Li J, Zhang D. Robust visual correspondence computation using monogenic curvature phase based mutual information. Opt Lett. 2012;37:10–2.

    Article  PubMed  Google Scholar 

Download references

Acknowledgments

This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Science and Technology (No. 2012-0003252). It was also supported by DGIST R&D Program of the Ministry of Education, Science and Technology of Korea(12-BD-0202) and by National Strategic R&D Program for Industrial Technology, Korea.

Author information

Authors and Affiliations

  1. Department of Electronic Engineering, LED-IT Fusion Technology Research Center, Yeungnam University, 214-1 Dae-dong Gyeongsan-si Gyeongsangbuk-do, Gyeongsan, 712-749, Korea

    Sungho Kim

  2. Daegu Gyeongbuk Institute of Science and Technology, 50-1, Sang-ri Hyeonpung-myeon, Dalseong-gun, Daegu, 711-873, Korea

    Soon Kwon

  3. Department of Electrical Engineering, Korea Advanced Institute of Science and Technology, 373-1 Guseong-dong, Yuseong-gu, Daejeon, 305-701, Korea

    In So Kweon

Authors
  1. Sungho Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Soon Kwon
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. In So Kweon
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sungho Kim.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Kim, S., Kwon, S. & Kweon, I.S. A Perceptual Visual Feature Extraction Method Achieved by Imitating V1 and V4 of the Human Visual System. Cogn Comput 5, 610–628 (2013). https://doi.org/10.1007/s12559-012-9194-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12559-012-9194-8

Keywords

Search

Navigation