Skip to main content
SpringerLink
Log in

A computational feature binding model of human texture perception

  • Research Report
  • Published:
Cognitive Processing Aims and scope Submit manuscript

Abstract

We present a computational model for human texture perception which assigns functional principles to the Gestalt laws of similarity and proximity. Motivated by early vision mechanisms, in the first stage, local texture features are extracted by utilizing multi-scale filtering and nonlinear spatial pooling. In the second stage, features are grouped according to the spatial feature binding model of the competitive layer model (CLM; Wersing et al. 2001). The CLM uses cooperative and competitive interactions in a recurrent network, where binding is expressed by the layer-wise coactivation of feature-representing neurons. The Gestalt law of similarity is expressed by a non-Euclidean distance measure in the abstract feature space with proximity being taken into account by a spatial component. To choose the stimulus dimensions which allow the most salient similarity-based texture segmentation, the feature similarity metrics is reduced to the directions of maximum variance. We show that our combined texture feature extraction and binding model performs segmentation in strong conformity with human perception. The examples range from classical microtextures and Brodatz textures to other classical Gestalt stimuli, which offer a new perspective on the role of texture for more abstract similarity grouping.

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 (a)
Fig. 10
Fig. 11
Fig. 12
Fig. 13a–g
Fig. 14
Fig.15
Fig. 16

Similar content being viewed by others

References

  • Albrecht DG, Hamilton DB (1982) Striate cortex of monkey and cat: contrast response function. J Neurophysiol 48(1):217–237

    CAS  PubMed  Google Scholar 

  • Bergen JR, Adelson EH (1988) Early vision and texture perception. Nature 333:363–364

    Article  CAS  PubMed  Google Scholar 

  • Besag J, Green P, Higdon D, Mengersen K (1995) Bayesian computation and stochastic systems. Stat Sci 1:3–66

    Google Scholar 

  • Bovik AC, Clark M, Geisler WS (1990) Multichannel texture analysis using localized spatial filters. IEEE Trans Pattern Anal Mach Intel 12(1):55–73

    Article  Google Scholar 

  • Brodatz P (1966) Texture: a photographic album for artists and designers. Dover, New York

  • Cesmeli E Wang DL (2001) Texture segmentation using Gaussian–Markov random fields and neural oscillator networks. IEEE Trans Neural Netw 12:394–404

    Article  Google Scholar 

  • Chubb C Landy MS (1991) Orthogonal distribution analysis: a new approach to the study of texture perception. In: Landy MS, Movshon JA (eds) Computational models of visual processing. MIT Press, Boston, pp 291–301

  • Daugman JG (1985) Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. J Optic Soc Am A 2(7):1160–1169

    CAS  Google Scholar 

  • Daugman JG (1988) Complete discrete 2D Gabor transforms by neural networks for image analysis and compression. IEEE Trans Acoust Speech Signal Process 36(7):1169–1179

    Article  Google Scholar 

  • Dunn D, Higgins WE, Wakeley J (1994) Texture segmentation using 2D Gabor elementary functions. IEEE Trans Pattern Anal Mach Intel 16(2):130–149

    Article  Google Scholar 

  • Feng J (1997) Lyapunov functions for neural nets with nondifferentiable input–output characteristics. Neural Comput 9:43–49

    CAS  PubMed  Google Scholar 

  • Fogel I, Sagi D (1989) Gabor filters as texture discriminator. Biol Cyber 61:103–113

    Google Scholar 

  • Giese MA (1999) Dynamic neural field theory for motion perception. Kluwer, Dordrecht

  • Graham N, Beck J, Sutter A (1992) Nonlinear processes in spatial-frequency channel models of perceived texture segregation: effects of sign and amount of contrast. Vision Res 32(4):719–743

    Article  CAS  PubMed  Google Scholar 

  • Grossberg S, Williamson JR (1999) A self organizing neural system for learning to recognize textured scenes. Vision Res 39(7):1385–1406

    Article  CAS  PubMed  Google Scholar 

  • Hahnloser RHR, Sarpeshkar R, Mahowald MA, Douglas RJ, Seung HS (2000) Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit. Nature 405:947–951

    Article  CAS  PubMed  Google Scholar 

  • Hancock PJB, Baddeley RJ, Smith LS (1992) The principal components of natural images. Network 3:61–70

    Article  Google Scholar 

  • Hofmann T, Puzicha J, Buhmann J (1996) A deterministic annealing framework for unsupervised texture segmentation. Tech Rep IAI-TR-96. University of Bonn

  • Hofmann T, Puzicha J, Buhmann JM (1998) Unsupervised texture segmentation in a deterministic annealing framework. IEEE Trans Pattern Anal Mach Intel 20(8):803–818

    Article  Google Scholar 

  • Hupe JM, James AC, Girard P, Bullier J (2001) Response modulations by static textures surround in area V1 of the macaque monkey do not depend on feedback connections from V2. J Neurophysiol 85(1):146–163

    PubMed  Google Scholar 

  • Jähne B (1993) Digitale Bildverarbeitung. Springer, Berlin Heidelberg New York

  • Jain AK, Farrokhina F (1991) Unsupervised texture segmentation using Gabor filters. Pattern Recog 24(12):1167–1186

    Article  Google Scholar 

  • Jones J, Palmer L (1987) An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex. J Neurophysiol 58:1233–1258

    CAS  PubMed  Google Scholar 

  • Julesz B (1981) Textons, the elements of texture perception and their interaction. Nature 290:91–97

    CAS  PubMed  Google Scholar 

  • Kreiter AK, Singer W (1996) Stimulus-dependent synchronization of neural responses in the visual cortex of the awake macaque monkey. J Neurosci 16:2381–2396

    CAS  PubMed  Google Scholar 

  • Kröse BJ (1987) Local structure analyzers as determinants of preattentive pattern discrimination. Biol Cybernetics 55:289–298

    Google Scholar 

  • Lamme VAF, Spekreijse H (1998) Neuronal synchrony does not represent texture segregation. Nature 396:362–366

    CAS  PubMed  Google Scholar 

  • Landy MS, Bergen JR (1991) Texture segregation and orientation gradient. Vision Res 31(4):679–691

    Article  CAS  PubMed  Google Scholar 

  • Lee TS (1996) Image representation using 2D Gabor wavelets. IEEE Trans Pattern Anal Mach Intel 18(10):959–971

    Article  Google Scholar 

  • Ma WY, Manjunath BS (1996) Texture features and learning similarity. In: Proc IEEE Int Conf on Computer Vision and Pattern Recognition (CVPR), San Francisco, California

  • Malik J, Perona P (1990) Preattentive texture discrimination with early vision mechanisms. J Optic Soc Am A 7(5)

  • Malsburg von der C, Buhmann J (1992) Sensory segmentation with coupled oscillators. Biol Cybernetics 54:29–40

    Google Scholar 

  • Manjunath BS, Chellappa R (1993) A unified approach to boundary perception: edges, textures, and illusory contours. IEEE Trans Neural Netw 4(1):96–107

    Article  Google Scholar 

  • Manjunath BS, Ma WY (1996) Texture features for browsing and retrieval of image data. IEEE Trans Pattern Anal Mach Intel 18(8):837–842

    Article  Google Scholar 

  • Nattkemper TW, Wersing H, Schubert W, Ritter H (2000) Fluorescence micrograph segmentation by gestalt-based feature binding. In: Proc IEEE Int Joint Conf on Neural Networks (IJCNN), Como, Italy, pp 248–254

  • Nothdurft HC (1985) Sensitivity for structure gradient in texture discrimination tasks. Vision Res 25(12):1957–1968

    Article  CAS  PubMed  Google Scholar 

  • Nothdurft HC (1991) Different effects from spatial frequency masking in texture segregation and texton detection tasks. Vision Res 31:299–320

    Article  CAS  PubMed  Google Scholar 

  • Nothdurft HC, Gallant JL, Van Essen DC (2000) Response profiles to texture border patterns in area V1. J Neurophysiol 16(3):421–436

    Google Scholar 

  • Pichler O, Teuner A, Hosticka BJ (1996) A comparison of texture feature extraction using adaptive Gabor filtering, pyramidal and tree structured transforms. Pattern Recognition 29(5):733–742

    Article  Google Scholar 

  • Randen T, Husøy JH (1999) Filtering for texture classification: a comparative study. IEEE Trans Pattern Anal Mach Intel 21(4):291–310

    Article  Google Scholar 

  • Rentschler I, Hubner M, Caelli T (1988) On the discrimination of compound Gabor signals and textures. Vision Res 28:279–291

    Article  CAS  PubMed  Google Scholar 

  • Ritter H (1990) A spatial approach to feature linking. In: Proc Int Neural Network Conf, Paris, vol 2, pp 898–901

  • Robert A (1997) From contour completion to image schemas: a modern perspective on Gestalt psychology. Tech Rep. Department of Cognitive Science, University of California, San Diego

    Google Scholar 

  • Roelfsema PR, Lamme VAF, Spekreisje H, Bosch H (2002) Figure-ground segregation in a recurrent network architecture. J Cognitive Neurosci 14:525–537

    Article  Google Scholar 

  • Rosenblatt F (1962) Principles of neurodynamics: perceptions and the theory of brain mechanics. Spartan Books, Washington, DC

    Google Scholar 

  • Sakai K, Tanaka S (2000) Spatial pooling in the second order spatial structure of cortical complex cells. Vision Res 40:855–871

    Article  CAS  PubMed  Google Scholar 

  • Schillen TB, Knig P (1994) Binding by temporal structure in multiple feature domains of an oscillatory network. Biol Cybernetics 70:397–405

    Article  CAS  Google Scholar 

  • Singer W (1999) Neuronal synchrony: a versatile code for the definition of relations? Neuron 24:49–65

    CAS  PubMed  Google Scholar 

  • Super H, van der Togt C, Spekreijse H, Lamme VAF (2003) Internal state of monkey primary visual cortex(V1) predicts figure-ground perception. J Neurosci 23(8):3407–3414

    CAS  PubMed  Google Scholar 

  • Sutter A, Sperling G, Chubb C (1995) Measuring the spatial frequency selectivity of second order texture mechanisms. Vision Res 35(7):915–924

    Article  CAS  PubMed  Google Scholar 

  • Terman D, Wang DL (1995) Global competition and local cooperation in a network of neural oscillators. Physica D 81:148–176

    Article  Google Scholar 

  • Treisman A, Schmidt H (1982) Illusory conjunctions in the perception of objects. Cognitive Psychol 14:107–141

    CAS  Google Scholar 

  • Turner MR (1986) Texture discrimination by Gabor functions. Biol Cybernetics 55:71–82

    CAS  Google Scholar 

  • Usrey WM, Reid RC (1999) Synchronous activity in the visual system. Annu Rev Neurosci 61:194–214

    Google Scholar 

  • De Valois RL, De Valois KK (1988) Spatial vision. Oxford University Press, New York

  • De Valois RL, Yund EW, Hepler N (1982a) The orientation and direction selectivity of cells in macaque visual cortex. Vision Res 22:531–544

    PubMed  Google Scholar 

  • De Valois RL, Albrecht DG, Thorell LG (1982b) Spatial frequency selectivity of cells in macaque visual cortex. Vision Res 22:545–559

    PubMed  Google Scholar 

  • Vernon D (1991) Machine vision. Prentice Hall, New York

  • Watson AB (1987) Efficiency of a model human image code. J Optic Soc Am A 4(12):2401–2417

    CAS  Google Scholar 

  • Wersing H (2000) Spatial feature binding and learning in competitive neural layer architectures. Cuvillier, Göttingen

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

    Article  CAS  PubMed  Google Scholar 

  • Wolfe JM, Cave KR (1999) The psychophysical evidence for a binding problem in human vision. Neuron 24:11–17

    CAS  PubMed  Google Scholar 

  • Wolfson SS, Landy MS (1998) Examining edge- and region-based texture analysis mechanisms. Vision Res 38(3):439–446

    Article  CAS  PubMed  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Neuroinformatics Group, Faculty of Technology, Bielefeld University, 33501 , Bielefeld, Germany

    Jörg Ontrup & Helge Ritter

  2. HONDA Research Institute, Europe GmbH, Carl-Legien-Str. 30, 63073 , Offenbach/Main, Germany

    Heiko Wersing

Authors
  1. Jörg Ontrup
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Heiko Wersing
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Helge Ritter
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jörg Ontrup.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Ontrup, J., Wersing, H. & Ritter, H. A computational feature binding model of human texture perception. Cogn Process 5, 31–44 (2004). https://doi.org/10.1007/s10339-003-0003-x

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10339-003-0003-x

Keywords

Search

Navigation