Skip to main content
Log in

Hypotheses for Image Features, Icons and Textons

  • Published:
International Journal of Computer Vision Aims and scope Submit manuscript

Abstract

We review ideas about the relationship between qualitative description of local image structure and quantitative description based on responses to a family of linear filters. We propose a sequence of three linking hypotheses. The first, the Feature Hypothesis, is that qualitative descriptions arise from a category system on filter-response space. The second, the Icon Hypothesis, is that the partitioning into categories of filter response space is determined by a system of iconic images, one associated with each point of the space. The third, the Texton Hypothesis, is that the correct images to play the role of icons are those that are the most likely explanations of a vector of filter responses. We present results in support of these three hypotheses, including new results on 2-D 1st order structure.

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

Similar content being viewed by others

References

  • Barlow, H. B. 1953. Summation and inhibition in the frog’s retina. Journal of Physiology (London), 119:69–88.

    Google Scholar 

  • Barlow, H. B. 1972. Single units and sensation: a neuron doctrine for perceptual psychology? Perception, 1: 371–394.

    Google Scholar 

  • Berlin, B. and Kay, P. 1969. Basic Color Terms: their Universality and Evolution, Berkeley: University of California Press.

    Google Scholar 

  • Bimler, D. 2004. Personal Communication.

  • Buchsbaum, G. and Bloch, O. 2002. Color categories revealed by non-negative matrix factorization of Munsell color spectra. Vision Research, 42:559–563.

    Article  Google Scholar 

  • Cen, F., et al. 2004. Robust registration of 3-D ultrasound images based on gabor filter and mean-shift method. In Computer Vision and Mathematical Methods in Medical and Biomedical Image Analysis. p. 304–316.

  • Davidoff, J., Davies, I., and Roberson, D. 1999. Colour categories in a stone-age tribe. Nature, 398(6724):203–204.

    Article  Google Scholar 

  • Debnath, L. 1964. On Hermite Transforms. Mathematicki Vesnik, 1(16):285–292.

    MATH  MathSciNet  Google Scholar 

  • Debnath, L. 1995. Integral Transforms and their Applications, CRC Press.

  • DeValois, R. L., Abramov, I., and Jacobs, G. H. 1966. Analysis of response patterns of LGN cells. Journal of the Optical Society of America, 56:966–977.

    Google Scholar 

  • Dowman, M. 2002. Modelling the acquisition of colour words. In Al 2002: Advances in Artificial Intelligence, p. 259–271.

  • Ellison, T. M. 2001. Induction and inherent similarity. In U. Hahn and M. Ramscar (Eds.) Similarity and Categorization, OUP: Oxford, p. 29–49.

    Google Scholar 

  • Florack, L. M. J., et al. 1992. Families of Tuned Scale-Space Kernels. In Computer Vision - ECCV ’92, p. 19–23.

  • Gärdenfors, P. 2000. Conceptual Spaces: the geometry of thought, Cambridge MA: MIT Press.

    Google Scholar 

  • Georgeson, M. A. and Freeman, T. C. A. 1997. Perceived location of bars and edges in one-dimensional images: Computational models and human vision. Vision Research, 37(1):127–142.

    Article  Google Scholar 

  • Geusebroek, J. M., et al. 2003. Color constancy from physical principles. Pattern Recognition Letters, 24(11):1653–1662.

    Article  Google Scholar 

  • Gibson, J. J. 1979. The Ecological Approach to Visual Perception, Houghton Mifflin.

  • Griffin, L. D. 1995. Descriptions of Image Structure, London: PhD thesis, University of London.

  • Griffin, L. D. 1997. Critical Points in Affine Scale Space. In Gaussian Scale-Space Theory, S. Sporring, et al. (Ed.) p. 165–180.

  • Griffin, L. D. 2001. Similarity of Pyschological and Physical Colour Space shown by Symmetry Analysis. Color Research and Application, 26(2):151–157.

    Article  MathSciNet  Google Scholar 

  • Griffin, L. D. 2002. Local image structure, metamerism, norms, and natural image statistics. Perception, 31(3):377–377.

    Google Scholar 

  • Griffin, L. D. 2005. Feature classes for 1-D, 2nd order image structure arise from the maximum likelihood statistics of natural images. Network-Computation in Neural Systems, in press.

  • Griffin, L. D. and Colchester, A. C. F. 1995. Superficial and Deep-Structure in Linear Diffusion Scale-Space - Isophotes, Critical-Points and Separatrices. Image and Vision Computing, 13(7):543–557.

    Article  Google Scholar 

  • Griffin, L. D. and Lillholm, M. 2003. Mode Estimation by Pessimistic Scale Space Tracking. In Scale Space ’03, Isle of Skye, UK: Springer.

    Google Scholar 

  • Griffin, L. D. and Lillholm, M. 2005. Image features and the 1-D, 2nd order gaussian derivative jet. In Proc. Scale Space 2005. Springer. p. 26–37.

  • Griffin, L. D. and Lillholm, M. 2005. The multiscale mean shift algorithm for mode estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence, submitted.

  • Griffin, L. D., Lillholm, M. and Nielsen, M. 2004. Natural image profiles are most likely to be step edges. Vision Research, 44(4): 407–421.

    Article  Google Scholar 

  • Heiler, M. and Schnorr, C. 2005. Natural image statistics for natural image segmentation. International Journal of Computer Vision, 63(1):5–19.

    Article  Google Scholar 

  • Hering, E. 1920. Outlines of a theory of the light sense, Harvard: Harvard University Press.

    Google Scholar 

  • Hubel, D. H. and Wiesel, T. N. 1968. Receptive fields and functional architecture of monkey striate cortex. Journal of Physiology, 195:215–243.

    Google Scholar 

  • Hurvich, L. M. and Jameson, D. 1957. An opponent-process theory of color vision. Psychological Review, 64:384–404.

    Article  Google Scholar 

  • Jameson, K. A. 2005. Culture and Cognition: what is universal about color experience? Cognition and Culture, in press.

  • Kay, P. 2005. Color categories are not arbitrary. Cross-Cultural Research, 39(1):39–55.

    Article  MathSciNet  Google Scholar 

  • Kay, P. and Maffi, L. 1999. Color appearance and the emergence and evolution of basic color lexicons. American Anthropologist, 101:743–760.

    Article  Google Scholar 

  • Kay, P. and McDaniel, C. K. 1978. The linguistic significance of the meanings of the basic color terms. Language, 54: 610–646.

    Article  Google Scholar 

  • Kay, P. and Regier, T. 2003. Resolving the question of color naming universals. Proceedings of the National Academy of Sciences of the United States of America, 100(15):9085–9089.

    Article  Google Scholar 

  • Kimmel, R. and Bruckstein, A. M. 2003. Regularized Laplacian Zero Crossings as Optimal Edge Integrators. International Journal of Computer Vision, 53(3):225–243.

    Article  Google Scholar 

  • Koenderink, J. J. 1984. The Structure of Images. Biological Cybernetics, 50(5):363–370.

    Article  MATH  MathSciNet  Google Scholar 

  • Koenderink, J. J. 1988. Operational Significance of Receptive-Field Assemblies. Biological Cybernetics, 1 58(3):163–171.

    Article  MathSciNet  Google Scholar 

  • Koenderink, J. J. 1993. What is a feature? Journal of Intelligent Systems, 3(1): 49–82.

    MathSciNet  Google Scholar 

  • Koenderink, J. J. 2001. Multiple visual worlds (editorial). Perception, 30:1–7.

    Article  Google Scholar 

  • Koenderink, J. J. and van Doorn, A. J. 1987. Representation of Local Geometry in the Visual-System. Biological Cybernetics, 55(6): 367–375.

    Article  MATH  MathSciNet  Google Scholar 

  • Koenderink, J. J. and van Doorn, A. J. 1990. Receptive-Field Families. Biological Cybernetics, 63(4):291–297.

    Article  MATH  MathSciNet  Google Scholar 

  • Koenderink, J. J. and van Doorn, A. J. 1992. Generic Neighborhood Operators. Ieee Transactions on Pattern Analysis and Machine Intelligence, 14(6):597–605.

    Article  Google Scholar 

  • Koenderink, J. J. and van Doorn, A. J. 1992. Receptive Field Assembly Specificity. Journal of Visual Communication and Image Representation, 3(1):1–12.

    Article  MathSciNet  Google Scholar 

  • Koenderink, J. J. and van Doorn, A. J. 1996. Metamerism in complete sets of image operators. In K. W. Bowyer and N. Ahuja (Eds.). Advances in Image Understanding: A Festschrift for Azriel Rosenfeld, Wiley-IEEE Computer Society Press, p. 113–129.

  • Koenderink, J. J. and van Doorn, A. J. 1997. Local Image Operators and Iconic Structure, In G. Sommer and J. J. Koenderink (Eds.). Algebraic Frames for the Perception-Action Cycle, Springer, p. 66–93.

  • Koenderink, J. J. and Van Doorn, A. J. 1998. The structure of relief, In Advances in Imaging and Electron Physics, 103:65–150.

    Article  Google Scholar 

  • Koenderink, J. J. and van Doorn, A. J. 2003. Perspectives on color space. In R. Mausfield and D. Heyer (Eds.). Colour Perception: Mind and the Physical World, OUP: Oxford, p. 1–56.

    Google Scholar 

  • Lawson, S. and Zhu, J. 2000. Image compression using wavelets and JPEG2000: a tutorial. Electronics & Communication Engineering Journal, 14(3):112–121.

    Article  Google Scholar 

  • Lee, A. B., Pedersen, K. S., and Mumford, D. 2003. The nonlinear statistics of high-contrast patches in natural images. International Journal of Computer Vision, 54(1–2):83–103.

    Article  MATH  Google Scholar 

  • Leung, T. and Malik, J. 2001. Representing and recognizing the visual appearance of materials using three-dimensional textons. International Journal of Computer Vision, 43(1):29–44.

    Article  MATH  Google Scholar 

  • Lillholm, M., Nielsen, M., and Griffin, L. D. 2003. Feature-based image analysis. International Journal of Computer Vision, 52(2–3):73–95.

    Article  Google Scholar 

  • Liu, X. W. and Wang, D. L. 2002. A spectral histogram model for texton modeling and texture discrimination. Vision Research, 42(23):2617–2634.

    Article  Google Scholar 

  • Logothetis, N. K., Pauls J., and Poggio, T. 1995. Shape Representation in the Inferior Temporal Cortex of Monkeys. Current Biology, 5(5):552–563.

    Article  Google Scholar 

  • Majthay, A. 1985. Foundations of Catastrophe Theory, London: Pitman Publishing Ltd.

    MATH  Google Scholar 

  • Makram-Ebeid, S. and Mory, B. 2003. Scale-space image analysis based on hermite polynomials theory. In L. D. Griffin and M. Lillholm (Eds.). Proc. Conf. on Scale Space Methods in Computer Vision, Springer, p. 57–71.

  • Manmatha, R., Ravela, S., and Chitti, Y. 1998. On computing local and global similarity in images. In Human Vision and Electronic Imaging III, p. 540–551.

  • Marr, D. and Hildreth, E. 1980. Theory of edge detection. Proceedings of the Royal Society Series B, 20: 187–217.

    Article  Google Scholar 

  • Marr, D., 1982, Vision. New York: W H Freeman & co.

    Google Scholar 

  • Martens, J. B. 1997. Local orientation analysis in images by means of the Hermite transform. IEEE Transactions on Image Processing, 6(8):1103–1116.

    Article  Google Scholar 

  • Martin, D. R., Fowlkes, C. C., and Malik, J. 2004. Learning to detect natural image boundaries using local brightness, color, and texture cues. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(5):530–549.

    Article  Google Scholar 

  • Nakamura, K., et al. 1994. Visual Response Properties of Single Neurons in the Temporal Pole of Behaving Monkeys. Journal of Neurophysiology, 71(3):1206–1221.

    Google Scholar 

  • Newton, I. 1706. Enumeratio linearum tertii ordinis.

  • Pedersen, K. S. 2003. Statistics of Natural Image Geometry. In Department of Computer Science, Copenhagen: University of Copenhagen.

    Google Scholar 

  • Richards, W. 1979. Quantifying Sensory Channels - Generalizing Colorimetry to Orientation and Texture, Touch, and Tones. Sensory Processes, 3(3):207–229.

    Google Scholar 

  • Rissanen, J. 1978. Modeling by shortest data description. Automatica, 14:465–471.

    Article  MATH  Google Scholar 

  • Rivero-Moreno, C. J. and Bres, S. 2003. Conditions of similarity between hermite and gabor filters as models of the human visual system. In N. Petkov and M. A. Westenberg (Eds.). Computer Analysis of Images and Patterns, Springer-Verlag, Berlin, p. 762–769.

    Google Scholar 

  • Roberson, D. 2005. Color categories are culturally diverse in cognition as well as in language. Cross-Cultural Research, 39(1):56–71.

    Article  Google Scholar 

  • Scale Space ’01. 2001. In Scale Space ’01. Vancouver, Canada: Springer.

  • Scale Space ’03. 2003. In Scale Space ’03. Isle of Skye, UK: Springer.

  • Scale Space ’05. 2005. In Scale Space ’05. Hofgeismar, Germany: Springer.

  • Scale Space ’99. 1999. In Scale Space ’99, Corfu, Greece: Springer.

  • Sigala, N. and Logothetis, N. K. 2002. Visual categorization shapes feature selectivity in the primate temporal cortex. Nature, 415(6869):318–320.

    Article  Google Scholar 

  • Steels, L. and Belpaeme, T. 2005. Coordinating perceptually grounded categories through language. A case study for colour. Behavioral and Brain Sciences, In Press.

  • Tagliati, E. and Griffin, L. D. 2001. Features in Scale Space: Progress on the 2D 2nd Order Jet. In M. Kerckhove (Ed.). LNCS, Springer, p. 51–62.

  • ter Haar Romeny, B. M. 2003. Front-end Vision and Multi-Scale Image Analysis. Kluwer.

  • ter Haar Romeny, B. M. and Florack, L. M. J. 1994. Higher-order differential structure of images. Image and Vision Computing, 12(6): 317–325.

    Article  Google Scholar 

  • Thom, R. 1972. Structural stability and morphogenesis. Reading MA: W. A. Benjamin, Inc.

    Google Scholar 

  • van den Boomgaard, R. 2003. Least squares and robust estimation of local image structure. In L. D. Griffin and M. Lillholm (Eds.). Proc. Scale Space Methods in Computer Vision, p. 237–254.

  • van Hateren, J. H. and van der Schaaf, A. 1998. Independent component filters of natural images compared with simple cells in primary visual cortex. Proceedings of the Royal Society of London Series B-Biological Sciences, 265(1394): 359–366.

    Article  Google Scholar 

  • van Trigt, C. 1990a. Smoothest Reflectance Functions .1. Definition and Main Results. Journal of the Optical Society of America a-Optics Image Science and Vision, 7(10):1891–1904.

    Google Scholar 

  • van Trigt, C. 1990b. Smoothest Reflectance Functions .2. Complete Results. Journal of the Optical Society of America a-Optics Image Science and Vision, 7(12):2208–2222.

    Article  Google Scholar 

  • Varma, M. and Zisserman, A. 2002. Classifying images of materials: achieving viewpoint and illumination independence. In ECCV ’02, Copenhagen, Springer.

    Google Scholar 

  • Varma, M. and Zisserman, A. 2005. A statistical approach to texture classification from single images. International Journal of Computer Vision, 62(1-2):61–81.

    Article  Google Scholar 

  • Vogels, R., et al., 2001. Inferior temporal neurons show greater sensitivity to nonaccidental than to metric shape differences. Journal of Cognitive Neuroscience, 13(4):444–453.

    Article  Google Scholar 

  • Wilson, M. and Debauche, B. A. 1981. Inferotemporal Cortex and Categorical Perception of Visual- Stimuli by Monkeys. Neuropsychologia, 19(1): 29–41.

    Article  Google Scholar 

  • Wu, S. W. and Gersho, A. 1993. Lapped Vector Quantization of Images. Optical Engineering, 32(7):1489–1495.

    Article  Google Scholar 

  • Yendrikhovskij, S. N. 2001. Computing color categories from statistics of natural images. Journal of Imaging Science and Technology, 45(5):409–417.

    Google Scholar 

  • Young, R. A. 1987. The Gaussian derivative model for spatial vision: I. Retinal mechanisms. Spatial Vision, 2:273–293.

    Google Scholar 

  • Young, R. A. and Lesperance, R. M. 2001. The Gaussian Derivative model for spatial-temporal vision: II. Cortical data. Spatial Vision, 14(3–4):321–389.

    Article  Google Scholar 

  • Young, R. A., Lesperance, R.M., and Meyer, W. W. 2001. The Gaussian Derivative model for spatial-temporal vision: I. Cortical model. Spatial Vision, 14(3–4):261–319.

    Article  Google Scholar 

  • Zhilkin, P. and Alexander, M. E. 2000. 3D image registration using a fast noniterative algorithm. Magnetic Resonance Imaging, 18(9):1143–1150.

    Article  Google Scholar 

  • Zhu, S.-C., et al. 2005. What are textons? International Journal of Computer Vision, 62(1):121–143.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Rights and permissions

Reprints and permissions

About this article

Cite this article

Griffin, L.D., Lillholm, M. Hypotheses for Image Features, Icons and Textons. Int J Comput Vision 70, 213–230 (2006). https://doi.org/10.1007/s11263-006-6355-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11263-006-6355-9

Keywords

Navigation