Abstract
Standard techniques for segmenting color images are based on finding normalized RGB discontinuities, color histogramming, or clustering techniques in RGB or CIE color spaces. The use of the psychophysical variable hue in HSI space has not been popular due to its numerical instability at low saturations. In this article, we propose the use of a simplified hue description suitable for implementation in analog VLSI. We demonstrate that if theintegrated white condition holds, hue is invariant to certain types of highlights, shading, and shadows. This is due to theadditive/shift invariance property, a property that other color variables lack. The more restrictive uniformly varying lighting model associated with themultiplicative/scale invariance property shared by both hue and normalized RGB allows invariance to transparencies, and to simple models of shading and shadows. Using binary hue discontinuities in conjunction with first-order type of surface interpolation, we demonstrate these invariant properties and compare them against the performance of RGB, normalized RGB, and CIE color spaces. We argue that working in HSI space offers an effective method for segmenting scenes in the presence of confounding cues due to shading, transparency, highlights, and shadows. Based on this work, we designed and fabricated for the first time an analog CMOS VLSI circuit with on-board phototransistor input that computes normalized color and hue.
Similar content being viewed by others
References
Abdou, I.E., and Pratt, W.K. 1979. Quantitative design and evaluation of enhancement/thresholding edge detectors,Proc. IEEE 67(5): 753–763.
Bajcsy, R., Lee, S.W., and Leonardis, A. 1990. Color image segmentation with detection of highlights and local illumination induced by inter-reflections.Proc. 10th Intern. Conf. Patt. Recog. B, Atlantic City, pp. 785–790.
Barth, M., Parthasarathy, S., Wang, J., Hu, E., Hackwood, S., and Beni, G. 1986. A color vision system for microelectronics: Application to oxide thickness measurement,Proc. Inter. Conf. Robot. Autom., San Francisco, pp. 1242–1247.
Berlin, B., and Kay, P. 1969.Basic Color Terms: Their Universality and Evolution, University of California.
Canny, J. 1986. A computational approach to edge detection.IEEE Tran. Patt. Anal. Mach. Intell. 8(6): 679–698.
Celenk, M. 1990. A color clustering technique for image segmentation,Comput. Vis., Graph. Image Process. 52: 145–170.
Cook, R.L., and Torrance, K.E. 1981. A reflectance model for computer graphics,Computer Graphics 15(3): 307–316.
Daily, M.J. 1989. Color image segmentation using Markov random fields,Proc. Conf. Comput. Vis. Patt. Recog., San Diego, pp. 304–312.
Delbruck, T. 1993. Investigations of analog VLSI visual transduction and motion processing, Ph.D. Thesis, California Institute of Technology.
Desimone, R., Schein, S.J., Moran, J., and Ungerleider, L.G. 1985. Contour, color and shape analysis beyond the striate cortex,Vision Research 25: 441.
De Valois, R.L., and De Valois, K.K. 1975. Neural coding of color,Handbook of Perception, vol. VSeeing, Academic Press: San Diego, pp. 117–166.
Dillon, P., Brault, A., Horak, J., Garcia, E., Martin, T., and Light, W. 1985. Fabrication and performance of color filter arrays for solid-state imagers,IEEE Trans. Electron Devices 25(2): 97–101.
Foley, J.D., VanDam, A., Feiner, S.K., and Hughes, J.F. 1990.Computer Graphics: Principles and Practice, Addison-Wesley: Reading, MA.
Geiger, D., and Girosi, F. 1990. Parallel and deterministic algorithms from MRFs: Surface reconstruction,IEEE Trans. Patt. Anal. Mach. Intell. 13(5): 401–412.
Geman, S., and Geman, D. 1984. Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images,IEEE Trans. Patt. Anal. Mach. Intell. 5: 721–741.
Genz, S.E. 1990. Real time chip set simplifies color image processing,Image Processing Handbook (8): 56–59, Data Translation™, Marlboro, MA.
Gilbert, B. 1975. Translinear circuits: A proposed classification,Electronics Letters 11(1): 14–16.
Gershon, R. 1985. Aspects of perception and computation in color vision,Comput. Vis. Graph. Image Process. 32: 245–278.
Gershon, R., Jepson, A., and Tsotsos, J. 1986. Ambient illumination and the determination of material changes,J. Opt. Soc. Amer. A 3(10): 1700–1707.
Harris, J.G., Koch, C., and Luo, J. 1990a. A two-dimensional analog VLSI circuit for detecting discontinuities in early vision,Science 248: 1209–1211.
Harris, J.G., Koch, C., Staats, E., and Luo, J. 1990b. Analog hardware for detecting discontinuities in early vision,Intern. J. Comput. Vis. 4: 211–233.
Healey, G. 1989. Using color for geometry-insensitive segmentation,J. Opt. Soc. Amer. A 6(6): 920–937.
Healey, G., and Binford, T.O., 1987. The role and use of color in a general vision system.DARPA-Image Understanding Workshop, Los Angeles, pp. 599–613.
Hurlbert, A., and Poggio, T. 1989. A network for image segmentation using color, InAdvances in Neural Information Processing Systems I, pp. 297–304, Morgan Kaufmann: San Mateo.
Ingling, C.R., and Tsou, B.H. 1977. Orthogonal combination of the three visual channels,Vision Research 17: 1075–1082.
Joblove, G.H., and Green, D. 1978. Color spaces for computer graphics,Computer Graphics 12(3): 20–25.
Jain, A.K. 1989.Fundamentals of Digital Image Processing, Prentice-Hall: Englewood Cliffs, NJ.
Kender, J. 1976. Saturation, hue, and normalized color: Calculation, digitization, and use, Computer Science Technical Report, Carnegie-Mellon University.
Klinker, G.J., Shafer, S.A., and Kanade, T. 1988. The measurement of highlights in color images,Intern. J. Comput. Vis. 2: 7–32.
Klinker, G.J., Shafer, S.A., and Kanade, T. 1990. A physical approach to color image understanding,Intern. J. Comput. Vis. 4: 7–38.
Koch, C. 1989. Seeing chips: Analog VLSI circuits for computer vision,Neural Computation, 1: 184–200.
Koch, C., Moore, A., Bair, W., Horiuchi, T., Bishofberger, B., and Lazzaro, J. 1991. Computing motion using analog VLSI vision chips: An experimental comparison among four approaches,IEEE Workshop on Visual Motion, Princeton, October, pp. 312–324.
Lenny, P., and D'Zmura, M. 1988. Mechanisms of color vision,CRC Crit. Rev. Neurobiol. 3(4): 333–400.
Mead, C. 1989.Analog VLSI and Neural Systems, Addison-Wesley: Reading, MA.
Nevatia, R. 1977. A color edge detector and its use in scene segmentation,IEEE Trans. Syst. Man, Cyb. 7(11): 820–826.
Ohlander, R.B. 1976. Analysis of Natural Scenes, Ph.D. thesis, Carnegie Mellon University.
Ohta, Y., Kanade, T., and Sakai, T. 1980. Color information for region segmentation,Comput. Graph. Image Process. 13: 222–241.
Perez, F.A., and Koch, C. 1992. Toward color image segmentation in analog VLSI,Rockwell 4th Annu. Tech. Conf. Cont. Sig. Process. pp. 246–263.
Perez, F.A., and Koch, C. 1992. Segmenting color images using hue, CNS Memo 20, California Institute of Technology, 16 October.
Phong, B.T. 1975. Illumination for computer generated pictures,Commu. ACM 18(6): 311–317.
Poggio, T., Torre, V., and Koch, C. 1985. Computational vision and regularization theory,Nature 317(6035): 314–319.
Poggio, T., Gamble, E.B., and Little, J.J. 1988. Parallel integration of vision modules,Science 242: 436–440.
Rubin, J.M., and Richards, W.A. 1982. Color vision and image intensities: When are changes material?Biological Cybernetics 45: 215–226.
Rubin, J.M., and Richards, W.A. 1984. Color vision: Representing material categories, AI Memo No. 764, Massachusetts Institute of Technology.
Schwarz, M.W., Cowan, W.B., and Beatty, J.C. 1987. Experimental comparison of RGB, YIQ, LAB, and opponent color models,ACM Trans. Graphics 6(2): 123–158.
Seevink, E. 1988. Analysis and synthesis of translinear integrated circuits, Elsevier: New York.
Shafer, S.A. 1985. Using color to separate reflection components,COLOR Res. Appl. 10(4): 210–218.
Sivilotti, M.A., Mahowald, and Mead, C.A. 1987. Real-time visual computation using analog CMOS processing arrays, 1987 Stanford Conf. VLSI, MIT Press: Cambridge, pp. 295–312.
Smith, A.R. 1978. Color gamut transform pairs,Computer Graphics 12(3): 12–19.
Terzopoulos, D. 1985. Computing visible-surface representations, AI Memo No. 800, Massachusetts Institute of Technology.
Tominaga, S. 1987. Expansion of color images using three perceptual attributes,Patt. Recog. Lett. 6: 77–85.
Tominaga, S. 1990. A color classification method for color images using a uniform color space,10th Intern. Conf. Patt. Recog., Atlantic City, pp. 803–807.
Toumazou, C., Lidgey, F., and Haigh, D, eds. 1990.Analogue IC Design: The Current Mode Approach, Short Run Press, England.
Wolfe, W.L., and Zissis, G.J. 1985.The Infrared Handbook, Environmental Research Institute of Michigan: Ann Arbor.
Wright, W.A. 1989. A Markov random field approach to data fusion and colour segmentation,Image Vis. Comput. 7(2): 144–150.
Wyszecki, G., and Stiles, W.S. 1982.Color Science: Concepts and Methods, Quantitative Data and Formulae, Wiley: New York.
Zeki, S. 1983. Colour coding in the cerebral cortex: The reaction of cells in monkey visual cortex to wavelengths and colours,Neuroscience 9(4): 741–765.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Perez, F., Koch, C. Toward color image segmentation in analog VLSI: Algorithm and hardware. Int J Comput Vision 12, 17–42 (1994). https://doi.org/10.1007/BF01420983
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF01420983