Abstract
A single-value total color difference (TCD) measurement for scene segmentation is proposed and evaluated experimentally. Both chrominance and luminance difference criteria are considered. The luminance component is defined by a unit in luminance change expressed in terms of MacAdam's Just Noticeable Difference, JND. The chromaticity component is derived directly from JND. Experiments using both pixel and region analysis show that the proposed TCD can effectively indicate object boundaries over a wide range of luminance changes. The results have been evaluated both subjectively and quantitatively. For comparison purposes, results have been obtained in several color spaces.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
BeckJ.: Surface Color Perception, Connell University Press, Ithaca, NY, 1965.
BerryD. T.: Color recognition using spectral signatures, Pattern Recognition Letters 6 (1987), 69–75.
BumbacaF. and SmithK. C.: Design and implementation of a color vision model for computer vision applications, Computer Vision, Graphics and Image Processing 39 (1987), 226–245.
CookR. L. and TorranceK. E.: A reflectance model for computer graphics, ACM Trans. Graph 1 (1982), 7–24.
Forsyth, D. A.: Color Constancy and its Applications in Machine Vision, PhD Thesis, University of Oxford, Oxford, 1988.
Forsyth, D. A.: A novel approach to color constancy, in Proc. 2nd IEEE Int. Conf. on Computer Vision, December 1988, pp. 9–18.
Funt, B. and Jain, H.: Color from black and white, in Proc. 2nd IEEE Int. Conf. on Computer Vision, December 1988, pp. 2–8.
HornB. K. P.: Understanding image intensities, Artifical Intelligence 8 (1977), 201–231.
HurvichL. M.: Color Vision, Sinauer Associates Inc., Cambridge, MA, 1981.
JainA. K.: Color distance and geodesics in color 3 space, J. Opt. Soc. Am. 62(11) (1972), 1287–1290.
Kelley, R. B.: A first look in to color vision, SPIE Vol. 579 Intelligent Robots and Computer Vision (1985), pp. 96–103.
Klinker, G., Shafer, S., and Kanade, T.: Using a color reflection model to separate highlights from object color, in Proc. 1st Int. Conf. on Computer Vision, London, June 1987, pp. 145–150.
KlinkerG., ShaferS., and KanadeT.: A physical approach to color image understanding, International Journal of Computer Vision 4(1) (1990), 5–38.
LandE.: The retinex theory of color vision, Scientific American 237 (1977), 108–128.
MacAdamD. L.: Visual sensitivities to color differences in daylight, J. Opt. Soc. Am. 32 (1942), 247–274.
MacAdamD. L.: Specification of small chromaticity differences, J. Opt. Soc. Am. 33 (1943), 18–26.
MacAdamD. L.: Sources of Color Science, MIT Press, Cambridge, MA, 1970.
MacAdamD. L.: Color Measurement, Theme and Variations, Springer-Verlag, New York, 1981.
MaloneyL. and WandellB.: Color constancy: A method for recovering surface spectral reflectance, J. Opt. Soc. Am. A-3 (1986), 1673–1683.
MarrD. and HildrethE. C.: Thoery of edge detection, Proc. Roy. Soc. London B-207 (1980), 187–217.
NevatiaR.: A color edge detector and its use in scene segmentation, IEEE Trans. on Systems, Man and Cybernetics SMC-7(11) (1977), 820–826.
Nevatia, R.: A color edge detector, in Proc. 3rd Int. Joint Conf. on Pattern Recognition 1979, pp. 829–832.
Ohlander, R.: Analysis of Natural Scenes, PhD Thesis, Carnegie Mellon University, Department of Computer Science, 1975.
OhlanderR., PriceK., and ReddyD. R.: Picture segementation using recursive region spliting method, Computer Graphics and Image Processing 8 (1978), 313–333.
OhtaY.: Knowledge-based Interpretation of Outdoor Natural Color Scenes, Research Notes in Artificial Intelligence 4, Pitman, UK, 1985.
OhtaY., KanadeT., and SakaiT.: Color information for region segmentation, Computer Graphics and Image Processing 13 (1980), 222–241.
Pentland, A. P.: The Visual Inference of Shape: Computation from Local Features, PhD Thesis, MIT, Department of Psychology, 1982.
PrattW. K.: Digital Image Processing, Wiley, New York, 1991.
RobinsonG. S.: Color edge detection, Optical Engineering 16(5) (1977), 479–484.
RubinJ. and RichardsW.: Color vision and image intensities: When are changes material? Biological Cybernetics 45 (1982), 215–226.
Rubin, J. and Richards, W.: Color vision: Representing material catalogues, Memo 764, MIT Artificial Intelligence Laboratory, 1984.
Shafer, S. A.: Using color to separate reflection components, Technical Report 136, University of Rochester, Computer Science Department, 1984.
WilliamsD. H. and AggarwalJ. K.: Computer detection and classification of three citrus infestations, Computer Graphics and Image Processing 14 (1980), 373–390.
Wintringham, W. T.: Color television and colorimetry, Proc. IRE 39(10), October 1951.
WyszeckiG. W. and StilesW. S.: Color Sciences, 2nd edn, Wiley, New York, 1982.
Zheng, J.: Smoothing and Segmentation of Color Images in Computer Vision, PhD Thesis, Northeastern University, Department of ECE, July 1991.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Valavanis, K.P., Zheng, J. & Paschos, G. A total color difference measure for segmentation in color images. J Intell Robot Syst 16, 269–313 (1996). https://doi.org/10.1007/BF00245424
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF00245424