Image retrieval by multi-scale illumination invariant Indexing
The purpose is to arrive at image retrieval invariant to a substantial change in illumination.
We will extend the theory that we have recently proposed on illumination invariant color models . Then, a multi-scale image representation is produced by applying Gaussian derivatives at different scale levels on the illumination invariant color models. In this way, a multi-dimensional multi-scale image index is obtained which is illumination-independent and invariant under the group of rotations in the image domain. The multi-scale image representation is taken as input for image retrieval by query by example (i.e. an example image is given by the user) and image retrieval by arranging the image database as a binary tree (i.e. no example image is given is available).
Experiments have been conducted on a database consisting of 500 images taken from multicolored man-made objects in real world scenes. From the experimental results it can be observed that image retrieval by multi-scale invariant indexing provides high retrieval accuracy even under spatially and spectrally varying illumination.
Key-wordsimage retrieval dichromatic reflection reflectance properties photometric color invariants Gaussian derivatives scale-space multi-scale invariant indexing query by example decision trees
Unable to display preview. Download preview PDF.
- 1.Finlayson, G. D., Drew M. S., and Funt B. V.: Spectral Sharpening: Sensor Transformations for improved Color Constancy. J. Opt. Soc. Am. 11(5) (1994) 1553–1563Google Scholar
- 2.Finlayson, G. D., Chatterjee S. S., and Funt B. V.: Color Angular Indexing. ECCV96 II (1996) 16–27Google Scholar
- 3.Forsyth, D.: A Novel Algorithm for Color Constancy. International Journal of Computer Vision Vol. 5 1990 5–36Google Scholar
- 4.Funt, B. V. and Drew, M. S.: Color Constancy Computation in Near-Mondrian Scenes. In Proceedings of the CVPR IEEE Computer Society Press 1988 544–549Google Scholar
- 5.Funt, B. V. and Finlayson, G. D.: Color Constant Color Indexing. IEEE PAMI 17(5) 1995 522–529Google Scholar
- 6.Gevers, T. and Smeulders, A. W. M.: Image Indexing using Composite Color and Shape Invariant Features. ICCV Bombay India (1998)Google Scholar
- 7.Hartigan, J. A.: Clustering Algorithms. John Wiley and Sons U.S.A (1975)Google Scholar
- 8.Healey, G. and Slater D.: Global Color Constancy: Recognition of Objects by Use of Illumination Invariant Properties of Color Distributions. J. Opt. Soc. Am. A Vol. 11 No. 11 (1995) 3003–3010Google Scholar
- 9.Koenderink, J. J. and van Doorn A. J.: Representation of Local Geometry in the Visual System. Biological Cybernetics No. 55 (1987) 367–375Google Scholar
- 10.Land, E. H. and McCann, J. J.: Lightness and Retinex Theory. J. Opt. Soc. Am. Vol. 61 (1971) 1–11Google Scholar
- 11.Lee H.-C., Breneman E. J. and Schulte C. P.: Modeling Light Reflection for Computer Color Vision. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 12 No. 3 (1990) 402–409Google Scholar
- 12.Levkowitz, H. and Herman G. T.: GLHS: A Generalized Lightness, Hue, and Saturation Color Model. CVGIP: Graphical Models and Image Processing Vol. 55 No. 4 (1993) 271–285Google Scholar
- 13.Nayar, S. K. and Bolle, R. M.: Reflectance Based Object Recognition. International Journal of Computer Vision Vol. 17 No. 3 1996 219–240Google Scholar
- 14.Shafer, S. A.: Using Color to Separate Reflection Components. COLOR Res. Appl. 10(4) (1985) 210–218Google Scholar
- 15.D. Slater and G. Healey: The Illumination-invariant Recognition of 3D Objects Using Local Color Invariants. IEEE Trans. PAMI 18(2) (1996)Google Scholar
- 16.Swain, M. J. and Ballard, D. H.: Color Indexing. International Journal of Computer Vision Vol. 7 No. 1 1991 11–32Google Scholar