This Article 
 Bibliographic References 
 Add to: 
Finite Prolate Spheroidal Sequences and their Applications II: Image Feature Description and Segmentation
March 1988 (vol. 10 no. 2)
pp. 193-203

The problem of uncertainty in image feature description is discussed, and it is shown how finite prolate spheroidal sequences can be used in the construction of feature descriptions that combine spatial and frequency-domain locality in an optimal way. Methods of constructing such optimal feature sets, which are suitable for graphical implementation, are described, and some generalizations of the quadtree concept are presented. These methods are illustrated by examples from image processing applications, including feature extraction and texture description. The problem of image segmentation is discussed, and the importance of scale invariance in overcoming the limitations imposed by uncertainty is demonstrated. A novel texture segmentation algorithm that is based on a combination of the new feature description and multiresolution techniques is described and shown to give accurate segmentations on a range of synthetic and natural textures.

[1] S. Levialdi, "Edge extraction techniques," inFundamentals in Computer Vision, O. Faugeras, Ed. London: Cambridge University Press, 1983.
[2] W. Frei and C. C. Chen, "Fast boundary detection: A generalization and a new algorithm,"IEEE Trans. Comput., vol. C-26, pp. 988- 998, 1977.
[3] D. Marr,Vision. San Francisco, CA: Freeman, 1982.
[4] H. B. Barlow, "Single units and sensation: A Neuron doctrine for perceptual psychology,"Perception, vol. 1, pp. 371-380, 1972.
[5] H. C. Andrews,Introduction to Mathematical Techniques in Pattern Recognition. New York: Wiley, 1972.
[6] C. H. Chen,Nonlinear Maximum Entropy Spectral Analysis for Signal Recognition. Chichester, England: Research Studies Press, 1982.
[7] L. O. Harvey and M. J. Gervais, "Visual texture perception and Fourier analysis,"Percept. and Psychophys., vol. 24, pp. 534-542, 1978.
[8] W. K. Pratt, and O. D. Faugeras, and A. Gagalowicz, "Visual discrimination of stochastic texture fields,"IEEE Trans. Syst., Man, Cybern., vol. SMC-8, pp. 796-804, 1978.
[9] N. Graham, "Spatial frequency channels in vision: Detecting edges without edge detectors," inVisual Coding and Adaptability, C. S. Harris, Ed. Hillsdale, NJ: Erlbaum, 1980.
[10] D. Gabor, "Theory of communication,"IEE Proc., vol. 93, no. 26, pp. 429-441, 1946.
[11] S. Marcelja, "Mathematical description of the responses of simple cortical cells,"J. Opt. Soc. Amer., vol. 70, pp. 1297-1300, 1980.
[12] D. A. Pollen and S. F. Ronner, "Spatial computation performed by simple and complex cells in the visual cortex of the cat,"Vision Res., vol. 22, pp. 101-118, 1982.
[13] D. A. Pollen and S. F. Ronner, "Visual cortical neurons as localized spatial frequency filters,"IEEE Trans. Syst., Man, Cybern., vol. SMC-13, pp. 907-916, 1983.
[14] R. Wilson and H. Knutsson, "Uncertainty and inference in the visual system," in submission.
[15] G. H. Granlund, "In search of a general picture processing operator,"Comput. Graphics Image Processing, vol. 8, pp. 155-173, 1978.
[16] L. Jacobson and H. Wechsler, "The Wigner distribution and its usefulness in 2-D image processing," inProc. 6th Int. Conf. Pattern Recognition, Munich, West Germany, 1982, pp. 542-544.
[17] H. Knutsson and G. H. Granlund, "Fourier domain design of line and edge detectors," inProc. IEEE Conf. Pattern Recognition, Miami, FL, 1980.
[18] K. Shanmugam, F. M. Dickey, and J. A. Green, "An optimal frequency domain filter for edge detection indigital pictures,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-1, pp. 37-69, 1979.
[19] M. Spann and R. Wilson, "A quadtree approach to image segmentation which combines statistical and spatial information,"Pattern Recognition, vol. 18, pp. 257-269, 1985.
[20] R. Wilson and G. H. Granlund, "The uncertainty principle in image processing,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI- 6, 1984.
[21] H. Knutsson, "Filtering and reconstruction in image processing," Ph.D. dissertation, Linkoeping Univ., 1982.
[22] G. H. Granlund and J. Arvidsson, "The GOP image computer," inFundamentals in Computer Vision, O. Faugeras, Ed. London: Cambridge University Press, 1983.
[23] R. Wilson, "Texture synthesis and analysis using minimum uncertainty filters," inProc. 1st Image Processing Symp., Biarritz, 1984.
[24] D. J. Thomson, "Spectrum estimation and harmonic analysis,"Proc. IEEE, vol. 70, pp. 1055-1096, 1982.
[25] P. Cavanagh, "Size and rotation invariance in the visual system,"Perception, vol. 7, pp. 167-177, 1978.
[26] R. Wilson, "From signals to symbols--The inferential structure of vision," inProc. IEEE COMPINT, Montreal, 1985.
[27] S. L. Tanimoto and T. Pavlidis, "A hierarchical data structure for image processing,"Comput. Graphics Image Processing, vol. 4, pp. 104-119, 1975.
[28] B. Julesz, "Perceptual limits of texture discrimination and their implications to figure-ground separation," inFormal Theories of Visual Perception, L. J. Leeuwenberg and H. F. Buffart, Eds. New York: Wiley, 1978.
[29] P. C. Chen and T. Pavlidis, "Image segmentation as an estimation problem," inImage Modeling, A. Rosenfeld, Ed. New York: Academic, 1981.
[30] P. J. Burt, T. H. Hong, and A. Rosenfeld, "Segmentation and estimation of region properties through cooperative hierarchical computation,"IEEE Trans. Syst., Man, Cybern., vol. SMC-11, pp. 802- 809, 1981.
[31] A. P. Witkin, "Scale-space filtering," inProc. IEEE ICASSP-84, San Diego, CA, 1984.
[32] R. Wilson, "A class of local centroid algorithms for classification and quantization in spaces of arbitrary dimension," inProc. IEEE CSSP, Bangalore, India, 1984.
[33] P. Brodatz,Texture: A Photograph Album for Artists and Designers. New York: Dover, 1956.
[34] M. Spann, "Texture segmentation and description in image processing, Ph.D. dissertation, Aston Univ., 1985.
[35] L. Van Gool, P. Dewaele, and A. Oosterlinck, "Texture analysis Anno. 1983,"Comput. Vision, Graphics, Image Processing, vol. 29, pp. 336-357, 1985.

Index Terms:
picture processing; pattern recognition; image feature description; finite prolate spheroidal sequences; frequency-domain locality; optimal feature sets; quadtree concept; image processing; feature extraction; texture description; image segmentation; scale invariance; multiresolution techniques; frequency-domain analysis; pattern recognition; picture processing; trees (mathematics)
R. Wilson, M. Span, "Finite Prolate Spheroidal Sequences and their Applications II: Image Feature Description and Segmentation," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 10, no. 2, pp. 193-203, March 1988, doi:10.1109/34.3882
Usage of this product signifies your acceptance of the Terms of Use.