This Article 
 Bibliographic References 
 Add to: 
Generic Neighborhood Operators
June 1992 (vol. 14 no. 6)
pp. 597-605

A method that treats linear neighborhood operators within a unified framework that enables linear combinations, concatenations, resolution changes, or rotations of operators to be treated in a canonical manner is presented. Various families of operators with special kinds of symmetries (such as translation, rotation, magnification) are explicitly constructed in 1-D, 2-D, and 3-D. A concept of 'order' is defined, and finite orthonormal bases of functions closely connected with the operators of various orders are constructed. Linear transformations between the various representations are considered. The method is based on two fundamental assumptions: a decrease of resolution should not introduce spurious detail, and the local operators should be self-similar under changes of resolution. These assumptions merely sum up the even more general need for homogeneity isotropy, scale invariance, and separability of independent dimensions of front-end processing in the absence of a priori information.

[1] J. Babaud, A. P. Witkin, M. Baudin, and R. O. Duda, "Uniqueness of the Gaussian kernel for scale-space filtering,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-8, pp. 26-33, Jan. 1986.
[2] P. Bijl and J. J. Koenderink, "Visibility of blobs with a gaussian luminance profile,"Vision Res., vol. 29, pp. 447-456, 1989.
[3] G. J. Burton, N. D. Haig, and I. R. Moorhead, "A self-similar stack model for human and machine vision,"Biol. Cybern., vol. 53, pp. 397-403, 1986.
[4] J. F. Canny, "Finding lines and edges in images," Artificial Intell. Lab., Massachusetts Inst. Technol., Tech. Rep. TM-720, 1983.
[5] J. M. Coggins and A. K. Jain, "A spatial filtering approach to texture analysis,"Patt. Recogn. Lett., vol. 3, pp. 195-203, 1985.
[6] J. M. Coggins, F. S. Fay, and K. E. Fogarty, "Development and application of a three-dimensional artificial visual system,"Comput. Methods Programs Biomed., vol. 22, pp. 69-77, 1986.
[7] I. S. Gradshteyn and I. M. Ryzhik,Tables of Integrals, Series, and Products. New York: Academic, 1965.
[8] R. A. Hummel, B. Kimia, and S. W. Zucker, "Deblurring gaussian blur,"Comput. Vision Graphics Image Processing, vol. 38, pp. 66-80, 1987.
[9] J. P. Jones and L. A. Palmer, "The two-dimensional spatial structure of simple receptive fields in cat striate cortex,"J. Neurophysiol., vol. 58, pp. 1187-1211, 1987.
[10] J. P. Jones and L. A. Palmer, An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex,"J. Neurophysiol., vol. 58, pp. 1233-1258, 1987.
[11] J. J. Koenderink and A. J. van Doorn, "Visual detection of spatial contrast; Influence of location in the visual field, target extent and illuminance level,"Biol. Cybern., vol. 30, pp. 157-167, 1978.
[12] J. J. Koenderink, "The structure of images,"Biol. Cybern., vol. 50, pp. 363-370, 1984.
[13] J. J. Koenderink and A. J. van Doorn, "Representation of local geometry in the visual system,"Biol. Cybern., vol. 55, pp. 367-375, 1987.
[14] J. J. Koenderink, "Operational significance of receptive field assemblies,"Biol. Cybern., vol. 58, pp. 163-171, 1988.
[15] J. J. Koenderink and W. Richards, "Two-dimensional curvature operators,"J. Opt. Soc. Amer., vol. A5, pp. 1136-1141, 1988.
[16] J. J. Koenderink, "A hitherto unnoticed singularity of scale-space,"IEEE Trans. Patt. Anal. Machine Intell., vol. 11, pp. 1222-1224, 1989.
[17] K.-C. Low and J. M. Coggins, "Multiscale vector fields for image pattern recognition," to be published.
[18] J. L. Powell and B. Crasemann,Quantum Mechanics. Reading MA: Addison-Wesley, 1961.
[19] A. Watson, "Efficiency of a model human image code,"J. Opt. Soc. Amer., vol. A4, pp. 2401-2417, 1987.
[20] R. A. Young, "The gaussian derivative theory of spatial vision: Analysis of cortical cell recptive field line-weighting profiles," General Motors Res. Tech. Rep., vol. GMR-4920, May 1985.
[21] A. L. Yuille and T. Poggio, "Fingerprints theorems for zero crossings,"J. Opt. Soc. Amer., vol. A5, pp. 683-692, 1985.
[22] S. W. Zucker and R. A. Hummel, "Receptive fields and the representation of visual information,"Human Neurobiol., vol. 5, pp. 121-128, 1986.

Index Terms:
picture processing; generic neighbourhood operators; linear neighborhood operators; concatenations; resolution changes; rotations of operators; magnification; 1-D; 2-D; 3-D; homogeneity; isotropy; scale invariance; separability; front-end processing; picture processing
J.J. Koenderink, A.J. van Doorn, "Generic Neighborhood Operators," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, no. 6, pp. 597-605, June 1992, doi:10.1109/34.141551
Usage of this product signifies your acceptance of the Terms of Use.