Generic Neighborhood Operators

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. L. Powell.  Quantum Mechanics , 1961 .

[2]  J. Canny.  Finding Edges and Lines in Images , 1983 .

[3]  T. Poggio,et al.  Fingerprints theorems for zero crossings , 1985 .

[4]  Anil K. Jain,et al.  A spatial filtering approach to texture analysis , 1985, Pattern Recognit. Lett..

[5]  S W Zucker,et al.  Receptive fields and the representation of visual information. , 1986, Human neurobiology.

[6]  J M Coggins,et al.  Development and application of a three-dimensional artificial visual system. , 1985, Computer methods and programs in biomedicine.

[7]  Andrew P. Witkin,et al.  Uniqueness of the Gaussian Kernel for Scale-Space Filtering , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  J. P. Jones,et al.  An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex. , 1987, Journal of neurophysiology.

[9]  J. P. Jones,et al.  The two-dimensional spectral structure of simple receptive fields in cat striate cortex. , 1987, Journal of neurophysiology.

[10]  A B Watson,et al.  Efficiency of a model human image code. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[11]  Benjamin B. Kimia,et al.  Deblurring Gaussian blur , 2015, Comput. Vis. Graph. Image Process..

[12]  Jan J. Koenderink,et al.  Two-dimensional curvature operators , 1988 .

[13]  J. Koenderink,et al.  Visibility of blobs with a gaussian luminance profile , 1989, Vision Research.

[14]  Jan J. Koenderink,et al.  A Hitherto Unnoticed Singularity of Scale-Space , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  James M. Coggins,et al.  Multiscale Vector Fields for Image Pattern Recognition , 1990, Other Conferences.

[16]  G. J. Burton,et al.  A self-similar stack model for human and machine vision , 1986, Biological Cybernetics.

[17]  J. Koenderink,et al.  Visual detection of spatial contrast; Influence of location in the visual field, target extent and illuminance level , 1978, Biological Cybernetics.