DMCA
Complete discrete 2-D Gabor transforms by neural networks for image analysis and compression (1988)
| Citations: | 475 - 8 self |
BibTeX
@MISC{Daugman88completediscrete,
author = {John G. Daugman},
title = {Complete discrete 2-D Gabor transforms by neural networks for image analysis and compression},
year = {1988}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
A three-layered neural network is described for transforming two-dimensional discrete signals into generalized nonorthogonal 2-D “Gabor” representations for image analysis, segmentation, and compression. These transforms are conjoint spatial/spectral representations [lo], [15], which provide a complete image description in terms of locally windowed 2-D spectral coordinates embedded within global 2-D spatial coordinates. Because intrinsic redundancies within images are extracted, the resulting image codes can be very compact. However, these conjoint transforms are inherently difficult to compute because t e elementary expansion functions are not orthogonal. One orthogonking approach developed for 1-D signals by Bastiaans [8], based on biorthonormal expansions, is restricted by constraints on the conjoint sampling rates and invariance of the windowing function, as well as by the fact that the auxiliary orthogonalizing functions are nonlocal infinite series. In the present “neural network” approach, based
Keyphrases
image analysis complete discrete 2-d gabor transforms neural network bastiaans si 2-d spectral coordinate biorthonormal expansion global 2-d spatial coordinate conjoint spatiahpectral representation abstract-a three-layered neural network image code two-dimensional discrete signal elementary expansion function intrinsic redundancy present neural network approach nonlocal infinite series windowing function 1-d signal complete image description generalized nonorthogonal 2-d gabor representation conjoint transforms auxiliary orthogonalizing function
