Complete discrete 2-D Gabor transforms by neural networks for image analysis and compression

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, which provide a complete image description in terms of locally windowed 2-D spectral coordinates embedded within global 2-D spatial coordinates. In the present neural network approach, based on interlaminar interactions involving two layers with fixed weights and one layer with adjustable weights, the network finds coefficients for complete conjoint 2-D Gabor transforms without restrictive conditions. In wavelet expansions based on a biologically inspired log-polar ensemble of dilations, rotations, and translations of a single underlying 2-D Gabor wavelet template, image compression is illustrated with ratios up to 20:1. Also demonstrated is image segmentation based on the clustering of coefficients in the complete 2-D Gabor transform. >

[1]  Dennis Gabor,et al.  Theory of communication , 1946 .

[2]  D. Hubel,et al.  Receptive fields, binocular interaction and functional architecture in the cat's visual cortex , 1962, The Journal of physiology.

[3]  D. A. Bell,et al.  Information Theory and Reliable Communication , 1969 .

[4]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[5]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[6]  D. Hubel,et al.  Sequence regularity and geometry of orientation columns in the monkey striate cortex , 1974, The Journal of comparative neurology.

[7]  Teuvo Kohonen,et al.  Associative memory. A system-theoretical approach , 1977 .

[8]  D. C. Essen,et al.  Visual areas of the mammalian cerebral cortex. , 1979 .

[9]  J. Daugman Two-dimensional spectral analysis of cortical receptive field profiles , 1980, Vision Research.

[10]  S Marcelja,et al.  Mathematical description of the responses of simple cortical cells. , 1980, Journal of the Optical Society of America.

[11]  M. Bastiaans,et al.  Gabor's expansion of a signal into Gaussian elementary signals , 1980, Proceedings of the IEEE.

[12]  D. Pollen,et al.  Phase relationships between adjacent simple cells in the visual cortex. , 1981, Science.

[13]  H. Szu Two -dimensional optical processing of one- dimensional acoustic data , 1982 .

[14]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[15]  J. Morlet,et al.  Wave propagation and sampling theory—Part I: Complex signal and scattering in multilayered media , 1982 .

[16]  J. Morlet,et al.  Wave propagation and sampling theory—Part II: Sampling theory and complex waves , 1982 .

[17]  D. C. Essen,et al.  Hierarchical organization and functional streams in the visual cortex , 1983, Trends in Neurosciences.

[18]  Takayuki Ito,et al.  Neocognitron: A neural network model for a mechanism of visual pattern recognition , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[19]  John Daugman,et al.  Six formal properties of two-dimensional anisotropie visual filters: Structural principles and frequency/orientation selectivity , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[20]  H.H. Szu,et al.  The mutual time—Frequency content of two signals , 1984, Proceedings of the IEEE.

[21]  A. Grossmann,et al.  DECOMPOSITION OF HARDY FUNCTIONS INTO SQUARE INTEGRABLE WAVELETS OF CONSTANT SHAPE , 1984 .

[22]  J. Daugman Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[23]  D Psaltis,et al.  Optical information processing based on an associative-memory model of neural nets with thresholding and feedback. , 1985, Optics letters.

[24]  A. Grossmann,et al.  Transforms associated to square integrable group representations. I. General results , 1985 .

[25]  S. Thomas Alexander,et al.  Adaptive Signal Processing , 1986, Texts and Monographs in Computer Science.

[26]  I. Daubechies,et al.  PAINLESS NONORTHOGONAL EXPANSIONS , 1986 .

[27]  Y. Meyer Principe d'incertitude, bases hilbertiennes et algèbres d'opérateurs , 1986 .

[28]  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.

[29]  A. Lapedes,et al.  Nonlinear signal processing using neural networks: Prediction and system modelling , 1987 .

[30]  R. Hecht-Nielsen Nearest matched filter classification of spatiotemporal patterns. , 1987, Applied optics.

[31]  Wilson S. Geisler,et al.  Texture segmentation using a class of narrowband filters , 1987, ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[32]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..