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

By John G. Daugman. 1988

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Robust multimodal face and fingerprint fusion in the presence of spoofing attacks (2016, background): “2D Gabor filters [30]: these filters as product of a Gaussian and a sinusoid capturing local details are parameterized by Gaussian space constants 240”
Statistical Richness of Visual Phase Information: Update on Recognizing Persons by Iris Patterns (2001, methodology): “Each isolated iris pattern is then demodulated (Daugman and Downing, 1995) to extract its phase information using quadrature 2D Gabor wavelets ( Daugman, 1980, 1985, 1988 ).”
Predictive Coding as a Model of Response Properties in Cortical Area V1 (2010, methodology): “The RF of a simple cell in primary visual cortex can be accurately modeled by a two-dimensional Gabor function (Daugman, 1980, 1988; Marcelja, 1980; Jones and Palmer, 1987; Lee, 1996).”
Image processing for artist identification (2008, methodology): “…methods, the Van Gogh and Kröller-Müller Museums in The Netherlands graciously agreed to make a data set of 101 high-resolution gray-scale scans [C. Richard Johnson, Jr., Ella Hendriks, Igor J. Berezhnoy, Eugene Brevdo, Shannon M. Hughes, Ingrid Daubechies, Jia Li, Eric Postma, and James Z. Wang]”
What Is the Goal of Sensory Coding? (1994, methodology): “The published response histograms by both Zetzsche (1990) and Daugman (1988) also suggest that codes based on the properties of the mammalian visual system will show positive kurtosis in response to natural scenes.”
Shiftable multiscale transforms (1992, background): “Several other authors have developed non-orthogonal oriented multiscale transforms in which the basis functions are translations and rotations of a common function [12], [19], [32], [47].”
Dictionaries for Sparse Representation Modeling (2010, methodology): “These results motivated the deployment of the transform to image processing tasks, led by works such as Daugman [22] and Porat and Zeevi [23].”
Contour detection based on nonclassical receptive field inhibition (2003, methodology): “compression [35], motion analysis [36], image enhancement [37], face recognition [38], person identification based on iris pattern analysis [39], texture analysis [40]–[45], retrieval from image databases [46]–[48], and edge detection [49]–[53].”
A neurodynamical cortical model of visual attention and invariant object recognition. (2004, methodology): “Even more, Daugman (1988) proposed that an ensemble of simple cells is best modelled as a family of 2D-Gabor wavelets sampling the frequency domain in a log-polar manner as a function of eccentricity.”
Image analysis by bidimensional empirical mode decomposition (2003, methodology): “The most commonly multiscale features used are Wigner distributions [14,31], Gabor functions [2,7,16] and wavelets transforms [18,19,21,34,36].”
Deep Hierarchies in the Primate Visual Cortex: What Can We Learn for Computer Vision? (2013, background): “Gabor wavelets have also been very successful in applications such as image compression [29], image retrieval [108], and face recognition [201].”
Statistical shape models for 3D medical image segmentation: A review (2009, methodology): “One feature that has been used successfully in face recognition with 2D SSMs is that of Gabor wavelets (Daugman, 1988): This method measures the local image response to a set of Gabor filters, resulting in a feature vector (also called jet) containing amplitude and phase for each individual filter.”
The Design and Use of Steerable Filters (1991, background): “Non-orthogonal pyramids with orientation tuning have been described by [9, 14, 28, 43].”
Image compression with neural networks - A survey (1999, background): “Neural networks are only developed to target individual problems inside this mode [9,15,36,47].”