Double-Gabor Filters Are Independent Components of Small Translation-Invariant Image Patches

The analysis of natural images with independent component analysis (ICA) yields localized bandpass Gabor-type filters similar to receptive fields of simple cells in visual cortex. We applied ICA on a subset of patches called position-centered patches, selected for forming a translation-invariant representation of small patches. The resulting filters were qualitatively different in two respects. One novel feature was the emergence of filters we call double-Gabor filters. In contrast to Gabor functions that are modulated in one direction, double-Gabor filters are sinusoidally modulated in two orthogonal directions. In addition the filters were more extended in space and frequency compared to standard ICA filters and better matched the distribution in experimental recordings from neurons in primary visual cortex. We further found a dual role for double-Gabor filters as edge and texture detectors, which could have engineering applications.

[1]  Eero P. Simoncelli,et al.  Spatiotemporal Elements of Macaque V1 Receptive Fields , 2005, Neuron.

[2]  Marcos S. Amaral,et al.  Signal-Tuned Gabor Functions as Models for Stimulus-Dependent Cortical Receptive Fields , 2014, Neural Computation.

[3]  Andrzej Cichocki,et al.  A New Learning Algorithm for Blind Signal Separation , 1995, NIPS.

[4]  Eero P. Simoncelli,et al.  Natural image statistics and neural representation. , 2001, Annual review of neuroscience.

[5]  Erkki Oja,et al.  Independent Component Analysis , 2001 .

[6]  David J. Field,et al.  Sparse coding with an overcomplete basis set: A strategy employed by V1? , 1997, Vision Research.

[7]  P. Comon.  Independent Component Analysis , 1992 .

[8]  Terrence J. Sejnowski,et al.  Unsupervised Learning , 2018, Encyclopedia of GIS.

[9]  David J. Field,et al.  Emergence of simple-cell receptive field properties by learning a sparse code for natural images , 1996, Nature.

[10]  Christian Jutten,et al.  Blind separation of sources, part I: An adaptive algorithm based on neuromimetic architecture , 1991, Signal Process..

[11]  Pierre Comon.  Independent component analysis - a new concept? signal processing , 1994 .

[12]  Pierre Comon,et al.  Independent component analysis, A new concept? , 1994, Signal Process..

[13]  J. H. Hateren,et al.  Independent component filters of natural images compared with simple cells in primary visual cortex , 1998 .

[14]  R. Shapley,et al.  Dynamics of orientation tuning in macaque V1: the role of global and tuned suppression. , 2003, Journal of Neurophysiology.

[15]  Feng Qi Han,et al.  Excitatory and suppressive receptive field subunits in awake monkey primary visual cortex (V1) , 2007, Proceedings of the National Academy of Sciences.

[16]  Xiang-Yan Zeng,et al.  Multi-class feature selection for texture classification , 2006, Pattern Recognit. Lett..

[17]  E. Oja,et al.  Independent Component Analysis , 2013 .

[18]  H. B. Barlow,et al.  Possible Principles Underlying the Transformations of Sensory Messages , 2012 .

[19]  D. Ringach.  Mapping receptive fields in primary visual cortex , 2004, The Journal of physiology.

[20]  Terrence J. Sejnowski,et al.  An Information-Maximization Approach to Blind Separation and Blind Deconvolution , 1995, Neural Computation.

[21]  S. Laughlin.  A Simple Coding Procedure Enhances a Neuron's Information Capacity , 1981, Zeitschrift fur Naturforschung. Section C, Biosciences.

[22]  Terrence J. Sejnowski,et al.  The “independent components” of natural scenes are edge filters , 1997, Vision Research.