PROBABILISTIC FRAMEWORK FOR THE ADAPTATION AND COMPARISON OF IMAGE CODES

We apply a Bayesian method for inferring an optimal basis to the problem of finding efficient image codes for natural scenes. The basis functions learned by the algorithm are oriented and localized in both space and frequency, bearing a resemblance to two-dimensional Gabor functions, and increasing the number of basis functions results in a greater sampling density in position, orientation, and scale. These properties also resemble the spatial receptive fields of neurons in the primary visual cortex of mammals, suggesting that the receptive-field structure of these neurons can be accounted for by a general efficient coding principle. The probabilistic framework provides a method for comparing the coding efficiency of different bases objectively by calculating their probability given the observed data or by measuring the entropy of the basis function coefficients. The learned bases are shown to have better coding efficiency than traditional Fourier and wavelet bases. This framework also provides a Bayesian solution to the problems of image denoising and filling in of missing pixels. We demonstrate that the results obtained by applying the learned bases to these problems are improved over those obtained with traditional techniques.

[1]  D. Whitteridge,et al.  Learning and Relearning , 1959, Science's STKE.

[2]  Miss A.O. Penney.  (b) , 1974, The New Yale Book of Quotations.

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

[4]  D. G. Albrecht,et al.  Spatial frequency selectivity of cells in macaque visual cortex , 1982, Vision Research.

[5]  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.

[6]  Geoffrey E. Hinton,et al.  Learning and relearning in Boltzmann machines , 1986 .

[7]  A. Parker,et al.  Two-dimensional spatial structure of receptive fields in monkey striate cortex. , 1988, Journal of the Optical Society of America. A, Optics and image science.

[8]  Ralph Linsker,et al.  Self-organization in a perceptual network , 1988, Computer.

[9]  I. Daubechies.  Orthonormal bases of compactly supported wavelets , 1988 .

[10]  John G. Daugman,et al.  Complete discrete 2-D Gabor transforms by neural networks for image analysis and compression , 1988, IEEE Trans. Acoust. Speech Signal Process..

[11]  J.G. Daugman,et al.  Entropy reduction and decorrelation in visual coding by oriented neural receptive fields , 1989, IEEE Transactions on Biomedical Engineering.

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

[13]  Ronald R. Coifman,et al.  Entropy-based algorithms for best basis selection , 1992, IEEE Trans. Inf. Theory.

[14]  Leslie S. Smith,et al.  The principal components of natural images , 1992 .

[15]  Edward H. Adelson,et al.  Shiftable multiscale transforms , 1992, IEEE Trans. Inf. Theory.

[16]  Stéphane Mallat,et al.  Matching pursuits with time-frequency dictionaries , 1993, IEEE Trans. Signal Process..

[17]  D. Ruderman.  The statistics of natural images , 1994 .

[18]  D. Donoho,et al.  Basis pursuit , 1994, Proceedings of 1994 28th Asilomar Conference on Signals, Systems and Computers.

[19]  J. Nadal,et al.  Nonlinear neurons in the low-noise limit: a factorial code maximizes information transfer Network 5 , 1994 .

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

[21]  David J. Field,et al.  What Is the Goal of Sensory Coding? , 1994, Neural Computation.

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

[23]  Lawrence Sirovich,et al.  Karhunen–Loève procedure for gappy data , 1995 .

[24]  Geoffrey E. Hinton,et al.  Bayesian Learning for Neural Networks , 1995 .

[25]  C. Fyfe,et al.  Finding compact and sparse-distributed representations of visual images , 1995 .

[26]  Barak A. Pearlmutter,et al.  Maximum Likelihood Blind Source Separation: A Context-Sensitive Generalization of ICA , 1996, NIPS.

[27]  Tai Sing Lee,et al.  Image Representation Using 2D Gabor Wavelets , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

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

[29]  Edward H. Adelson,et al.  Noise removal via Bayesian wavelet coring , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[30]  Toby Berger,et al.  Reliable On-Line Human Signature Verification Systems , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

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

[32]  K.M. Buckley,et al.  Single-snapshot DOA estimation and source number detection , 1997, IEEE Signal Processing Letters.

[33]  J. Cardoso.  Infomax and maximum likelihood for blind source separation , 1997, IEEE Signal Processing Letters.

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

[35]  Song-Chun Zhu,et al.  Minimax Entropy Principle and Its Application to Texture Modeling , 1997, Neural Computation.

[36]  Rajesh P. N. Rao,et al.  Dynamic Model of Visual Recognition Predicts Neural Response Properties in the Visual Cortex , 1997, Neural Computation.

[37]  Néstor Parga,et al.  Redundancy Reduction and Independent Component Analysis: Conditions on Cumulants and Adaptive Approaches , 1997, Neural Computation.

[38]  J. V. van Hateren,et al.  Independent component filters of natural images compared with simple cells in primary visual cortex , 1998, Proceedings of the Royal Society of London. Series B: Biological Sciences.

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

[40]  Michael A. Saunders,et al.  Atomic Decomposition by Basis Pursuit , 1998, SIAM J. Sci. Comput..

[41]  D. Ruderman,et al.  Independent component analysis of natural image sequences yields spatio-temporal filters similar to simple cells in primary visual cortex , 1998, Proceedings of the Royal Society of London. Series B: Biological Sciences.

[42]  Rajesh P. N. Rao,et al.  Development of localized oriented receptive fields by learning a translation-invariant code for natural images. , 1998, Network.

[43]  Eero P. Simoncelli,et al.  Image compression via joint statistical characterization in the wavelet domain , 1999, IEEE Trans. Image Process..

[44]  Hagai Attias,et al.  Independent Factor Analysis , 1999, Neural Computation.

[45]  Bhaskar D. Rao,et al.  An affine scaling methodology for best basis selection , 1999, IEEE Trans. Signal Process..

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

[47]  Terrence J. Sejnowski,et al.  Learning Overcomplete Representations , 2000, Neural Computation.

[48]  RussLL L. Ds Vnlos,et al.  SPATIAL FREQUENCY SELECTIVITY OF CELLS IN MACAQUE VISUAL CORTEX , 2022 .