Statistically and perceptually motivated nonlinear image representation

We describe an invertible nonlinear image transformation that is well-matched to the statistical properties of photographic images, as well as the perceptual sensitivity of the human visual system. Images are first decomposed using a multi-scale oriented linear transformation. In this domain, we develop a Markov random field model based on the dependencies within local clusters of transform coefficients associated with basis functions at nearby positions, orientations and scales. In this model, division of each coefficient by a particular linear combination of the amplitudes of others in the cluster produces a new nonlinear representation with marginally Gaussian statistics. We develop a reliable and efficient iterative procedure for inverting the divisive transformation. Finally, we probe the statistical and perceptual advantages of this image representation, examining robustness to added noise, rate-distortion behavior, and artifact-free local contrast enhancement.

[1]  Patrick C. Teo,et al.  Perceptual image distortion , 1994, Electronic Imaging.

[2]  Fionn Murtagh,et al.  Gray and color image contrast enhancement by the curvelet transform , 2003, IEEE Trans. Image Process..

[3]  Eero P. Simoncelli,et al.  Directly Invertible Nonlinear Divisive Normalization Pyramid for Image Representation , 2003, VLBV.

[4]  Joshua Gluckman,et al.  Higher Order Image Pyramids , 2006, ECCV.

[5]  R. Navarro,et al.  Optimal coding through divisive normalization models of V1 neurons , 2003, Network.

[6]  Leszek Wojnar,et al.  Image Analysis , 1998 .

[7]  G. Granlund.  In search of a general picture processing operator , 1978 .

[8]  Geoffrey E. Hinton,et al.  Topographic Product Models Applied to Natural Scene Statistics , 2006, Neural Computation.

[9]  J. Besag.  Spatial Interaction and the Statistical Analysis of Lattice Systems , 1974 .

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

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

[12]  Kannan Ramchandran,et al.  Low-complexity image denoising based on statistical modeling of wavelet coefficients , 1999, IEEE Signal Processing Letters.

[13]  D. Heeger.  Normalization of cell responses in cat striate cortex , 1992, Visual Neuroscience.

[14]  Eero P. Simoncelli,et al.  Statistical Modeling of Images with Fields of Gaussian Scale Mixtures , 2006, NIPS.

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

[16]  Martin J. Wainwright,et al.  Scale Mixtures of Gaussians and the Statistics of Natural Images , 1999, NIPS.

[17]  Eero P. Simoncelli,et al.  Random Cascades on Wavelet Trees and Their Use in Analyzing and Modeling Natural Images , 2001 .

[18]  M. Bethge.  Factorial coding of natural images: how effective are linear models in removing higher-order dependencies? , 2006, Journal of the Optical Society of America. A, Optics, image science, and vision.

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

[20]  Ken D. Sauer,et al.  A generalized Gaussian image model for edge-preserving MAP estimation , 1993, IEEE Trans. Image Process..

[21]  D. G. Albrecht,et al.  Cortical neurons: Isolation of contrast gain control , 1992, Vision Research.

[22]  P. J. Burt,et al.  Fast Filter Transforms for Image Processing , 1981 .

[23]  Dani Lischinski,et al.  Gradient Domain High Dynamic Range Compression , 2023 .

[24]  Pierre Moulin,et al.  Analysis of Multiresolution Image Denoising Schemes Using Generalized Gaussian and Complexity Priors , 1999, IEEE Trans. Inf. Theory.

[25]  Justin K. Romberg,et al.  Bayesian wavelet-domain image modeling using hidden Markov trees , 1999, Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348).

[26]  T.,et al.  Shiftable Multi-scale TransformsEero , 1992 .

[27]  E. Peli.  Contrast in complex images. , 1990, Journal of the Optical Society of America. A, Optics and image science.

[28]  Anuj Srivastava,et al.  Universal Analytical Forms for Modeling Image Probabilities , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[29]  J A Solomon,et al.  Model of visual contrast gain control and pattern masking. , 1997, Journal of the Optical Society of America. A, Optics, image science, and vision.

[30]  Eero P. Simoncelli.  Statistical models for images: compression, restoration and synthesis , 1997, Conference Record of the Thirty-First Asilomar Conference on Signals, Systems and Computers (Cat. No.97CB36136).

[31]  J. Gluckman.  Higher order image pyramids: an early visual representation , 2006 .

[32]  Gerhard Winkler,et al.  Image Analysis, Random Fields and Markov Chain Monte Carlo Methods: A Mathematical Introduction , 2002 .

[33]  Francesc J. Ferri,et al.  Non-linear Invertible Representation for Joint Statistical and Perceptual Feature Decorrelation , 2000, SSPR/SPR.

[34]  Michael W. Marcellin,et al.  JPEG2000 - image compression fundamentals, standards and practice , 2002, The Kluwer International Series in Engineering and Computer Science.

[35]  Robert D. Nowak,et al.  Wavelet-based statistical signal processing using hidden Markov models , 1998, IEEE Trans. Signal Process..

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

[37]  R. Navarro,et al.  Optimal coding through divisive normalization models of V1 neurons. , 2003 .

[38]  Edward H. Adelson,et al.  Compressing and companding high dynamic range images with subband architectures , 2005, SIGGRAPH 2005.

[39]  E. Jaynes.  Information Theory and Statistical Mechanics , 1957 .

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

[41]  Eero P. Simoncelli,et al.  Nonlinear image representation for efficient perceptual coding , 2006, IEEE Transactions on Image Processing.

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

[43]  D J Field,et al.  Relations between the statistics of natural images and the response properties of cortical cells. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[44]  Song-Chun Zhu,et al.  Prior Learning and Gibbs Reaction-Diffusion , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[45]  William H. Press,et al.  Numerical recipes , 1990 .

[46]  Michael J. Black,et al.  Fields of Experts: a framework for learning image priors , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[47]  Eero P. Simoncelli,et al.  Natural signal statistics and sensory gain control , 2001, Nature Neuroscience.

[48]  David Mumford,et al.  Statistics of natural images and models , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[49]  J. M. Foley,et al.  Human luminance pattern-vision mechanisms: masking experiments require a new model. , 1994, Journal of the Optical Society of America. A, Optics, image science, and vision.

[50]  Eero P. Simoncelli,et al.  Locally adaptive multiscale contrast optimization , 2005, IEEE International Conference on Image Processing 2005.

[51]  Lucas C. Parra,et al.  Higher-Order Statistical Properties Arising from the Non-Stationarity of Natural Signals , 2000, NIPS.

[52]  Bernhard Wegmann,et al.  Statistical dependence between orientation filter outputs used in a human-vision-based image code , 1990, Other Conferences.

[53]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.