The DOI matches its Crossref record; 40 of the 40 references it cites were found in a registry or an index.
Prior learning and Gibbs reaction-diffusion
Open accessAbstract
This article addresses two important themes in early visual computation: it presents a novel theory for learning the universal statistics of natural images, and, it proposes a general framework of designing reaction-diffusion equations for image processing. We studied the statistics of natural images including the scale invariant properties, then generic prior models were learned to duplicate the observed statistics, based on minimax entropy theory. The resulting Gibbs distributions have potentials of the form U(I; /spl Lambda/, S)=/spl Sigma//sub /spl alpha/=1//sup k//spl Sigma//sub x,y//spl lambda//sup (/spl alpha/)/((F/sup (/spl alpha/)/*I)(x,y)) with S={F/sup (1)/, F/sup (2)/,...,F/sup (K)/} being a set of filters and /spl Lambda/={/spl lambda//sup (1)/(),/spl lambda//sup (2)/(),...,/spl lambda//sup (K)/()} the potential functions. The learned Gibbs distributions confirm and improve the form of existing prior models such as line-process, but, in contrast to all previous models, inverted potentials were found to be necessary. We find that the partial differential equations given by gradient descent on U(I; /spl Lambda/, S) are essentially reaction-diffusion equations, where the usual energy terms produce anisotropic diffusion, while the inverted energy terms produce reaction associated with pattern formation, enhancing preferred image features. We illustrate how these models can be used for texture pattern rendering, denoising, image enhancement, and clutter removal by careful choice of both prior and data models of this type, incorporating the appropriate features.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
On Information and Sufficiency
Kullback, S., & Leibler, R. A. (1951) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177729694 · Cited by 20,193
Stochastic relaxation, gibbs distributions, and the bayesian restoration of images.
Geman, S., & Geman, D. (1984) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.1984.4767596 · Cited by 17,949
Scale-space and edge detection using anisotropic diffusion
Perona, P., & Malik, J. (1990) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.56205 · Cited by 12,119
The chemical basis of morphogenesis
Turing, A. M. (1952) · Philosophical Transactions of the Royal Society of London. Series B, Biological Sciences · doi:10.1098/rstb.1952.0012 · Cited by 11,733
Solutions of Ill-Posed Problems.
Bell, J. B., Tikhonov, A. N., & Arsenin, V. Y. (1978) · Mathematics of Computation · doi:10.2307/2006360 · Cited by 8,101
Optimal approximations by piecewise smooth functions and associated variational problems
Mumford, D., & Shah, J. (1989) · Communications on Pure and Applied Mathematics · doi:10.1002/cpa.3160420503 · Cited by 5,208
Self-citationГабор, Д. (1946) · Journal of the IEE · Cited by 5,036
The renormalization group: Critical phenomena and the Kondo problem
Wilson, K. G. (1975) · Reviews of Modern Physics · doi:10.1103/revmodphys.47.773 · Cited by 4,522
Networks for approximation and learning
Poggio, T., & Girosi, F. (1990) · Proceedings of the IEEE · doi:10.1109/5.58326 · Cited by 3,252
Relations between the statistics of natural images and the response properties of cortical cells
Field, D. J. (1987) · Journal of the Optical Society of America A · doi:10.1364/josaa.4.002379 · Cited by 3,241
Daugman, J. G. (1985) · Journal of the Optical Society of America A · doi:10.1364/josaa.2.001160 · Cited by 3,219
A maximum entropy approach to natural language processing
Berger, A. L., Pietra, V. J. D., & Pietra, S. A. D. (1996) · doi:10.5555/234285.234289 · Cited by 3,065
Blake, A., & Zisserman, A. (1987) · The MIT Press eBooks · doi:10.7551/mitpress/7132.001.0001 · Cited by 2,105
Region competition: unifying snakes, region growing, and Bayes/MDL for multiband image segmentation
Zhu, S. C., & Yuille, A. (1996) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.537343 · Cited by 1,913
Self-citationComputational vision and regularization theory
Poggio, T., Torre, V., & Koch, C. (1985) · Nature · doi:10.1038/317314a0 · Cited by 1,412
Black, M. J., Sapiro, G., Marimont, D. H., & Heeger, D. (1998) · IEEE Transactions on Image Processing · doi:10.1109/83.661192 · Cited by 1,295
Constrained restoration and the recovery of discontinuities
Geman, D., & Reynolds, G. (1992) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.120331 · Cited by 1,085
Statistics of natural images: Scaling in the woods
Ruderman, D. L., & Bialek, W. (1994) · Physical Review Letters · doi:10.1103/physrevlett.73.814 · Cited by 920
Probabilistic Solution of Ill-Posed Problems in Computational Vision
Marroquin, J., Mitter, S., & Poggio, T. (1987) · Journal of the American Statistical Association · doi:10.1080/01621459.1987.10478393 · Cited by 766
Black, M. J., & Rangarajan, A. (1996) · International Journal of Computer Vision · doi:10.1007/bf00131148 · Cited by 757
Filters, Random Fields and Maximum Entropy (FRAME): Towards a Unified Theory for Texture Modeling
Zhu, S. C., Wu, Y., & Mumford, D. (1998) · International Journal of Computer Vision · doi:10.1023/a:1007925832420 · Cited by 652
Self-citationRobust regression methods for computer vision: A review
Meer, P., Mintz, D., Rosenfeld, A., & Kim, D. Y. (1991) · International Journal of Computer Vision · doi:10.1007/bf00127126 · Cited by 638
Natural image statistics and efficient coding
Olshausen, B. A., & Field, D. J. (1996) · Network: Computation in Neural Systems · doi:10.1088/0954-898x_7_2_014 · Cited by 561
Kimia, B. B., Tannenbaum, A. R., & Zucker, S. W. (1995) · International Journal of Computer Vision · doi:10.1007/bf01451741 · Cited by 543
Image Analysis, Random Fields and Dynamic Monte Carlo Methods
Winkler, G. (1995) · Springer eBooks · doi:10.1007/978-3-642-97522-6 · Cited by 515
Parallel and deterministic algorithms from MRFs: surface reconstruction
Geiger, D., & Girosi, F. (1991) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.134040 · Cited by 447
Minimax Entropy Principle and Its Application to Texture Modeling
Zhu, S. C., Wu, Y. N., & Mumford, D. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1627 · Cited by 420
Self-citationGenerating textures on arbitrary surfaces using reaction-diffusion
Turk, G. (1991) · Proceedings of the 18th annual conference on Computer graphics and interactive techniques · doi:10.1145/122718.122749 · Cited by 405
A Pre-pattern formation mechanism for animal coat markings
Murray, J. D. (1981) · Journal of Theoretical Biology · doi:10.1016/0022-5193(81)90334-9 · Cited by 367
Multilevel computational processes for visual surface reconstruction
Terzopoulos, D. (1983) · Computer Vision, Graphics, and Image Processing · doi:10.1016/0734-189x(83)90020-8 · Cited by 317
Diffusions for Global Optimization
Geman, S., & Hwang, C.-R. (1986) · SIAM Journal on Control and Optimization · doi:10.1137/0324060 · Cited by 313
Nonlinear image filtering with edge and corner enhancement
Nitzberg, M., & Shiota, T. (1992) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.149593 · Cited by 301
Witkin, A., & Kass, M. (1991) · Proceedings of the 18th annual conference on Computer graphics and interactive techniques · doi:10.1145/122718.122750 · Cited by 300
A model for the formation of ocular dominance stripes
Swindale, N. V. (1980) · Proceedings of the Royal Society of London. Series B. Biological Sciences · doi:10.1098/rspb.1980.0051 · Cited by 244
Efficiency of a model human image code
Watson, A. B. (1987) · Journal of the Optical Society of America A · doi:10.1364/josaa.4.002401 · Cited by 209
A common framework for image segmentation
Geiger, D., & Yuille, A. (1991) · International Journal of Computer Vision · doi:10.1007/bf00115697 · Cited by 177
Witkin, A., & Kass, M. (1991) · ACM SIGGRAPH Computer Graphics · doi:10.1145/127719.122750 · Cited by 164
FRAME: filters, random fields, and minimax entropy towards a unified theory for texture modeling
Zhu, S. C., Wu, Y., & Mumford, D. (1996) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.1996.517147 · Cited by 38
Self-citationA General Framework for Geometry-Driven Evolution Equations
Niessen, W. J., Romeny, B. M. T. H., Florack, L. M. J., & Viergever, M. A. (1997) · International Journal of Computer Vision · doi:10.1023/a:1007995731951 · Cited by 30
M-lattice: from morphogenesis to image processing
Sherstinsky, A. S., & Picard, R. W. (1996) · IEEE Transactions on Image Processing · doi:10.1109/83.502393 · Cited by 22
Cited by
Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries
Elad, M., & Aharon, M. (2006) · IEEE Transactions on Image Processing · doi:10.1109/tip.2006.881969 · Cited by 5,321
Multi-Stage Progressive Image Restoration
Zamir, S. W., Arora, A., Khan, S., Hayat, M., Khan, F. S., Yang, M.-H., & Shao, L. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01458 · Cited by 2,095
Sparse Representation for Color Image Restoration
Mairal, J., Elad, M., & Sapiro, G. (2008) · IEEE Transactions on Image Processing · doi:10.1109/tip.2007.911828 · Cited by 1,716
Learning a variational network for reconstruction of accelerated MRI data
Hammernik, K., Klatzer, T., Kobler, E., Recht, M. P., Sodickson, D. K., Pock, T., & Knoll, F. (2018) · Magnetic Resonance in Medicine · doi:10.1002/mrm.26977 · Cited by 1,713
Statistical Color Models with Application to Skin Detection
Jones, M. J., & Rehg, J. M. (2002) · International Journal of Computer Vision · doi:10.1023/a:1013200319198 · Cited by 1,542
Metadata
- Authors
- Zhu, S. C., & Mumford, D.
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 1997
- Volume
- 19
- Issue
- 11
- Pages
- 1236-1250
- ISSN
- 0162-8828 (ISSN-L)
- OpenAlex
- W2149396346
- Cited by
- 319
- References
- 40
- FWCI
- 16.50
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.