research-article

Learning High-order Generative Texture Models

Authors:

Ralph Versteegen,

Georgy Gimel'farb,

Patricia RiddleAuthors Info & Claims

IVCNZ '14: Proceedings of the 29th International Conference on Image and Vision Computing New Zealand

Pages 90 - 95

https://doi.org/10.1145/2683405.2683420

Published: 19 November 2014 Publication History

Abstract

We introduce a new simple framework for texture modelling with Markov--Gibbs random fields (MGRF). The framework learns texture-specific high order pixel interactions described by feature functions of signal patterns. Currently, modelling of high order interactions is almost exclusively achieved by linear filtering. Instead we investigate `binary pattern' (BP) features which are faster to compute and describe quite different properties than linear filters. The features are similar to local binary patterns (LBPs) --- previously not applied as MGRF features --- but with learnt shapes. In contrast to the majority of MGRF models the set of features used is learnt from the training data and is heterogeneous. This paper shows how these features can be efficiently selected by nesting the models. Each new layer corrects errors of the previous model while allowing incremental composition of the features, and uses validation data to decide the stopping point. The framework also reduces overfitting and speeds learning due to a feasible number of free parameters to be learnt at each step. Texture synthesis results of the proposed texture models were quantitatively evaluated by a panel of observers, showing higher order BP features resulted in significant improvements on regularly and irregularly structured textures.

References

[1]

L. B. Almeida, T. Langlois, J. D. Amaral, and A. Plakhov. On-line learning in neural networks. chapter Parameter Adaptation in Stochastic Optimization, pages 111--134. Cambridge University Press, New York, 1998.

Digital Library

[2]

P. Brodatz. Textures: a Photographic Album for Artists and Designers. Dover, New York, 1966.

[3]

G. R. Cross and A. K. Jain. Markov random field texture models. IEEE Trans. on Pattern Analysis and Machine Intelligence, 5(1):25--39, Jan 1983.

Digital Library

[4]

S. Della Pietra, V. Della Pietra, and J. Lafferty. Inducing features of random fields. IEEE Trans. on Pattern Analysis and Machine Intelligence, 19(4):380--393, 1997.

Digital Library

[5]

A. Gagalowicz and S. D. Ma. Sequential synthesis of natural textures. Computer Vision, Graphics, and Image Processing, 30(3):289--315, 1985.

[6]

G. Gimel'farb. Image Textures and Gibbs Random Fields. Kluwer Academic Publishers, Dordrecht, 1999.

[7]

N. Heess, C. K. I. Williams, and G. E. Hinton. Learning generative texture models with extended Fields-of-Experts. In Proc. British Machine Vision Conf. (BMVC'09), 2009.

[8]

E. T. Jaynes. Information theory and statistical mechanics. Phys. Rev., 106:620--630, May 1957.

[9]

J. J. Kivinen and C. Williams. Multiple texture Boltzmann machines. In N. D. Lawrence and M. A. Girolami, editors, Proc. 15th Int. Conf. on Artificial Intelligence and Statistics, pages 638--646 vol.2, 2012.

[10]

V. Kwatra, A. Schödl, I. Essa, G. Turk, and A. Bobick. Graphcut textures: Image and video synthesis using graph cuts. ACM Trans. on Graphics, SIGGRAPH 2003, 22(3):277--286, July 2003.

Digital Library

[11]

S. Lee, V. Ganapathi, and D. Koller. Efficient structure learning of Markov networks using L1-regularization. In Advances in Neural Information Processing Systems 19 (NIPS'06), 2006.

[12]

H. Luo, P. L. Carrier, A. Courville, and Y. Bengio. Texture modeling with convolutional spike-and-slab RBMs and deep extensions. J. of Machine Learning Research, 31:415--423, 2013.

[13]

L. Mihalkova and R. J. Mooney. Bottom-up learning of Markov logic network structure. In Proc. 24th Int. Conf. on Machine Learning, ICML '07, pages 625--632, New York, 2007. ACM.

Digital Library

[14]

T. Ojala, M. Pietikäinen, and D. Harwood. A comparative study of texture measures with classification based on featured distributions. Pattern Recognition, 29(1):51--59, 1996.

[15]

T. Ojala, M. Pietikäinen, and T. Maenpaa. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. on Pattern Analysis and Machine Intelligence, 24(7):971--987, Jul 2002.

Digital Library

[16]

J. Portilla and E. P. Simoncelli. A parametric texture model based on joint statistics of complex wavelet coefficients. Int. J. Computer Vision, 40(1):49--70, 2000.

Digital Library

[17]

M. Ranzato, V. Mnih, and G. E. Hinton. Generating more realistic images using gated MRFs. In Advances in Neural Information Processing Systems 23 (NIPS'10), pages 2002--2010. Curran Associates, 2010.

[18]

S. Roth and M. J. Black. Fields of Experts. Int. J. of Computer Vision, 82(2):205--229, 2009.

Digital Library

[19]

M. Schmidt and K. Murphy. Convex structure learning in log-linear models: Beyond pairwise potentials. In Proc. Int. Workshop on Artificial Intelligence and Statistics, 2010.

[20]

T. Tieleman. Training restricted Boltzmann machines using approximations to the likelihood gradient. In Proc. 25th Int. Conf. on Machine Learning (ICML'08), pages 1064--1071. ACM, 2008.

Digital Library

[21]

J. Žujović. Perceptual Texture Similarity Metrics. PhD thesis, Northwestern University, 2011.

[22]

L.-Y. Wei and M. Levoy. Fast texture synthesis using tree-structured vector quantization. In Proc. 27th Conf. on Computer Graphics and Interactive Techniques, SIGGRAPH '00, pages 479--488, New York, 2000. ACM Press/Addison-Wesley Publishing.

Digital Library

[23]

A. Zalesny. Analysis and synthesis of textures with pairwise signal interactions. Technical Report KUL/ESAT/PSI/9902, Katholieke Universiteit Leuven, 1999.

[24]

Y. Zhai, D. Neuhoff, and T. Pappas. Local radius index - a new texture similarity feature. In IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), pages 1434--1438, May 2013.

[25]

S. C. Zhu, Y. Wu, and D. Mumford. Filters, random fields and maximum entropy (FRAME): Towards a unified theory for texture modeling. Int. J. of Computer Vision, 27(2):107--126, 1998.

Digital Library

[26]

K. Zuiderveld. Contrast limited adaptive histogram equalization. In Graphic Gems IV, pages 474--485. Academic Press Professional, 1994.

Digital Library

Cited By

Cai XSong BFang Z(2019)Exemplar based Regular Texture Synthesis Using LSTMPattern Recognition Letters10.1016/j.patrec.2019.09.006Online publication date: Sep-2019
https://doi.org/10.1016/j.patrec.2019.09.006
Versteegen RGimel'farb GRiddle P(2015)Texture modelling with non-contiguous filters2015 International Conference on Image and Vision Computing New Zealand (IVCNZ)10.1109/IVCNZ.2015.7761520(1-6)Online publication date: Nov-2015
https://doi.org/10.1109/IVCNZ.2015.7761520
Lewis J(2015)Realism and Texture: Benchmark Problems for Natural ComputationUnconventional Computation and Natural Computation10.1007/978-3-319-21819-9_3(53-65)Online publication date: 4-Aug-2015
https://doi.org/10.1007/978-3-319-21819-9_3

Index Terms

Learning High-order Generative Texture Models
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision problems
      2. Computer vision tasks
        Scene understanding
    2. Philosophical/theoretical foundations of artificial intelligence
  2. Computer graphics
    1. Image manipulation

Recommendations

Learnable high-order MGRF models for contrast-invariant texture recognition

A new learnable high-order ordinal Markov-Gibbs field model of textures.Fast analytic learning of up to 8th-order potentials and iteraction structures.Texture-specific local binary/ternary patterns for accurate retrieval.Learning shapes, sizes, and ...
High-Order MGRF Models for Contrast/Offset Invariant Texture Retrieval
IVCNZ '14: Proceedings of the 29th International Conference on Image and Vision Computing New Zealand

Local ordinal signal relations, such as local binary or ternary patterns (LBP/LTP), and their statistics are promising texture descriptors due to their invariance to frequent in practice spatially variant contrast / offset deviations that preserve image ...
Learning completed discriminative local features for texture classification

We propose a novel feature representation method, namely Completed Discriminative Local Features (CDLF), for texture classification.The CDLF learn transformation matrices for texture images that maximize the mutual information between the local features ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

IVCNZ '14: Proceedings of the 29th International Conference on Image and Vision Computing New Zealand

November 2014

298 pages

ISBN:9781450331845

DOI:10.1145/2683405

Co-chairs:
John Perrone,
Michael Mayo,
Anthony Blake,
General Chair:
Michael J. Cree,
Publications Chair:
Lee Streeter

Copyright © 2014 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

In-Cooperation

The University of Waikato

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 19 November 2014

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Qualifiers

Research-article
Research
Refereed limited

Conference

IVCNZ '14

IVCNZ '14: The 29th International Conference on Image and Vision Computing New Zealand

November 19 - 21, 2014

Hamilton, New Zealand

Acceptance Rates

IVCNZ '14 Paper Acceptance Rate 55 of 74 submissions, 74%;

Overall Acceptance Rate 55 of 74 submissions, 74%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

3
Total Citations
View Citations
52
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 10 Oct 2024

Other Metrics

View Author Metrics

Citations

Cited By

Cai XSong BFang Z(2019)Exemplar based Regular Texture Synthesis Using LSTMPattern Recognition Letters10.1016/j.patrec.2019.09.006Online publication date: Sep-2019
https://doi.org/10.1016/j.patrec.2019.09.006
Versteegen RGimel'farb GRiddle P(2015)Texture modelling with non-contiguous filters2015 International Conference on Image and Vision Computing New Zealand (IVCNZ)10.1109/IVCNZ.2015.7761520(1-6)Online publication date: Nov-2015
https://doi.org/10.1109/IVCNZ.2015.7761520
Lewis J(2015)Realism and Texture: Benchmark Problems for Natural ComputationUnconventional Computation and Natural Computation10.1007/978-3-319-21819-9_3(53-65)Online publication date: 4-Aug-2015
https://doi.org/10.1007/978-3-319-21819-9_3

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents