This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Visually Distinct Patterns with Matching Subband Statistics
February 2005 (vol. 27 no. 2)
pp. 252-264
ASCII Text
x 
 
Joshua Gluckman, "Visually Distinct Patterns with Matching Subband Statistics," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, no. 2, pp. 252-264, February, 2005.
 
 
BibTex
x
 
@article{ 10.1109/TPAMI.2005.42,
author = {Joshua Gluckman},
title = {Visually Distinct Patterns with Matching Subband Statistics},
journal ={IEEE Transactions on Pattern Analysis and Machine Intelligence},
volume = {27},
number = {2},
issn = {0162-8828},
year = {2005},
pages = {252-264},
doi = {http://doi.ieeecomputersociety.org/10.1109/TPAMI.2005.42},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - JOUR
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
TI - Visually Distinct Patterns with Matching Subband Statistics
IS - 2
SN - 0162-8828
SP252
EP264
EPD - 252-264
A1 - Joshua Gluckman,
PY - 2005
KW - Texture
KW - statistical models
KW - feature representation
KW - moments.
VL - 27
JA - IEEE Transactions on Pattern Analysis and Machine Intelligence
ER -
 
A commonly used representation of a visual pattern is a statistical distribution measured from the output of a bank of filters (Gaussian, Laplacian, Gabor, etc.). Both marginal and joint distributions of filter responses have been advocated and effectively used for a variety of vision tasks, including texture classification, texture synthesis, object detection, and image retrieval. This paper examines the ability of these representations to discriminate between an arbitrary pair of visual stimuli. Examples of patterns are derived that provably possess the same marginal and joint statistical properties, yet are "visually distinct.” This is accomplished by showing sufficient conditions for matching the first k moments of the marginal distributions of a pair of images. Then, given a set of filters, we show how to match the marginal statistics of the subband images formed through convolution with the filter set. Next, joint statistics are examined and images with similar joint distributions of subband responses are shown. Finally, distinct periodic patterns are derived that possess approximately the same subband statistics for any arbitrary filter set.

[1] M. Mandal and T. Aboulnasr, “Image Indexing Using Moments and Wavelets,” IEEE Trans. Consumer Electronics, vol. 42, no. 3, pp. 557-565, 1996.
[2] B. Schiele and J. Crowley, “Recognition without Correspondence Using Multidimensional Receptive Field Histograms,” Int'l J. Computer Vision, vol. 36, no. 1, 2000.
[3] C. Schmid, “Constructing Models for Content-Based Image Retrieval,” Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR '01), 2001.
[4] H. Schneiderman and T. Kanade, “A Statistical Method for 3D Object Detection Applied to Faces and Cars,” Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR '00), 2000.
[5] J. Portilla and E. Simoncelli, “A Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients,” Int'l J. Computer Vision, vol. 40, no. 1, pp. 49-71, 2000.
[6] E. Simoncelli and E. Adelson, “Noise Removal via Bayesian Wavelet Coding,” Int'l Conf. Image Processing, 1996.
[7] J. De Bonet and P. Viola, “A Non-Parametric Multi-Scale Statistical Model for Natural Images,” Advances in Neural Information Processing, vol. 10, 1997.
[8] X. Liu and D. Wang, “Texture Classification Using Spectral Histograms,” IEEE Trans. Image Processing, vol. 12, no. 6, 2003.
[9] B. Julesz, “Visual Pattern Discrimination,” Trans. Information Theory, no. 8, pp. 84-92, 1962.
[10] T. Caelli and B. Julesz, “On Perceptual Analyzers Underlying Visual Texture Discrimination,” Part I: Biological Cybernetics, vol. 28, pp. 167-175, 1978.
[11] B. Julesz, E. Gilbert, and J. Victor, “Visual Discrimination of Textures with Identical Third-Order Statistics,” Biological Cybernetics, vol. 31, 1978.
[12] E. Gilbert, “Random Colorings of a Lattice on Squares in the Plane,” SIAM J. Algorithms of Discrete Methods, vol. 1, pp. 152-159, 1980.
[13] J. Yellott, “Implications of Triple Correlation Uniqueness for Texture Statistics and the Julesz Conjecture,” J. Optical Soc. Am. A, vol. 10, no. 5, pp. 777-793, 1993.
[14] O. Faugeras and W. Pratt, “Decorrelation Methods of Texture Feature Extraction,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 2, no. 4, pp. 323-332, July 1980.
[15] M. Silverman, D. Grosof, R. DeValois, and S. Elfar, “Spatial-Frequency Organization in Primate Striate Cortex,” Proc. Nat'l Academy of Sciences of the USA, 1989.
[16] C. Chubb and M.S. Landy, “Orthogonal Distribution Analysis: A New Approach to the Study of Texture Perception,” Computational Models of Visual Processing, M.S. Landy, ed., 1991.
[17] J.R. Bergen and E.H. Adelson, “Theories of Visual Texture,” Spatial Vision, D. Regan, ed., 1991.
[18] T. Randen and J.H. Husoy, “Filtering for Texture Classification: A Comparative Study,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 21, no. 4, Apr. 1999.
[19] W. Ma and B. Manjunath, “Texture Features and Learning Similarity,” Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR '96), 1996.
[20] A. Bovic, M. Clark, and W. Geisler, “Multichannel Texture Analysis Using Localized Spatial Filters,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, no. 1, Jan. 1990.
[21] S.G. Mallat, “A Theory for Multiresolution Signal Decomposition: The Wavelet Representation,” IEEE Trans. Pattern Analysis and Machine Intelligence, July 1989.
[22] S.C. Zhu, Y. Wu, and D. Mumford, “Filters, Random-Fields and Maximum-Entropy Frame: Towards a Unified Theory for Texture Modeling,” Int'l J. Computer Vision, vol. 27, no. 2, pp. 107-126, 1998.
[23] D.L. Ruderman, “The Statistics of Natural Images,” Network, 1994.
[24] C. Zetzsche, “Polyspectra of Natural Images,” Natural Scene Statistics Meeting, 1997.
[25] J. Huang and D. Mumford, “Statistics of Natural Images and Models,” Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR '99), 1999.
[26] D. Heeger and J Bergen, “Pyramid-Based Texture Analysis/Synthesis,” Proc. SIGGRAPH Conf. '95, 1995.
[27] S.C. Zhu, X. Liu, and Y. Wu, “Exploring Texture Ensembles by Efficient Markov Chain Monte Carlo,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 6, June 2000.
[28] A. Srivastava, X. Liu, and U. Grenander, “Universal Analytical Forms for Modeling Image Probabilities,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 9, Sept. 2002.
[29] T. Leung and J. Malik, “Representing and Recognizing the Visual Appearance of Materials Using Three-Dimensional Textons,” Int'l J. Computer Vision, Dec. 1999.
[30] K. Dana and S. Nayar, “Histogram Model for 3D Textures,” Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR '98), 1998.
[31] M. Varma and A. Zisserman, “Classifying Images of Materials: Achieving Viewpoint and Illumination Independence,” Proc. European Conf. Computer Visions, 2002.
[32] S. Konishi and A. Yuille, “Statistical Cues for Domain Specific Image Segmentation,” Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR '00), 2000.
[33] E. Hadjidemetriou, M. Grossberg, and S. Nayar, “Histogram Preserving Image Transformations,” Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR '00), 2000.
[34] E. Hadjidemetriou, M. Grossberg, and S. Nayar, “Spatial Information in Multiresolution Histograms,” Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR '01), 2001.
[35] P. Meyer, Introductory Probability and Statistical Applications, second ed. Addison Wesley, 1970.
[36] E. Candes and D. Donoho, “Ridgelets: A Key to Higher-Dimensional Intermittency?” Philosophical Trans. Royal Soc. London A, vol. 357, pp. 2495-2509, 1999.
[37] J. Starck, E. Candes, and D. Donoho, “The Curvelet Transform for Image Denoising,” IEEE Trans. Image Processing, vol. 11, pp. 670-684, 2001.
[38] N. Graham, J. Beck, and A. Sutter, “Nonlinear Processes in Spatial-Frequency Channel Models of Perceived Texture Segregation,” Vision Research, vol. 32, pp. 719-743, 1991.
[39] A. Sutter, G. Sperling, and C. Chubb, “Measuring the Spatial Frequency Selectivity of Second-Order Texture Mechanisms,” Vision Research, vol. 35, no. 7, 1995.
[40] A. Schofield and M. Georgeson, “Sensitivity to Contrast Modulation: The Spatial Frequency Dependence of Second-Order Vision,” Vision Research, vol. 43, pp. 243-259, 2003.

Index Terms:
Texture, statistical models, feature representation, moments.
Citation:
Joshua Gluckman, "Visually Distinct Patterns with Matching Subband Statistics," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, no. 2, pp. 252-264, Feb. 2005, doi:10.1109/TPAMI.2005.42
Usage of this product signifies your acceptance of the Terms of Use.