Document Detail


Bispectral analysis and model validation of texture images.
MedLine Citation:
PMID:  18290049     Owner:  NLM     Status:  In-Data-Review    
Abstract/OtherAbstract:
Statistical approaches to texture analysis and synthesis have largely relied upon random models that characterize the 2-D process in terms of its first- and second-order statistics, and therefore cannot completely capture phase properties of random fields that are non-Gaussian and/or asymmetric. In this paper, higher than second-order statistics are used to derive and implement 2-D Gaussianity, linearity, and spatial reversibility tests that validate the respective modeling assumptions. The nonredundant region of the 2-D bispectrum is correctly defined and proven. A consistent parameter estimator for nonminimum phase, asymmetric noncausal, 2-D ARMA models is derived by minimizing a quadratic error polyspectrum matching criterion. Simulations on synthetic data are performed and the results of the bispectral analysis on real textures are reported.
Authors:
T E Hall; G B Giannakis
Related Documents :
20594959 - Biologically plausible saliency mechanisms improve feedforward object recognition.
15344469 - Permutation tests for classification: towards statistical significance in image-based s...
19934529 - The family approach to assessing fit in rasch measurement.
17032289 - Computing power in case-control association studies through the use of quadratic approx...
16504059 - Statistical analysis of real-time pcr data.
25088359 - Screw-in' tendency of rotary nickel-titanium files due to design geometry.
22477769 - Pdb_redo: automated re-refinement of x-ray structure models in the pdb.
19653089 - Investigating the role of appearance-based factors in predicting sunbathing and tanning...
10698559 - Identification of pharmaceutical excipients using nir spectroscopy and simca.
Publication Detail:
Type:  Journal Article    
Journal Detail:
Title:  IEEE transactions on image processing : a publication of the IEEE Signal Processing Society     Volume:  4     ISSN:  1057-7149     ISO Abbreviation:  IEEE Trans Image Process     Publication Date:  1995  
Date Detail:
Created Date:  2008-02-21     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  9886191     Medline TA:  IEEE Trans Image Process     Country:  United States    
Other Details:
Languages:  eng     Pagination:  996-1009     Citation Subset:  -    
Affiliation:
Dept. of Electr. Eng., Virginia Univ., Charlottesville, VA.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  On some Bayesian/regularization methods for image restoration.
Next Document:  Real-time synthetic aperture sonar imaging using a parallel architecture.