Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Recursive estimation of images using non-Gaussian autoregressive models.

S R Kadaba1, S B Gelfand, R L Kashyap

  • 1Dept. of Wireless Syst. Core Technol., Lucent Technol., Whippany, NJ 07981, USA. skadaba@lucent.com

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|February 16, 2008
PubMed
Summary

This study introduces a new recursive algorithm for estimating images modeled by non-Gaussian autoregressive (AR) processes corrupted by Gaussian noise. The method provides near minimum mean square error (MMSE) image estimation, outperforming Kalman filtering in specific scenarios.

Related Concept Videos

One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation01:24

One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation

This lesson introduces two critical methods in pharmacokinetics, the Wagner-Nelson and Loo-Riegelman methods, used for estimating the absorption rate constant (ka) for drugs administered via non-intravenous routes. The Wagner-Nelson method relates ka to the plasma concentration derived from the slope of a semilog percent unabsorbed time plot. However, it is limited to drugs with one-compartment kinetics and can be impacted by factors like gastrointestinal motility or enzymatic degradation.
On...
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A geometrical approach to polygonal dissimilarity and shape matching.

IEEE transactions on pattern analysis and machine intelligence·2012
Same author

Synthesis and estimation of random fields using long-correlation models.

IEEE transactions on pattern analysis and machine intelligence·2012
Same author

Syntactic decision rules for recognition of spoken words and phrases using a stochastic automaton.

IEEE transactions on pattern analysis and machine intelligence·2011
Same author

Optimal Choice of AR and MA Parts in Autoregressive Moving Average Models.

IEEE transactions on pattern analysis and machine intelligence·2011
Same author

Scale preserving smoothing of polygons.

IEEE transactions on pattern analysis and machine intelligence·2011
Same author

Using polygons to recognize and locate partially occluded objects.

IEEE transactions on pattern analysis and machine intelligence·2011

Area of Science:

  • Digital Image Processing
  • Statistical Signal Processing
  • Machine Learning

Background:

  • Image estimation often relies on autoregressive (AR) models, but non-Gaussian variations present challenges.
  • Recursive estimation algorithms are crucial for efficient processing of large image datasets.
  • Minimizing mean square error (MMSE) is a standard objective in image estimation.

Purpose of the Study:

  • To develop a recursive algorithm for near minimum mean square error (MMSE) estimation of images.
  • To handle images modeled by non-Gaussian autoregressive (AR) processes corrupted by white Gaussian noise.
  • To achieve efficient computation using a fixed lookahead of observations.

Main Methods:

  • Developed a suboptimal nonlinear estimator based on a simplifying approximation.

Related Experiment Videos

  • Extended a non-Gaussian AR time-series algorithm to two-dimensional image processing.
  • Utilized the reduced update Kalman filter (KF) technique to manage computational complexity.

    • Main Results:

    • The proposed algorithm effectively estimates pixels in non-Gaussian AR images.
    • Demonstrated the non-Gaussian nature of residuals in AR image models.
    • The developed algorithm shows favorable performance compared to traditional Kalman filtering techniques in non-Gaussian cases.

    Conclusions:

    • The novel recursive algorithm offers a viable solution for estimating non-Gaussian AR images.
    • The approach provides a practical and computationally efficient alternative to existing methods.
    • The findings highlight the importance of considering non-Gaussian models for accurate image estimation.