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

Polynomial distance classifier correlation filter for pattern recognition.

Mohamed Alkanhal1, B V K Vijaya Kumar

  • 1Electrical and Computer Engineering Department, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, USA.

Applied Optics
|September 19, 2003
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Mutual Information Regularized Feature-Level Frankenstein for Discriminative Recognition.

IEEE transactions on pattern analysis and machine intelligence·2021
Same author

2<sup>16</sup> shades of gray: high bit-depth projection using light intensity control.

Optics express·2016
Same author

Zero-Aliasing Correlation Filters for Object Recognition.

IEEE transactions on pattern analysis and machine intelligence·2015
Same author

An Automatic Subject-Adaptable Heartbeat Classifier Based on Multiview Learning.

IEEE journal of biomedical and health informatics·2015
Same author

Noninvasive diabetes mellitus detection using facial block color with a sparse representation classifier.

IEEE transactions on bio-medical engineering·2014
Same author

Detecting diabetes mellitus and nonproliferative diabetic retinopathy using tongue color, texture, and geometry features.

IEEE transactions on bio-medical engineering·2013

We developed a new nonlinear classifier, the polynomial distance classifier correlation filter (PDCCF), enhancing pattern recognition. This method jointly optimizes multiple filters for improved multi-class classification in synthetic aperture radar images.

Area of Science:

  • Computer Vision
  • Signal Processing
  • Machine Learning

Background:

  • Linear classifiers like distance classifier correlation filters (DCCF) are effective but limited in handling complex patterns.
  • Existing methods may struggle with the intricate, nonlinear features present in real-world data, such as synthetic aperture radar (SAR) images.

Purpose of the Study:

  • Introduce a novel nonlinear classifier, the polynomial distance classifier correlation filter (PDCCF).
  • Extend the capabilities of linear correlation filters to incorporate nonlinear pattern characteristics.
  • Provide a unified framework for combining diverse classification filters to leverage individual strengths.

Main Methods:

  • Developed the polynomial distance classifier correlation filter (PDCCF) theory, extending linear DCCF.

Related Experiment Videos

  • Incorporated nonlinear functions of the input pattern into the filter design.
  • Jointly optimized all constituent filters within the PDCCF framework for synergistic performance.

    • Main Results:

    • Demonstrated the effectiveness of the PDCCF method with both simulated and real multi-class SAR data.
    • Showcased the advantage of the nonlinear approach over traditional linear methods in complex classification tasks.
    • Validated the framework's ability to combine filters, enhancing overall classification accuracy.

    Conclusions:

    • The PDCCF offers a significant advancement in nonlinear, shift-invariant classification.
    • The joint optimization strategy effectively integrates multiple filters for superior performance.
    • PDCCF shows strong potential for applications in advanced pattern recognition, particularly with SAR imagery.