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 Video

Updated: Jul 7, 2026

Superior Auto-Identification of Trypanosome Parasites by Using a Hybrid Deep-Learning Model
08:20

Superior Auto-Identification of Trypanosome Parasites by Using a Hybrid Deep-Learning Model

Published on: October 27, 2023

Algorithm for training the minimum error one-class classifier of images.

J T Guillen-Bonilla1, E Kurmyshev, E González

  • 1Departamento de Metrología Optica, Centro de Investigaciones en Optica A. C., Loma del Bosque No. 115, Col. Lomas del Campestre, C.P. 37150, León, Gto., México.

Applied Optics
|February 2, 2008
PubMed
Summary

This study introduces an optimized training algorithm for one-class classifiers, enhancing texture image classification. The method efficiently identifies the optimal slack parameter (C) to minimize classification errors, achieving near-perfect accuracy.

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

Comparative efficacy and side effects of the treatment of euthyroid goiter with levo-thyroxine or triiodothyroacetic acid.

The Journal of clinical endocrinology and metabolism·2003
Same author

[Interaction of caffeine with basic nucleic acids my a molecular mechanic method].

Biofizika·2003
Same author

[Possible configuration of dimers of Gua-Cyt bases. Computation by molecular mechanic models and density functional theory].

Biofizika·2003
Same author

Methodologies for determining capture efficiencies in surface treatment tanks.

AIHA journal : a journal for the science of occupational and environmental health and safety·2003
Same author

Results of kidney transplantation in recipients over 70 years of age: experience at a single center.

Transplantation proceedings·2003
Same author

Helical computed tomography angiography is the most efficient test to assess vascular calcifications in the iliac arterial sector in renal transplant candidates.

Transplantation proceedings·2003

Area of Science:

  • Computer Vision
  • Machine Learning
  • Pattern Recognition

Background:

  • One-class classification is crucial for anomaly detection and image analysis.
  • Optimizing classifier parameters, such as the slack parameter (C), is essential for performance.
  • Existing methods may not effectively balance classifier selectivity and error minimization.

Purpose of the Study:

  • To propose a novel training algorithm for one-class classifiers.
  • To determine the optimal slack parameter (C) for minimizing classification error.
  • To enhance the classification accuracy of texture images.

Main Methods:

  • Developed a training algorithm to find the optimal slack parameter (C) for one-class classifiers.
  • Employed a coordinated clusters representation for image data.

Related Experiment Videos

Last Updated: Jul 7, 2026

Superior Auto-Identification of Trypanosome Parasites by Using a Hybrid Deep-Learning Model
08:20

Superior Auto-Identification of Trypanosome Parasites by Using a Hybrid Deep-Learning Model

Published on: October 27, 2023

  • Computed misclassification rates across a range of C values using training samples.
  • Identified the optimal C (C(opt)) that minimized training set misclassification.

    • Main Results:

    • The proposed algorithm successfully identified an optimal slack parameter (C(opt)).
    • The optimized one-class classifier demonstrated high classification efficiency on texture images.
    • Experimental results showed classification efficiency approaching or reaching 100%.

    Conclusions:

    • The proposed training algorithm effectively optimizes one-class classifiers for improved performance.
    • Optimal slack parameter selection is critical for achieving high classification accuracy in texture image analysis.
    • The method offers a robust approach for enhancing one-class classification tasks.