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

Perceptual adaptive insensitivity for support vector machine image coding.

Gabriel Gómez-Pérez1, Gustavo Camps-Valls, Juan Gutiérrez

  • 1Department of Electrical Engineering, University of València, València, Spain. gabriel.gomez@uv.es

IEEE Transactions on Neural Networks
|December 14, 2005
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

Altered mitochondrial ultrastructure in salivary epithelial cells of patients with Sjögren's disease is associated with mitochondrial DNA release and increased activation of pattern recognition receptors: potential use of tofacitinib as therapy.

Annals of the rheumatic diseases·2026
Same author

Contrast sensitivity in multimodal large language models: A psychophysics-inspired evaluation.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

Current and Future Treatment Options for Cerebral Cavernous Malformations.

Stroke (Hoboken, N.J.)·2026
Same author

A Turing Test for artificial nets devoted to vision.

Frontiers in artificial intelligence·2026
Same author

RAID-Dataset: human responses to affine image distortions and Gaussian noise.

Scientific data·2026
Same author

Higher-Order Triadic Interactions: Insights Into the Multiscale Network Organization in Schizophrenia.

Human brain mapping·2025
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

Adaptive Support Vector Machines (SVM) improve frequency domain image compression by using a visual cortex model. This approach enhances rate-distortion performance over constant insensitivity methods.

Area of Science:

  • Digital Signal Processing
  • Machine Learning
  • Computer Vision

Background:

  • Support Vector Machine (SVM) learning was previously applied to frequency domain image compression with a constant insensitivity zone.
  • A constant insensitivity zone is suboptimal for frequency domain compression due to image statistics and human perception.
  • Prior methods made a fixed low-pass assumption by limiting Discrete Cosine Transform (DCT) coefficients during training.

Purpose of the Study:

  • To extend existing SVM-based image compression by introducing adaptive insensitivity.
  • To improve rate-distortion performance by utilizing a perception model based on the visual cortex.
  • To avoid a priori assumptions inherent in previous fixed insensitivity approaches.

Main Methods:

  • Proposed adaptive insensitivity Support Vector Machines (SVMs) for image coding.

Related Experiment Videos

  • Employed an appropriate distortion criterion based on a simple visual cortex model.
  • Trained the SVM using an accurate perception model, avoiding fixed assumptions.

    • Main Results:

    • Achieved improved rate-distortion performance compared to the original constant insensitivity SVM approach.
    • Demonstrated the effectiveness of adaptive insensitivity in frequency domain image compression.
    • Validated the benefits of using a perception model for training SVMs in image coding.

    Conclusions:

    • Adaptive insensitivity SVMs offer superior performance for frequency domain image compression.
    • Incorporating visual perception models enhances the accuracy and efficiency of image compression algorithms.
    • The proposed method overcomes limitations of fixed insensitivity zones in DCT-based image coding.