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: Jun 28, 2026

Image Recognition and Parameter Analysis of Concrete Vibration State Based on Support Vector Machine
08:27

Image Recognition and Parameter Analysis of Concrete Vibration State Based on Support Vector Machine

Published on: January 5, 2024

Simple method for high-performance digit recognition based on sparse coding.

Kai Labusch1, Erhardt Barth, Thomas Martinetz

  • 1Neuro- and Bioinformatics, University of Lübeck, D-23538 Lübeck, Germany. labusch@inb.uni-luebeck.de

IEEE Transactions on Neural Networks
|November 13, 2008
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

Do Highly Over-Parameterized Neural Networks Generalize Since Bad Solutions are Rare?

IEEE transactions on neural networks and learning systems·2025
Same author

Possible mechanisms to improve sleep spindles via closed loop stimulation during slow wave sleep: A computational study.

PloS one·2024
Same author

Artificial Intelligence in Fluorescence Lifetime Imaging Ophthalmoscopy (FLIO) Data Analysis-Toward Retinal Metabolic Diagnostics.

Diagnostics (Basel, Switzerland)·2024
Same author

Chaos analysis of the cortical boundary for the recognition of psychosis.

Journal of psychiatry & neuroscience : JPN·2023
Same author

Differential thalamocortical interactions in slow and fast spindle generation: A computational model.

PloS one·2022
Same author

Chaos analysis of the brain topology in first-episode psychosis and clinical high risk patients.

Frontiers in psychiatry·2022
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

This study introduces a novel feature extraction method for digit recognition using sparse coding and local maximum operations. The approach achieves state-of-the-art results on the MNIST benchmark, improving handwritten digit classification performance.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Pattern Recognition

Background:

  • Digit recognition is a critical task in pattern recognition.
  • Existing methods often require complex feature engineering.
  • Inspiration from vision research can lead to more effective feature extraction.

Purpose of the Study:

  • To propose a novel feature extraction method for digit recognition.
  • To leverage sparse coding and local maximum operations for improved performance.
  • To achieve state-of-the-art classification results on a benchmark dataset.

Main Methods:

  • Utilized the unsupervised Sparsenet algorithm for learning image patch representations.
  • Applied a local maximum operation to achieve local shift invariance.

Related Experiment Videos

Last Updated: Jun 28, 2026

Image Recognition and Parameter Analysis of Concrete Vibration State Based on Support Vector Machine
08:27

Image Recognition and Parameter Analysis of Concrete Vibration State Based on Support Vector Machine

Published on: January 5, 2024

  • Trained a support vector machine (SVM) classifier on the extracted features.

    • Main Results:

    • Achieved state-of-the-art classification performance on the MNIST digit recognition benchmark.
    • Demonstrated superior performance compared to Gabor wavelets and Principal Component Analysis (PCA).
    • The proposed method, despite its simplicity, yielded highly competitive results.

    Conclusions:

    • Learning sparse representations of local image patches is effective for feature extraction.
    • Combining sparse coding with local maximum operations significantly enhances digit recognition performance.
    • The proposed method offers a simple yet powerful approach for high-performance digit recognition.