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 13, 2026

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
12:27

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

Image clustering using local discriminant models and global integration.

Yi Yang1, Dong Xu, Feiping Nie

  • 1College of Computer Science, Zhejiang University, Hangzhou, Zhejiang Province 310027, P R China.

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|April 29, 2010
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

MUFOLD-DB: a processed protein structure database for protein structure prediction and analysis.

BMC genomics·2015
Same author

Advances in translational bioinformatics facilitate revealing the landscape of complex disease mechanisms.

BMC bioinformatics·2015
Same author

The I-TASSER Suite: protein structure and function prediction.

Nature methods·2014
Same author

Genome-wide expression analysis of soybean NF-Y genes reveals potential function in development and drought response.

Molecular genetics and genomics : MGG·2014
Same author

Classification of lung cancer using ensemble-based feature selection and machine learning methods.

Molecular bioSystems·2014
Same author

Resveratrol possesses protective effects in a pristane-induced lupus mouse model.

PloS one·2014

We introduce clustering using local discriminant models and global integration (LDMGI), a novel image clustering algorithm. LDMGI effectively handles nonlinear data and outperforms existing methods like normalized cut, especially when ground truth is unavailable.

Area of Science:

  • Computer Science
  • Machine Learning
  • Image Processing

Background:

  • Image clustering is crucial for organizing large datasets.
  • Existing methods like spectral clustering struggle with nonlinear data manifolds.
  • Parameter tuning is a challenge in real-world applications without ground truth.

Purpose of the Study:

  • To propose a new image clustering algorithm, LDMGI, robust to parameter variations.
  • To develop a method that effectively handles data points sampled from nonlinear manifolds.
  • To provide a unified framework integrating local and global clustering information.

Main Methods:

  • Constructing local cliques for each data point and its neighbors.
  • Employing local discriminant models inspired by the Fisher criterion.

Related Experiment Videos

Last Updated: Jun 13, 2026

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
12:27

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

  • Integrating local models via a unified objective function for global clustering.
  • Utilizing spectral relaxation and rotation to derive cluster indicators.
  • Learning a new Laplacian matrix incorporating manifold structure and local discriminant information.

    • Main Results:

    • LDMGI demonstrates effectiveness on benchmark image datasets.
    • The algorithm shows robustness to algorithmic parameters compared to normalized cut.
    • K-means and discriminative K-means are shown to be special cases of LDMGI.
    • LDMGI achieves superior performance in scenarios lacking ground truth for parameter tuning.

    Conclusions:

    • LDMGI offers an effective and robust solution for image clustering, particularly in unsupervised settings.
    • The algorithm's ability to learn a new Laplacian matrix enhances its performance on complex data.
    • LDMGI presents a promising alternative for real-world image clustering applications.