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

Creating Objects and Object Categories for Studying Perception and Perceptual Learning
14:38

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

Published on: November 2, 2012

Unsupervised category modeling, recognition, and segmentation in images.

Sinisa Todorovic1, Narendra Ahuja

  • 1Beckman Institute, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA. sintod@vision.ai.uiuc.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence
|November 8, 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

Multimodal Respiratory Rate Estimation From Audio and Video in Emergency Department Patients.

IEEE journal of translational engineering in health and medicine·2026
Same author

Machine learning-enabled computer vision for plant phenotyping: a primer on AI/ML and a case study on stomatal patterning.

Journal of experimental botany·2024
Same author

Estimation of Respiratory Rate from Breathing Audio.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2022
Same author

CX-ToM: Counterfactual explanations with theory-of-mind for enhancing human trust in image recognition models.

iScience·2022
Same author

Joint Image Filtering with Deep Convolutional Networks.

IEEE transactions on pattern analysis and machine intelligence·2019
Same author

Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks.

IEEE transactions on pattern analysis and machine intelligence·2018

This study introduces an unsupervised method for identifying 2D object properties and learning category models from unlabeled images. It enables robust detection, recognition, and segmentation of objects with high accuracy using minimal training data.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Pattern Recognition

Background:

  • Unsupervised learning of object categories from images presents significant challenges.
  • Existing methods often require labeled data or struggle with diverse object properties.

Purpose of the Study:

  • To develop a method for unsupervised identification of photometric, geometric, and topological properties of 2D objects.
  • To learn a region-based structural model for object categories.
  • To achieve simultaneous detection, recognition, and segmentation of objects in new images.

Main Methods:

  • Representing images as trees capturing multiscale segmentation.
  • Matching trees to extract maximally matching subtrees as category instances.
  • Fusing extracted subtrees into a canonical category model (tree-union).

More Related Videos

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

Related Experiment Videos

Last Updated: Jun 28, 2026

Creating Objects and Object Categories for Studying Perception and Perceptual Learning
14:38

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

Published on: November 2, 2012

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

  • Detecting, recognizing, and segmenting objects by matching the category model to new image segmentation trees.

    • Main Results:

    • Experimental validation on benchmark datasets demonstrates robustness.
    • High accuracy in learned category models achieved with few training examples.
    • Successful unsupervised learning without human supervision.

    Conclusions:

    • The proposed tree-matching approach effectively learns object category models from unlabeled data.
    • The method enables accurate and simultaneous object detection, recognition, and segmentation.
    • This approach offers a powerful tool for unsupervised visual category discovery.