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

Object segmentation and labeling by learning from examples.

Yaowu Xu1, Eli Saber, A Murat Tekalp

  • 1Dept. of Electr. and Comput. Eng., Univ. of Rochester, NY 14627, USA. yaxu@ece.rochester.edu

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|February 2, 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

Padé Neurons for Efficient Neural Models.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

Regulating Modality Utilization within Multimodal Fusion Networks.

Sensors (Basel, Switzerland)·2024
Same author

End-to-End Rate-Distortion Optimized Learned Hierarchical Bi-Directional Video Compression.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2021
Same author

Optical Flow Based Co-located Reference Frame for Video Compression.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2020
Same author

Realizing a Low-Power Head-Mounted Phase-Only Holographic Display by Light-Weight Compression.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2020
Same author

Synthesis of intensity gradient and texture information for efficient three-dimensional segmentation of medical volumes.

Journal of medical imaging (Bellingham, Wash.)·2015
Same journal

Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

GoP-based Quality Enhancement on Video Compression.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Align then Tensorize: Multi-Level Consistent Anchor Graph Learning for Scalable Multi-View Clustering.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented Diffusion.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
See all related articles

This study introduces an automated system for object recognition using image segmentation and template matching. The system efficiently groups image regions into objects, enhancing retrieval speed after a learning phase.

Area of Science:

  • Computer Vision
  • Image Processing
  • Machine Learning

Background:

  • Automated object recognition is crucial for image database management.
  • Current methods often require manual feature engineering or extensive training data.
  • Efficiently grouping image segments into meaningful objects remains a challenge.

Purpose of the Study:

  • To develop an automated system for grouping low-level image segments into objects.
  • To utilize color and two-dimensional (2-D) shape matching for object identification.
  • To improve the efficiency of object retrieval in image databases.

Main Methods:

  • Employing low-level image segmentation to divide images into basic regions.
  • Utilizing color and 2-D shape matching against user-provided object templates.

Related Experiment Videos

  • Implementing a hierarchical content tree data structure to store identified objects.
  • Introducing a 'learning' phase for labeling successful object matches.

    • Main Results:

    • The system successfully groups image segments into objects based on learned templates.
    • A hierarchical content tree effectively stores object representations.
    • Significant increase in retrieval speed for learned objects was observed.
    • Effectiveness demonstrated on car and face image datasets.

    Conclusions:

    • The proposed system offers an effective method for automated object grouping and retrieval.
    • Hierarchical content trees combined with learning by color and 2-D shape matching improve database efficiency.
    • The system's learning phase allows for faster recognition of previously identified objects.