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

Template matching based object recognition with unknown geometric parameters.

Roger M Dufour1, Eric L Miller, Nikolas P Galatsanos

  • 1MIT Lincoln Lab., Lexington, MA 02420-9185, USA. dufour@ll.mit.edu

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|February 6, 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

PET/CT imaging of tuberculosis lung lesions in marmosets treated with different drug regimens aligns with human clinical outcomes.

Science translational medicine·2026
Same author

Multi-modal label-free imaging of cellular metabolism and oxidative stress in 3D brain tissue models.

Communications biology·2025
Same author

Salivary Biosensing Opportunities for Predicting Cognitive and Physical Human Performance.

Biosensors·2025
Same author

Beyond boundaries: a location-based toolkit for quantifying group dynamics in diverse contexts.

Cognitive research: principles and implications·2025
Same author

Corrigendum: An updated catalogue of diverse type II polyketide synthase biosynthetic gene clusters captured from large-scale nucleotide databases.

Microbial genomics·2025
Same author

Movement Sensing Opportunities for Monitoring Dynamic Cognitive States.

Sensors (Basel, Switzerland)·2024
Same journal

Hyperbolic Cycle Alignment for Infrared-Visible Image Fusion.

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

Learning Gaze Synthesizer via 3D-eye Controlled Diffusion and Cross-domain Feature Alignment.

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

Underlying Semantic Diffusion for Effective and Efficient In-Context Learning.

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

DiffRES: Unleashing Text-to-Image Diffusion Models for Generative Referring Expression Segmentation without Information Leakage.

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

Location Matters: Frequency-Spatial Dual Space Adaptation for Cross-Domain Few-Shot Segmentation.

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

BayeTopo: Bayesian-based Topology-guided Learning for Vascular Imaging Segmentation.

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

This study introduces a novel image object localization method robust to unknown size and rotation. By using smooth template approximations, it overcomes local minima issues in traditional image restoration for accurate object detection.

Area of Science:

  • Computer Vision
  • Image Processing
  • Pattern Recognition

Background:

  • Traditional image restoration methods struggle with unknown object size and rotation.
  • Existing techniques face challenges due to numerous local minima and zero-gradient areas in the likelihood surface when geometric parameters are unknown.

Purpose of the Study:

  • To develop a robust object localization method for images with unknown size and rotation.
  • To overcome the limitations of existing image restoration techniques in handling unknown geometric parameters.

Main Methods:

  • A novel approach using smooth template approximations to minimize a well-behaved likelihood surface.
  • A coarse-to-fine template library generation using a diffusion-like equation.
  • Successive minimizations utilizing the template library for accurate estimation.

Related Experiment Videos

Main Results:

  • The proposed method effectively handles unknown object size and rotation.
  • Numerical experiments confirm the approach's accuracy across a wide range of geometric parameters.
  • The coarse-to-fine strategy ensures convergence to the global minimum.

Conclusions:

  • The new image object localization technique provides accurate results despite unknown geometric parameters.
  • Smooth template approximation offers a significant improvement over traditional methods for object detection.
  • This approach enhances the reliability of image analysis in computer vision applications.