Jove
Visualize
Contact Us

Related Experiment Videos

Robust and efficient image alignment based on relative gradient matching.

Shou-Der Wei1, Shang-Hong Lai

  • 1Department of Computer Science, National Tsing-Hua University, Hsinchu, Taiwan. dr918308@cs.nthu.edu.tw

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|October 7, 2006
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

Relationship between sonography of sternocleidomastoid muscle and cervical passive range of motion in infants with congenital muscular torticollis.

Biomedical journal·2019
Same author

Learning component-level sparse representation for image and video categorization.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2013
Same author

Automatic distortion correction of endoscopic images captured with wide-angle zoom lens.

IEEE transactions on bio-medical engineering·2013
Same author

Reconstructing 3D Face Model with Associated Expression Deformation from a Single Face Image via Constructing a Low-Dimensional Expression Deformation Manifold.

IEEE transactions on pattern analysis and machine intelligence·2011
Same author

An orientation inference framework for surface reconstruction from unorganized point clouds.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2010
Same author

Compressibility-aware media retargeting with structure preserving.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2010
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
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

This study introduces a robust image alignment algorithm using relative gradient maps. The method excels in accuracy and resilience to illumination changes, outperforming traditional techniques.

Area of Science:

  • Computer Vision
  • Image Processing
  • Pattern Recognition

Background:

  • Image alignment is crucial for various applications, but conventional methods struggle with illumination variations.
  • Robust algorithms are needed to handle real-world image conditions.

Purpose of the Study:

  • To develop a novel and robust image alignment algorithm.
  • To improve accuracy and efficiency compared to existing methods, particularly under non-uniform illumination.

Main Methods:

  • A two-stage approach combining learning-based approximate pattern search and iterative energy minimization.
  • Matching of relative gradient maps derived from training data and synthesized transformed images.
  • Utilizing nearest-neighbor search for candidate pose identification and energy minimization for refinement.

Related Experiment Videos

Main Results:

  • The algorithm demonstrates robustness against non-uniform illumination variations.
  • Experimental results show superior efficiency and robustness compared to the normalized correlation method.
  • Successful validation on both simulated and real-world image datasets.

Conclusions:

  • The proposed relative gradient matching algorithm offers a robust solution for image alignment.
  • The two-stage approach effectively handles geometric transformations and illumination changes.
  • This method presents a significant advancement for image registration tasks.