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

Edge-SIFT: discriminative binary descriptor for scalable partial-duplicate mobile search.

Shiliang Zhang1, Qi Tian, Ke Lu

  • 1Key Lab of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100080, China. slzhang@jdl.ac.cn

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|March 14, 2013
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

Intercalation-Coupled Zn<sup>2+</sup> Transfer Enables Reversible ZnS Conversion in Aqueous Zn-S Batteries.

Nano letters·2026
Same author

Dietary alanine or glycine improves feed utilization and modulates gut-liver physiological responses in largemouth bass fed a low-fishmeal diet.

Comparative biochemistry and physiology. Part B, Biochemistry & molecular biology·2026
Same author

Tuning Sulfur Reduction via Unique Radical-Mediated Solid-Liquid-Solid Pathway for High-Rate Aqueous Zn-S Batteries.

Nano letters·2026
Same author

Knockout of bsal/cel.2 results in growth retardation, reduced lipid digestion and altered energy metabolism in medaka larvae (oryzias latipes).

Functional & integrative genomics·2026
Same author

Training-Free Open-Set Domain Adaptation With Vision-Language Models.

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

DreamAssemble: Complex Multi-Object Text-to-3D Generation via Multi-Density Neural Fields.

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

Through the Looking Glass: A Dual Perspective on Weakly-Supervised Few-Shot Segmentation.

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

Mask-guided Asymmetric Contrastive and Semantic Alignment for Unsupervised Person Re-Identification.

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

Edge-SIFT, a novel binary local descriptor, enhances mobile visual search by being discriminative, efficient, and compact. It outperforms traditional methods like SIFT for accurate and fast image retrieval on mobile devices.

Area of Science:

  • Computer Vision
  • Image Processing
  • Machine Learning

Background:

  • Histogram-based local descriptors like Scale Invariant Feature Transform (SIFT) are suboptimal for large-scale mobile visual search due to computational cost and loss of spatial information.
  • Existing methods struggle with the trade-off between descriptor discriminative power, efficiency, and compactness on resource-constrained mobile platforms.

Purpose of the Study:

  • To develop a novel, highly discriminative, efficient, and compact binary local descriptor for large-scale partial duplicate visual search on mobile devices.
  • To address the limitations of histogram-based descriptors in preserving spatial clues and computational efficiency.

Main Methods:

  • Proposed Edge-SIFT descriptor extracted from binary edge maps of normalized image patches.
  • Preserves edge locations and orientations, compressing sparse binary edge maps using a boosting strategy.

Related Experiment Videos

  • Developed a fast similarity measurement and an indexing framework with online verification.

    • Main Results:

    • Edge-SIFT demonstrates superior retrieval accuracy and precision compared to Oriented BRIEF (ORB).
    • Edge-SIFT significantly outperforms SIFT in efficiency, compactness, and transmission cost.
    • The descriptor is ideal for computation-sensitive scenarios like mobile image search.

    Conclusions:

    • Edge-SIFT offers a powerful solution for accurate and efficient mobile visual search.
    • The proposed descriptor effectively balances discriminative power, computational efficiency, and representation compactness.
    • Edge-SIFT represents a significant advancement for large-scale partial duplicate visual search applications.