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

Scale Invariant and Noise Robust Interest Points With Shearlets.

Miguel A Duval-Poo, Nicoletta Noceti, Francesca Odone

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |March 31, 2017
    PubMed
    Summary

    This study introduces a novel shearlet-based blob detector and keypoint descriptor. The new method excels at identifying blob-like features in noisy and compressed images, outperforming existing algorithms.

    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

    Video-based 2D markerless gait analysis in people with multiple sclerosis.

    Multiple sclerosis and related disorders·2026
    Same author

    Video-based computational analysis of spontaneous movements in preterm infants: A longitudinal neuromotor assessment.

    Computer methods and programs in biomedicine·2026
    Same author

    FiloAnalyzer: a deep learning approach for cell filopodia segmentation.

    BMC bioinformatics·2026
    Same author

    SpaceTime-SonoNet: efficient classification of ultra-sound video sequences.

    Medical & biological engineering & computing·2026
    Same author

    Automated video-based differentiation of sleep-related hypermotor epilepsy and parasomnia episodes.

    NPJ digital medicine·2026
    Same author

    Video-based markerless assessment of bilateral upper limb motor activity following cervical spinal cord injury.

    Computers in biology and medicine·2025

    Area of Science:

    • Image analysis
    • Computer vision
    • Signal processing

    Background:

    • Shearlets offer a powerful framework for analyzing directional multi-scale signals.
    • They effectively enhance signal discontinuities like edges and corners, even with significant noise.
    • Blob-like features are important but challenging to detect in degraded images.

    Purpose of the Study:

    • To develop a robust blob detection and keypoint description method using shearlets.
    • To introduce a new measure for effective blob detection within the shearlet framework.
    • To evaluate the performance of the proposed method against state-of-the-art algorithms, particularly on noisy and compressed images.

    Main Methods:

    • Derivation of a novel measure for blob detection based on the shearlet transform.

    Related Experiment Videos

  • Proposal of a combined blob detector and keypoint descriptor utilizing the derived measure.
  • Evaluation of the measure's scale invariance property in the continuous domain.
  • Robustness testing against various noise types (blur, compression artifacts, Gaussian noise).

    • Main Results:

    • The proposed shearlet-based measure is highly effective for blob detection.
    • The combined detector and descriptor significantly outperform current methods on noisy and compressed images.
    • The measure demonstrates perfect scale invariance in the continuous case.
    • The algorithm shows strong robustness to diverse noise conditions and compression.

    Conclusions:

    • Shearlets provide an effective framework for detecting blob-like features in challenging image conditions.
    • The novel shearlet-based approach offers superior performance for blob detection and keypoint description in noisy and compressed images.
    • This method represents a significant advancement in robust feature detection for image analysis.