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 Concept Videos

IR Frequency Region: Fingerprint Region01:03

IR Frequency Region: Fingerprint Region

2.1K
IR spectra are divided into two main regions: the diagnostic region and the fingerprint region. The diagnostic region of the spectrum lies above 1500 cm−1. The absorptions resulting from single-bond vibrations of the N–H, C–H, and O–H stretch at higher wavenumbers and appear on the left side of the spectrum. The stretching absorptions of the C≡C and C≡N occur between 2100–2300 cm−1. In contrast, those arising from stretching absorptions of the...
2.1K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Sublethal Clothianidin Exposure Impairs Development, Thyroid Hormones, Locomotion and Predation in <i>Fejervarya cancrivora</i> from Rice Paddy Ecosystems.

Toxics·2026
Same author

Constraint optimization and key factor analysis based vehicle emergency braking strategy generator.

Scientific reports·2026
Same author

Volatile organic compound emission profiles of banker plants and their effects on natural enemy attraction and insect community structures in agro-ecosystems.

Pest management science·2025
Same author

Floral Volatile Organic Compound Profiles of Eco-Functional Plants Shape Plant-Insect Interactions and Their Community Structures in Wheat Agroecosystems.

Journal of agricultural and food chemistry·2025
Same author

Tissue-Resident Macrophage Membrane-Coated Nanomedicine for Targeted Tumor Therapy.

ACS nano·2025
Same author

Demagnetization Effect in a Meander-Core Orthogonal Fluxgate Sensor.

Micromachines·2021

Related Experiment Video

Updated: Mar 1, 2026

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.7K

MBR-SIFT: A mirror reflected invariant feature descriptor using a binary representation for image matching.

Mingzhe Su1, Yan Ma1, Xiangfen Zhang1

  • 1College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai, China.

Plos One
|May 26, 2017
PubMed
Summary
This summary is machine-generated.

This study introduces MBR-SIFT, a novel binary descriptor for image matching that is invariant to mirror reflections. It significantly improves matching speed and accuracy compared to traditional methods.

More Related Videos

Optical Scatter Microscopy Based on Two-Dimensional Gabor Filters
14:58

Optical Scatter Microscopy Based on Two-Dimensional Gabor Filters

Published on: June 2, 2010

10.0K
Magnetic Resonance Derived Myocardial Strain Assessment Using Feature Tracking
07:21

Magnetic Resonance Derived Myocardial Strain Assessment Using Feature Tracking

Published on: February 12, 2011

14.9K

Related Experiment Videos

Last Updated: Mar 1, 2026

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.7K
Optical Scatter Microscopy Based on Two-Dimensional Gabor Filters
14:58

Optical Scatter Microscopy Based on Two-Dimensional Gabor Filters

Published on: June 2, 2010

10.0K
Magnetic Resonance Derived Myocardial Strain Assessment Using Feature Tracking
07:21

Magnetic Resonance Derived Myocardial Strain Assessment Using Feature Tracking

Published on: February 12, 2011

14.9K

Area of Science:

  • Computer Vision
  • Image Processing
  • Machine Learning

Background:

  • Traditional Scale-Invariant Feature Transform (SIFT) is effective for image matching but computationally expensive due to Euclidean distance.
  • Binary SIFT (BSIFT) methods enhance efficiency but lack invariance to mirror reflections.
  • Existing methods struggle with mirror-reflected images, limiting their applicability.

Purpose of the Study:

  • To develop a novel binary descriptor invariant to horizontal and vertical mirror reflections for improved image matching.
  • To enhance the efficiency and accuracy of image matching algorithms.
  • To address the limitations of existing binary SIFT descriptors.

Main Methods:

  • A new descriptor, MBR-SIFT (Mirror-reflection Binary Robust SIFT), is proposed.
  • Local regions around SIFT keypoints are reorganized and transformed into an eight-direction reconstructed vector.
  • Binarization and reverse coding are applied to generate the MBR-SIFT descriptor.
  • A fast matching algorithm with a coarse-to-fine strategy and specialized similarity measures is introduced.

Main Results:

  • MBR-SIFT achieves invariance to horizontal and vertical mirror reflections.
  • The proposed method demonstrates competitive matching accuracy.
  • Significant improvements in matching speed are observed compared to traditional SIFT.
  • Experimental results on the UKBench dataset validate the effectiveness of the approach.

Conclusions:

  • MBR-SIFT effectively addresses the mirror reflection problem in binary SIFT descriptors.
  • The novel matching approach enhances both speed and accuracy.
  • MBR-SIFT offers a promising solution for efficient and robust image matching applications.