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 Video

Updated: May 22, 2026

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware
08:13

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware

Published on: December 25, 2017

Trainable COSFIRE filters for keypoint detection and pattern recognition.

George Azzopardi1, Nicolai Petkov

  • 1Johann Bernoulli Institute for Mathematics and Computer Science, University of Groningen, The Netherlands. g.azzopardi@rug.nl

IEEE Transactions on Pattern Analysis and Machine Intelligence
|May 16, 2012
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

IR Frequency Region: Fingerprint Region01:03

IR Frequency Region: Fingerprint Region

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 C=O, C=N, and C=C occur between 1600–1850 cm−1.
The...

You might also read

Related Articles

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

Sort by
Same author

Reply to: "On the Limitations of Computer Vision Models for Movement Disorders".

Movement disorders : official journal of the Movement Disorder Society·2026
Same author

Machine learning methods on BioVid heat pain database for pain intensity estimation.

Scientific reports·2025
Same author

Video-Based Data-Driven Models for Diagnosing Movement Disorders: Review and Future Directions.

Movement disorders : official journal of the Movement Disorder Society·2025
Same author

The coming decade of digital brain research: A vision for neuroscience at the intersection of technology and computing.

Imaging neuroscience (Cambridge, Mass.)·2025
Same author

Segmentation in large-scale cellular electron microscopy with deep learning: A literature survey.

Medical image analysis·2023
Same author

Survey of feature selection and extraction techniques for stock market prediction.

Financial innovation·2023
Same journal

TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

SWIFT: A Small-World Interaction Framework for Flow-Aware Trajectory Prediction in Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Adaptive Hardness-Driven Dictionary Distillation for Incomplete Streaming View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

A new trainable filter, Combination Of Shifted Filter Responses (COSFIRE), enhances keypoint detection by improving selectivity for shape properties. This method demonstrates high effectiveness in diverse computer vision tasks.

Area of Science:

  • Computer Vision
  • Biologically Inspired Computing

Background:

  • Keypoint detection is crucial for computer vision but existing methods lack selectivity and are sensitive to noise and contrast variations.
  • Current techniques struggle with feature shape properties, noise, and texture, limiting their robustness.

Purpose of the Study:

  • To introduce a novel trainable filter, Combination Of Shifted Filter Responses (COSFIRE), for robust keypoint detection and pattern recognition.
  • To develop a method inspired by visual cortex neurons for improved feature selectivity.

Main Methods:

  • Proposed a trainable filter (COSFIRE) configured to detect local contour patterns using a bank of Gabor filters.
  • COSFIRE filters compute responses as a weighted geometric mean of blurred and shifted Gabor filter outputs.
  • Filter configuration involves selecting Gabor channels and determining blur/shift parameters.

Related Experiment Videos

Last Updated: May 22, 2026

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware
08:13

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware

Published on: December 25, 2017

Main Results:

  • Achieved 98.50% recall and 96.09% precision in retinal vascular bifurcation detection (DRIVE dataset).
  • Demonstrated 99.48% correct classification for handwritten digit recognition (MNIST dataset).
  • Reached 100% recall and precision in traffic sign detection and recognition within complex scenes.

Conclusions:

  • COSFIRE filters are simple, easy to implement, and versatile for keypoint detection.
  • The proposed method shows high effectiveness and robustness in practical computer vision applications.
  • COSFIRE filters offer a powerful tool for various pattern recognition tasks.