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

Improving object recognition by transforming Gabor filter responses.

M Pötzsch1, N Krüger, C von der Malsburg

  • 1Ruhr-Universität Bochum, Institut für Neuroinformatik, D-44780, Bochum, Germany.

Network (Bristol, England)
|May 1, 1996
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

Clinical outcomes of drug-coated balloon vs. second-generation drug-eluting stent for coronary in-stent restenosis.

Clinical research in cardiology : official journal of the German Cardiac Society·2025
Same author

Effectiveness, safety and quality-of-life effects of guselkumab and ustekinumab in patients with psoriasis: Week 104 results from the non-interventional, prospective, German multicentre PERSIST study.

Journal of the European Academy of Dermatology and Venereology : JEADV·2023
Same author

Prognostic impact of activin subunit inhibin beta A in gastric and esophageal adenocarcinomas.

BMC cancer·2022
Same author

Better prognosis of gastric cancer patients with high levels of tumor infiltrating lymphocytes is counteracted by PD-1 expression.

Oncoimmunology·2020
Same author

Tracheostomy, ventilation and anterior cervical surgery: Timing and Complications.

South African journal of surgery. Suid-Afrikaanse tydskrif vir chirurgie·2017
Same author

[Body contouring].

Der Hautarzt; Zeitschrift fur Dermatologie, Venerologie, und verwandte Gebiete·2015
Same journal

Enhancing IoT security: A Creative Swagger Optimization algorithm for DDoS defence.

Network (Bristol, England)·2026
Same journal

Parametric optimization for electrical discharge diamond grinding (EDDG) system using dual approach.

Network (Bristol, England)·2025
Same journal

A novel lung cancer diagnosis model using hybrid convolution (2D/3D)-based adaptive DenseUnet with attention mechanism.

Network (Bristol, England)·2025
Same journal

Hybrid optimization enabled Eff-FDMNet for Parkinson's disease detection and classification in federated learning.

Network (Bristol, England)·2025
Same journal

AI-driven plant disease detection with tailored convolutional neural network.

Network (Bristol, England)·2025
Same journal

Layer modified residual Unet++ for speech enhancement using Aquila Black widow optimizer algorithm.

Network (Bristol, England)·2025
See all related articles

This study enhances an object recognition system using Gabor wavelets. The improved system robustly handles scale, rotation, and background variations for better performance.

Area of Science:

  • Computer Vision
  • Biologically Inspired Computing
  • Pattern Recognition

Background:

  • Previous object recognition systems utilized Gabor wavelets for feature extraction.
  • Gabor wavelets offer robustness against minor distortions, rotations, and illumination changes.
  • Limitations existed in handling significant scale and rotation variations, and background complexity.

Purpose of the Study:

  • To extend a biologically motivated object recognition system.
  • To improve robustness against arbitrary in-plane rotation, scale changes, and depth rotation.
  • To enhance performance by addressing background variations.

Main Methods:

  • Employed Gabor wavelets as the fundamental feature type.
  • Implemented simple linear transformations on Gabor filter responses.

Related Experiment Videos

  • Extended the system to manage diverse image variances including scale and rotation.

    • Main Results:

    • The enhanced system demonstrates significant performance improvements.
    • Successfully addressed image variance from arbitrary in-plane rotation.
    • Effectively managed substantial scale changes and moderate depth rotations.
    • Showed improved handling of background variations.

    Conclusions:

    • The extended object recognition system exhibits superior performance.
    • Linear transformations of Gabor filter responses effectively handle complex image variations.
    • The biologically motivated approach provides a robust framework for object recognition.