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

A sparse texture representation using local affine regions.

Svetlana Lazebnik1, Cordelia Schmid, Jean Ponce

  • 1Beckman Institute, University of Illinois, 405 N. Mathews Ave., Urbana, IL 61801, USA. slazebni@uiuc.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence
|August 27, 2005
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

CoVR-2: Automatic Data Construction for Composed Video Retrieval.

IEEE transactions on pattern analysis and machine intelligence·2024
Same author

Learning to Answer Visual Questions From Web Videos.

IEEE transactions on pattern analysis and machine intelligence·2022
Same author

Revisiting Image-Language Networks for Open-Ended Phrase Detection.

IEEE transactions on pattern analysis and machine intelligence·2020
Same author

Homography-Based Minimal-Case Relative Pose Estimation With Known Gravity Direction.

IEEE transactions on pattern analysis and machine intelligence·2020
Same author

Learning Semantic Correspondence Exploiting an Object-Level Prior.

IEEE transactions on pattern analysis and machine intelligence·2020
Same author

Contextual Translation Embedding for Visual Relationship Detection and Scene Graph Generation.

IEEE transactions on pattern analysis and machine intelligence·2020
Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

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

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

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

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

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

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

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

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

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

Learning Shape Anchors for Holistic Indoor Scene Understanding.

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

This study presents a novel texture representation for robust image recognition, even with viewpoint changes and deformations. It uses affine-invariant descriptors for accurate texture analysis and classification.

Area of Science:

  • Computer Vision
  • Image Processing
  • Pattern Recognition

Background:

  • Recognizing textured surfaces under transformations is challenging.
  • Existing methods struggle with viewpoint changes and nonrigid deformations.

Purpose of the Study:

  • Introduce a robust texture representation for image recognition.
  • Improve accuracy across various transformations like viewpoint changes and deformations.

Main Methods:

  • Extract sparse affine Harris and Laplacian regions as texture elements.
  • Utilize shape normalization and compute novel spin image and RIFT descriptors.
  • Employ elliptical shape as an additional feature when affine invariance is not needed.

Main Results:

Related Experiment Videos

  • Demonstrated effectiveness in texture retrieval and classification tasks.
  • Evaluated using the Brodatz database and a diverse collection of 1,000 textured surface images.
  • Achieved robust recognition under a wide range of transformations.

Conclusions:

  • The proposed texture representation is effective for recognizing textured surfaces.
  • The method shows strong performance across various real-world conditions.
  • Offers a significant advancement in texture analysis and image recognition.