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

TEXEMS: texture exemplars for defect detection on random textured surfaces.

Xianghua Xie1, Majid Mirmehdi

  • 1Department of Computer Science, University of Bristol, MVB 2.08, Woodland Road, Bristol BS8 1UB, UK. xie@cs.bris.ac.uk

IEEE Transactions on Pattern Analysis and Machine Intelligence
|June 15, 2007
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

WildDrone: autonomous drone technology for monitoring wildlife populations.

Frontiers in robotics and AI·2026
Same author

Enhanced YOLOv11n for small object detection in UAV imagery: higher accuracy with fewer parameters.

Scientific reports·2026
Same author

An RBFNN-Based Prescribed Performance Controller for Spacecraft Proximity Operations with Collision Avoidance.

Sensors (Basel, Switzerland)·2026
Same author

Maximizing Sample Utilization in CKD Classification: Fusion and Alignment of Locally Trained Models with a Global Model.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

Your turn: At home turning angle estimation for Parkinson's disease severity assessment.

Artificial intelligence in medicine·2025
Same author

Automatic prediction of stroke treatment outcomes: latest advances and perspectives.

Biomedical engineering letters·2025
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
Same journal

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads.

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

Achieving Text-based Person Retrieval with Any Granularity.

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

This study introduces a novel method for defect detection in random color textures using unsupervised learning with minimal defect-free samples. The approach effectively identifies and locates texture anomalies by analyzing image patch variations, outperforming traditional methods.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Image Processing

Background:

  • Defect detection in random color textures is challenging due to inherent variability.
  • Existing methods often require extensive labeled data or struggle with complex textures.

Purpose of the Study:

  • To develop an unsupervised approach for detecting and localizing defects in random color textures.
  • To introduce a novel method based on textural exemplars (texems) and mixture models.
  • To evaluate the proposed method against existing techniques and assess different texem generalization schemes.

Main Methods:

  • Utilizing mixture models and multiscale analysis to extract textural exemplars (texems) from defect-free samples.
  • Applying novelty detection based on same-source similarity and data likelihood across multiple scales.

Related Experiment Videos

  • Employing logical processes to combine defect candidates for precise defect localization.

    • Main Results:

    • The proposed method demonstrates effective defect detection and localization in random color textures.
    • Comparison against a Gabor filter bank-based method shows competitive or superior performance.
    • Evaluation of texem generalization schemes provides insights into accuracy and efficiency trade-offs.

    Conclusions:

    • The presented unsupervised approach offers a robust solution for defect detection in challenging random color textures.
    • The texem-based method provides a computationally efficient and accurate alternative to traditional techniques.
    • This work contributes to advancing automated visual inspection systems in industrial applications.