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

Deformation models for image recognition.

Daniel Keysers1, Thomas Deselaers, Christian Gollan

  • 1Germany Research Center for Artificial Intelligence (DFKI GmbH), Image Understanding and Pattern Recognition Group, D-67663 Kaiserslautern, Germany. daniel.keysers@dfki.de

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

Weakly Supervised Learning with Multi-Stream CNN-LSTM-HMMs to Discover Sequential Parallelism in Sign Language Videos.

IEEE transactions on pattern analysis and machine intelligence·2019
Same author

Upper and Lower Tight Error Bounds for Feature Omission with an Extension to Context Reduction.

IEEE transactions on pattern analysis and machine intelligence·2018
Same author

Multi-Language Online Handwriting Recognition.

IEEE transactions on pattern analysis and machine intelligence·2016
Same author

Measuring the objectness of image windows.

IEEE transactions on pattern analysis and machine intelligence·2012
Same author

Latent log-linear models for handwritten digit classification.

IEEE transactions on pattern analysis and machine intelligence·2011
Same author

Does the cost function matter in Bayes decision rule?

IEEE transactions on pattern analysis and machine intelligence·2011
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 novel nonlinear image deformation model offers superior performance in image recognition tasks. This approach excels in handling local changes and variability, achieving high accuracy in digit and medical image classification.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Pattern Recognition

Background:

  • Image recognition often struggles with local variations and object variability.
  • Existing nonlinear deformation models can be complex and computationally intensive.

Purpose of the Study:

  • To evaluate different nonlinear image deformation models for image recognition.
  • To identify a model balancing implementation simplicity, computational efficiency, and performance.

Main Methods:

  • Application of various nonlinear image deformation models.
  • Experimental validation on handwritten digit recognition (MNIST) and medical image classification (ImageCLEF 2005).

Main Results:

  • One model demonstrated superior performance, simplicity, and low computational cost.

Related Experiment Videos

  • Achieved 0.54% error rate on MNIST and 12.6% on ImageCLEF medical image categorization.

    • Conclusions:

    • The selected nonlinear deformation model exhibits high generalization capacity.
    • This model is effective for diverse real-world image recognition challenges.