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 26, 2026

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Trainable Convolution Filters and Their Application to Face Recognition.

Ritwik Kumar1, Arunava Banerjee, Baba C Vemuri

  • 1IBM Research-Almaden, 650 Harry Road, San Jose, CA 95123, USA. rkkumar@us.ibm.com

IEEE Transactions on Pattern Analysis and Machine Intelligence
|December 7, 2011
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Association Areas of the Cortex01:21

Association Areas of the Cortex

Association areas are regions of the cerebral cortex that do not have a specific sensory or motor function. Instead, they integrate and interpret information from various sources to enable higher cognitive processes such as memory, learning, and decision-making. Some key association areas include the following:
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...

You might also read

Related Articles

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

Sort by
Same author

Clocks and Dominoes: Timing Mechanisms of Embryogenesis.

bioRxiv : the preprint server for biology·2026
Same author

Task-Specific Directions: Definition, Exploration, and Utilization in Parameter Efficient Fine-Tuning.

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

SmartEM: machine learning-guided electron microscopy.

Nature methods·2025
Same author

SynAnno: Interactive Guided Proofreading of Synaptic Annotations.

IEEE transactions on visualization and computer graphics·2025
Same author

SEAL: Spatially-resolved Embedding Analysis with Linked Imaging Data.

IEEE transactions on visualization and computer graphics·2025
Same author

EmbryoProfiler: A Visual Clinical Decision Support System for IVF.

IEEE transactions on visualization and computer graphics·2025
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 introduces Volterra kernel classifiers for image classification, particularly effective for face recognition. The novel system enhances accuracy by combining trainable filters and a boosting scheme for patch-level analysis.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Pattern Recognition

Background:

  • Image classification is a fundamental task in computer vision.
  • Existing methods often struggle with variations in lighting, pose, and expression in facial images.
  • There is a need for robust and accurate face recognition systems.

Purpose of the Study:

  • To present a novel image classification system using trainable filter ensembles called Volterra kernel classifiers.
  • To develop a method for accurate face recognition by treating images as collections of patches.
  • To outperform existing state-of-the-art methods in embedding-based face image discrimination.

Main Methods:

  • Image classification system based on Volterra kernel classifiers.
  • Treats images as overlapping patches for classification.

Related Experiment Videos

Last Updated: May 26, 2026

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

  • Employs trainable convolution filters (Volterra kernels) for patch mapping.
  • Utilizes a boosting scheme to combine classifiers for improved per-patch accuracy.
  • Aggregates patch classifications via voting for final image classification.

    • Main Results:

    • Demonstrated effectiveness of the Volterra kernel classifier system on benchmark face datasets (Yale, CMU PIE, Extended Yale B, Multi-PIE, MERL Dome).
    • Achieved superior performance compared to various state-of-the-art methods in embedding-based face image discrimination.
    • The proposed technique, termed Volterrafaces for face recognition, shows consistent outperformance.

    Conclusions:

    • The proposed Volterra kernel classifier system offers a novel and effective approach to image classification.
    • The method demonstrates significant advancements in face recognition accuracy and robustness.
    • This technique represents a promising direction for embedding-based face image discrimination methods.