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: Oct 27, 2025

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

1.1K

Multispectral Face Recognition Using Transfer Learning with Adaptation of Domain Specific Units.

Luis Lopes Chambino1,2, José Silvestre Silva2,3,4, Alexandre Bernardino1,5

  • 1Instituto Superior Técnico, Universidade de Lisboa, 1049-001 Lisbon, Portugal.

Sensors (Basel, Switzerland)
|July 20, 2021
PubMed
Summary

Related Concept Videos

Association Areas of the Cortex01:21

Association Areas of the Cortex

7.1K
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,...
7.1K

You might also read

Related Articles

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

Sort by
Same author

Training an unconstrained 6 DOF biomimetic robotic eye with deep reinforcement learning.

IEEE transactions on bio-medical engineering·2026
Same author

Development of personalized exercogs for older adults care: A feasibility and single-arm study.

International journal of clinical and health psychology : IJCHP·2026
Same author

Energy efficiency and neural control of continuous versus intermittent swimming in a fishlike robot.

Science robotics·2026
Same author

STAR-eX: A Student-Teacher Assistive Rehabilitation Exoskeleton for Post-Stroke Mirror Therapy Hand Hemiplegia.

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

Using the soft actor-critic algorithm to generate rapid eye movements with an unconstrained 6DOF biomimetic robotic eye.

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

Frame-Level Real-Time Assessment of Stroke Rehabilitation Exercises from Video-Level Labeled Data: Task-Specific vs. Foundation Models.

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

This study introduces a novel multispectral facial recognition system using deep neural networks and a skin detector for enhanced forgery detection. The proposed method achieves superior performance on benchmark datasets.

Area of Science:

  • Computer Science
  • Biometrics
  • Artificial Intelligence

Background:

  • Facial recognition systems traditionally use visible light, limiting performance in varied conditions.
  • Multispectral imaging offers enhanced robustness for facial recognition.
  • Deep learning models require adaptation for effective multispectral data processing.

Purpose of the Study:

  • To propose a novel deep learning architecture for multispectral facial recognition.
  • To develop a skin detection module for improved forgery detection in facial recognition systems.
  • To evaluate the efficacy of domain-specific transfer learning for adapting pre-trained models to multispectral data.

Main Methods:

  • A novel architecture combining multiple deep convolutional neural networks (CNNs) for multispectral facial recognition.
Keywords:
facial recognitioninfraredmultispectral imagespresentation attack detector

Related Experiment Videos

Last Updated: Oct 27, 2025

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

1.1K
  • Domain-specific transfer learning applied to RGB-pretrained deep neural networks for multispectral adaptation.
  • Development and evaluation of a skin detector module for anti-spoofing capabilities.
  • Performance assessment using Support Vector Machines (SVM) and k-nearest neighbor (KNN) classifiers on extracted embeddings.

    • Main Results:

    • The proposed domain-specific transfer learning approach effectively adapts pre-trained networks to the multispectral domain.
    • The skin detector module demonstrated effectiveness in detecting forgeries using various mask materials.
    • State-of-the-art performance achieved on the Tufts and CASIA NIR-VIS 2.0 multispectral databases.
    • Rank-1 accuracy scores of 99.7% and 99.8% were recorded on the respective datasets.

    Conclusions:

    • The novel multispectral facial recognition architecture significantly enhances identification accuracy.
    • The integration of a skin detector provides a robust solution for forgery detection.
    • The proposed methods represent a substantial advancement in the field of multispectral facial recognition.