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 Concept Videos

Muscles for Facial Expressions01:14

Muscles for Facial Expressions

2.5K
The craniofacial muscles are a collection of approximately 20 thin skeletal muscles situated beneath the skin of the face and scalp. These muscles, primarily responsible for the vast array of human facial expressions, originate from the bones or fibrous structures of the skull and extend outwards to connect with the skin. While most skeletal muscles in the body are enveloped in thick fascia, facial muscles generally have a more delicate fascial covering, with the buccinator muscle being a...
2.5K
Facial Feedback Hypothesis01:24

Facial Feedback Hypothesis

234
Charles Darwin proposed that facial expressions are an evolutionary adaptation for communication. He argued that these expressions are not influenced by culture but are universal across species. For example, a snarling expression with exposed teeth signals a threat in many animals, including humans. Darwin also suggested that displaying an emotion can intensify the feeling. Smiling, for example, could enhance one's sense of happiness. This idea laid the foundation for understanding the role...
234

You might also read

Related Articles

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

Sort by
Same author

The nitric oxide donor pentaerythritol tetranitrate lowers hypertension and angiogenic imbalance in pregnancies with impaired uterine perfusion-a secondary analysis of a randomized trial.

American journal of obstetrics and gynecology·2025
Same author

Combination of App-Based Ultrasound Simulation and Conventional Learning Methods in Medical Education for Fetal Echocardiography.

Ultraschall in der Medizin (Stuttgart, Germany : 1980)·2025
Same author

[Otorhinolaryngologic diseases during lactation-which medications are compatible with breastfeeding?]

HNO·2025
Same author

[The forgotten gender - How do fathers experience an unforeseen caesarean section of their partner? An exploratory study].

Psychotherapie, Psychosomatik, medizinische Psychologie·2025
Same author

[Effects of Pregnancy on Sexuality, Physical Activity, and Well-Being of Women During Pregnancy].

Zeitschrift fur Geburtshilfe und Neonatologie·2025
Same author

Negative Effect of Intravenous Antibiotics on Survival in Patients with Triple-Negative Breast Cancer.

Cancers·2025

Related Experiment Video

Updated: Aug 28, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.0K

Novel Method for Three-Dimensional Facial Expression Recognition Using Self-Normalizing Neural Networks and Mobile

Tim Johannes Hartmann1,2, Julien Ben Joachim Hartmann3, Ulrike Friebe-Hoffmann2

  • 1Universitäts-Hautklinik Tübingen, Tübingen, Germany.

Geburtshilfe Und Frauenheilkunde
|September 16, 2022
PubMed
Summary

This study introduces a portable 3D facial scanning app using smartphones for real-time emotion recognition. The system achieved over 81% accuracy, paving the way for advanced diagnostics and health monitoring.

Keywords:
disease recognitionfacial expression recognitionfacial geometryself-normalizing neural networks

More Related Videos

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

494
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.3K

Related Experiment Videos

Last Updated: Aug 28, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.0K
Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

494
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.3K

Area of Science:

  • Computer Vision
  • Biomedical Engineering
  • Human-Computer Interaction

Background:

  • Traditional facial expression recognition often uses 2D images, limiting detail.
  • Existing 3D approaches require stationary equipment, hindering portability and scalability.
  • Portable, real-time 3D facial scanning is crucial for emotion and disease detection.

Purpose of the Study:

  • To develop a novel, portable solution for 3D facial geometry acquisition and expression recognition.
  • To enable real-time 3D facial scanning using readily available smartphones with TrueDepth cameras.
  • To categorize acquired facial geometry into distinct expressions.

Main Methods:

  • Trained a self-normalizing neural network using over 500,000 facial "snapshots".
  • Collected data from 226 medical students displaying "disappointed", "stressed", "happy", "sad", and "surprised" expressions.
  • Utilized a custom app on iPads equipped with TrueDepth cameras for data acquisition.

Main Results:

  • The neural network achieved 80.54% accuracy after training and 81.15% in testing.
  • Recall rates varied from 74.79% ("stressed") to 87.61% ("happy").
  • Precision ranged from 77.48% ("sad") to 86.87% ("surprised").

Conclusions:

  • Respectable results were achieved despite dataset challenges.
  • Future improvements in accuracy are expected with app optimizations.
  • The goal is to create an open database for expression and disease recognition, and treatment monitoring.