SlideShare a Scribd company logo
Automated Prediction of
Preferences Using Facial
Expressions
David Masip, Michael S. North, Alexander Todorov, Daniel Osherson, PLOSOne
1
Automated Prediction of Preferences Using Facial Expressions
Introduction: Reading minds
Detailed problem: subtle facial expressions
• State-of-the-art
• Example
Methods
• Target phase
• Perceiver phase
• Algorithm
Results
• Hypothesis one: simple classifier
• Hypothesis two: machine learning classifier
Conclusions
Índex
2
Automated Prediction of Preferences Using Facial Expressions
1. Reading minds
Can we read the mind? The answer is NO. Not completely at least…
Our face reflects somehow our feelings, emotions, … We propose to read/predict
what people thinks about two stimuli in a very particular setting: Preferences
We explore whether computers can read and infer what humans believe in a binary
choosing scenario, and we use only subtle facial expressions and a laptop.
3
Automated Prediction of Preferences Using Facial Expressions
4
Facial expression is a powerful non verbal communication cue beyond natural language.
“The expression of the Emotions in Man and Animals”. Charles Darwin
Paul Ekman. Universality of Facial expression. 6 Universal human emotions.
“We need to give computers the capacity to read our feelings and react, in ways that
have come to seem startlingly human.” Rana El Kaliouby
1.1. Detailed problem
Automated Prediction of Preferences Using Facial Expressions
5
FACS 46 atomic movements of facial muscles.
Action Units = Building blocks of the emotions
Facial emotions = combinations of AUs
1.1. Detailed problem
Applications: We transmit more data with our expressions than with what we say.
Facial expressions predict: the result of a negotiation, the winner of a congress elections,
the election of a partner,…
GOAL: apply Computer Vision algorithms to model user preferences
in non-posed scenarios.
Automated Prediction of Preferences Using Facial Expressions
6
Which cartoon this student enjoyed the most?
Automated Prediction of Preferences Using Facial Expressions
Methods: target phase
Target phase: Students evaluate two visual stimuli. [People,
Cartoons, Animals, Paintings]
Visualization for 3 seconds in a screen (E-Prime SW)
7
Automated Prediction of Preferences Using Facial Expressions
Methods: perceiver phase
Students infer the preferences of other students from covertly
recorded videos of target’s faces.
They only see the target’s face, and guess the preference
8
Automated Prediction of Preferences Using Facial Expressions
Methods: Algorithm
Facial landmarks detection per frame
Dispersion descriptor based on temporal landmarks displacements
Model:
9
Face
Detection
Mesh
Fitting
Dynamic
Landmark
Descriptor
Classifier
Automated Prediction of Preferences Using Facial Expressions
10
Results
Hypothesis one: Maximum – minimum displacement
JESP is human accuracy
Automated Prediction of Preferences Using Facial Expressions
11
Results
Hypothesis two: apply SVM to the 66 differences between the
maximum and minimum centered displacement.
SVM: Standard Machine Learning classifier on a 132 dimensional space
Automated Prediction of Preferences Using Facial Expressions
Conclusions
Complex subtle emotion reading technology
Can we read minds from facial expression?
Yes, if we lower the expectations [Binary preference selection problem]
Applications:
- Depression monitorization
- Pain detection
- Deception detection
- Dynamically price advertising depending on how people responded to it,
- Autism
- Sony, Yahoo!, Motorola, Verizon, …
“Research in this area provides a rare point of convergence
between Computer Science and Social Psychology”
12
Automated Prediction of Preferences Using Facial Expressions
Automated Prediction of Preferences Using Facial Expressions

More Related Content

Similar to Automated Prediction of Preferences Using Facial Expressions

Artificial Intelligence And Face Detection
Artificial Intelligence And Face DetectionArtificial Intelligence And Face Detection
Artificial Intelligence And Face Detection
MuhammadAdnanBashir5
 
Review of methods and techniques on Mind Reading Computer Machine
Review of methods and techniques on Mind Reading Computer MachineReview of methods and techniques on Mind Reading Computer Machine
Review of methods and techniques on Mind Reading Computer Machine
Madhavi39
 
Final Year Project - Enhancing Virtual Learning through Emotional Agents (Doc...
Final Year Project - Enhancing Virtual Learning through Emotional Agents (Doc...Final Year Project - Enhancing Virtual Learning through Emotional Agents (Doc...
Final Year Project - Enhancing Virtual Learning through Emotional Agents (Doc...
Sana Nasar
 
Image processing
Image processingImage processing
Image processing
Vinod Gurram
 
Facial expression using 3 d animation
Facial expression using 3 d animationFacial expression using 3 d animation
Facial expression using 3 d animation
iaemedu
 
Facial expression using 3 d animation
Facial expression using 3 d animationFacial expression using 3 d animation
Facial expression using 3 d animation
iaemedu
 
Facial expression using 3 d animation
Facial expression using 3 d animationFacial expression using 3 d animation
Facial expression using 3 d animation
IAEME Publication
 
Facial expression using 3 d animation
Facial expression using 3 d animationFacial expression using 3 d animation
Facial expression using 3 d animation
iaemedu
 
1 facial expression 9 (1)
1 facial expression 9 (1)1 facial expression 9 (1)
1 facial expression 9 (1)
prjpublications
 
Final_Facial_Emotion_Detection_ppt.pdf
Final_Facial_Emotion_Detection_ppt.pdfFinal_Facial_Emotion_Detection_ppt.pdf
Final_Facial_Emotion_Detection_ppt.pdf
ankitasenapati2003
 
430634527-Final-Facial-Emotion-Detection-ppt-pdf.pdf
430634527-Final-Facial-Emotion-Detection-ppt-pdf.pdf430634527-Final-Facial-Emotion-Detection-ppt-pdf.pdf
430634527-Final-Facial-Emotion-Detection-ppt-pdf.pdf
ashimavashisth001
 
Face expression recognition using Scaled-conjugate gradient Back-Propagation ...
Face expression recognition using Scaled-conjugate gradient Back-Propagation ...Face expression recognition using Scaled-conjugate gradient Back-Propagation ...
Face expression recognition using Scaled-conjugate gradient Back-Propagation ...
IJMER
 
Real time facial expression analysis using pca
Real time facial expression analysis using pcaReal time facial expression analysis using pca
Real time facial expression analysis using pca
International Journal of Science and Research (IJSR)
 
Emotion Recognition using Image Processing
Emotion Recognition using Image ProcessingEmotion Recognition using Image Processing
Emotion Recognition using Image Processing
ijtsrd
 
Face and Eye Detection Varying Scenarios With Haar Classifier_2015
Face and Eye Detection Varying Scenarios With Haar Classifier_2015Face and Eye Detection Varying Scenarios With Haar Classifier_2015
Face and Eye Detection Varying Scenarios With Haar Classifier_2015
Showrav Mazumder
 
Research Inventy : International Journal of Engineering and Science
Research Inventy : International Journal of Engineering and ScienceResearch Inventy : International Journal of Engineering and Science
Research Inventy : International Journal of Engineering and Science
researchinventy
 
photo detection in personal photo collection
photo detection in personal photo collectionphoto detection in personal photo collection
photo detection in personal photo collection
sonalijagtap15
 
Criminal Detection System
Criminal Detection SystemCriminal Detection System
Criminal Detection System
Intrader Amit
 
Emotion intelligence
Emotion intelligenceEmotion intelligence
Emotion intelligence
BhawnaSingh351973
 
Two Level Decision for Recognition of Human Facial Expressions using Neural N...
Two Level Decision for Recognition of Human Facial Expressions using Neural N...Two Level Decision for Recognition of Human Facial Expressions using Neural N...
Two Level Decision for Recognition of Human Facial Expressions using Neural N...
IIRindia
 

Similar to Automated Prediction of Preferences Using Facial Expressions (20)

Artificial Intelligence And Face Detection
Artificial Intelligence And Face DetectionArtificial Intelligence And Face Detection
Artificial Intelligence And Face Detection
 
Review of methods and techniques on Mind Reading Computer Machine
Review of methods and techniques on Mind Reading Computer MachineReview of methods and techniques on Mind Reading Computer Machine
Review of methods and techniques on Mind Reading Computer Machine
 
Final Year Project - Enhancing Virtual Learning through Emotional Agents (Doc...
Final Year Project - Enhancing Virtual Learning through Emotional Agents (Doc...Final Year Project - Enhancing Virtual Learning through Emotional Agents (Doc...
Final Year Project - Enhancing Virtual Learning through Emotional Agents (Doc...
 
Image processing
Image processingImage processing
Image processing
 
Facial expression using 3 d animation
Facial expression using 3 d animationFacial expression using 3 d animation
Facial expression using 3 d animation
 
Facial expression using 3 d animation
Facial expression using 3 d animationFacial expression using 3 d animation
Facial expression using 3 d animation
 
Facial expression using 3 d animation
Facial expression using 3 d animationFacial expression using 3 d animation
Facial expression using 3 d animation
 
Facial expression using 3 d animation
Facial expression using 3 d animationFacial expression using 3 d animation
Facial expression using 3 d animation
 
1 facial expression 9 (1)
1 facial expression 9 (1)1 facial expression 9 (1)
1 facial expression 9 (1)
 
Final_Facial_Emotion_Detection_ppt.pdf
Final_Facial_Emotion_Detection_ppt.pdfFinal_Facial_Emotion_Detection_ppt.pdf
Final_Facial_Emotion_Detection_ppt.pdf
 
430634527-Final-Facial-Emotion-Detection-ppt-pdf.pdf
430634527-Final-Facial-Emotion-Detection-ppt-pdf.pdf430634527-Final-Facial-Emotion-Detection-ppt-pdf.pdf
430634527-Final-Facial-Emotion-Detection-ppt-pdf.pdf
 
Face expression recognition using Scaled-conjugate gradient Back-Propagation ...
Face expression recognition using Scaled-conjugate gradient Back-Propagation ...Face expression recognition using Scaled-conjugate gradient Back-Propagation ...
Face expression recognition using Scaled-conjugate gradient Back-Propagation ...
 
Real time facial expression analysis using pca
Real time facial expression analysis using pcaReal time facial expression analysis using pca
Real time facial expression analysis using pca
 
Emotion Recognition using Image Processing
Emotion Recognition using Image ProcessingEmotion Recognition using Image Processing
Emotion Recognition using Image Processing
 
Face and Eye Detection Varying Scenarios With Haar Classifier_2015
Face and Eye Detection Varying Scenarios With Haar Classifier_2015Face and Eye Detection Varying Scenarios With Haar Classifier_2015
Face and Eye Detection Varying Scenarios With Haar Classifier_2015
 
Research Inventy : International Journal of Engineering and Science
Research Inventy : International Journal of Engineering and ScienceResearch Inventy : International Journal of Engineering and Science
Research Inventy : International Journal of Engineering and Science
 
photo detection in personal photo collection
photo detection in personal photo collectionphoto detection in personal photo collection
photo detection in personal photo collection
 
Criminal Detection System
Criminal Detection SystemCriminal Detection System
Criminal Detection System
 
Emotion intelligence
Emotion intelligenceEmotion intelligence
Emotion intelligence
 
Two Level Decision for Recognition of Human Facial Expressions using Neural N...
Two Level Decision for Recognition of Human Facial Expressions using Neural N...Two Level Decision for Recognition of Human Facial Expressions using Neural N...
Two Level Decision for Recognition of Human Facial Expressions using Neural N...
 

More from UOC Universitat Oberta de Catalunya

“Global Trends and Patterns of Violent Extremism: Finding New Responses”
“Global Trends and Patterns of Violent  Extremism: Finding New Responses”“Global Trends and Patterns of Violent  Extremism: Finding New Responses”
“Global Trends and Patterns of Violent Extremism: Finding New Responses”
UOC Universitat Oberta de Catalunya
 
Irrupción de la FP en línea
Irrupción de la FP en líneaIrrupción de la FP en línea
Irrupción de la FP en línea
UOC Universitat Oberta de Catalunya
 
Irrupció de la FP en línia
Irrupció de la FP en líniaIrrupció de la FP en línia
Irrupció de la FP en línia
UOC Universitat Oberta de Catalunya
 
Mobile ensembles: The uses of mobile phones for social protest by Spain’s ind...
Mobile ensembles: The uses of mobile phones for social protest by Spain’s ind...Mobile ensembles: The uses of mobile phones for social protest by Spain’s ind...
Mobile ensembles: The uses of mobile phones for social protest by Spain’s ind...
UOC Universitat Oberta de Catalunya
 
El principio de integridad en la contratación pública. Mecanismos para la pre...
El principio de integridad en la contratación pública. Mecanismos para la pre...El principio de integridad en la contratación pública. Mecanismos para la pre...
El principio de integridad en la contratación pública. Mecanismos para la pre...
UOC Universitat Oberta de Catalunya
 
Smart contradictions: The politics of making Barcelona a Self-sufficient city
Smart contradictions: The politics of making Barcelona a Self-sufficient citySmart contradictions: The politics of making Barcelona a Self-sufficient city
Smart contradictions: The politics of making Barcelona a Self-sufficient city
UOC Universitat Oberta de Catalunya
 
Gender Stereotypes and Attitudes Towards Information and Communication Techno...
Gender Stereotypes and Attitudes Towards Information and Communication Techno...Gender Stereotypes and Attitudes Towards Information and Communication Techno...
Gender Stereotypes and Attitudes Towards Information and Communication Techno...
UOC Universitat Oberta de Catalunya
 
Co-creation and Participation as a Means of Innovation in New Media: An Analy...
Co-creation and Participation as a Means of Innovation in New Media: An Analy...Co-creation and Participation as a Means of Innovation in New Media: An Analy...
Co-creation and Participation as a Means of Innovation in New Media: An Analy...
UOC Universitat Oberta de Catalunya
 
The end of scarcity? Water desalination as the new cornucopia for Mediterrane...
The end of scarcity? Water desalination as the new cornucopia for Mediterrane...The end of scarcity? Water desalination as the new cornucopia for Mediterrane...
The end of scarcity? Water desalination as the new cornucopia for Mediterrane...
UOC Universitat Oberta de Catalunya
 
Urban Ecology Under Fire: Water Supply in Madrid During the Spanish Civil War...
Urban Ecology Under Fire: Water Supply in Madrid During the Spanish Civil War...Urban Ecology Under Fire: Water Supply in Madrid During the Spanish Civil War...
Urban Ecology Under Fire: Water Supply in Madrid During the Spanish Civil War...
UOC Universitat Oberta de Catalunya
 
Little arrangements that matter. Rethinking autonomy-enabling innovations for...
Little arrangements that matter. Rethinking autonomy-enabling innovations for...Little arrangements that matter. Rethinking autonomy-enabling innovations for...
Little arrangements that matter. Rethinking autonomy-enabling innovations for...
UOC Universitat Oberta de Catalunya
 
La construcción colaborativa de proyectos como metodología para adquirir comp...
La construcción colaborativa de proyectos como metodología para adquirir comp...La construcción colaborativa de proyectos como metodología para adquirir comp...
La construcción colaborativa de proyectos como metodología para adquirir comp...
UOC Universitat Oberta de Catalunya
 
What leads people to keep on e-learning? An empirical analysis of users’ expe...
What leads people to keep on e-learning? An empirical analysis of users’ expe...What leads people to keep on e-learning? An empirical analysis of users’ expe...
What leads people to keep on e-learning? An empirical analysis of users’ expe...
UOC Universitat Oberta de Catalunya
 
Rethinking dropout in online higher education: The case of the Universitat Ob...
Rethinking dropout in online higher education: The case of the Universitat Ob...Rethinking dropout in online higher education: The case of the Universitat Ob...
Rethinking dropout in online higher education: The case of the Universitat Ob...
UOC Universitat Oberta de Catalunya
 
Framework for preserving security and privacy in peer-to-peer content distrib...
Framework for preserving security and privacy in peer-to-peer content distrib...Framework for preserving security and privacy in peer-to-peer content distrib...
Framework for preserving security and privacy in peer-to-peer content distrib...
UOC Universitat Oberta de Catalunya
 
Routing Fleets with Multiple Driving Ranges: is it possible to use greener fl...
Routing Fleets with Multiple Driving Ranges: is it possible to use greener fl...Routing Fleets with Multiple Driving Ranges: is it possible to use greener fl...
Routing Fleets with Multiple Driving Ranges: is it possible to use greener fl...
UOC Universitat Oberta de Catalunya
 
Another look at ‘being there’ experiences in digital media: exploring connect...
Another look at ‘being there’ experiences in digital media: exploring connect...Another look at ‘being there’ experiences in digital media: exploring connect...
Another look at ‘being there’ experiences in digital media: exploring connect...
UOC Universitat Oberta de Catalunya
 
RSS and Sensor Fusion Algorithms for Indoor Location Systems on Smartphones
RSS and Sensor Fusion Algorithms for Indoor Location Systems on SmartphonesRSS and Sensor Fusion Algorithms for Indoor Location Systems on Smartphones
RSS and Sensor Fusion Algorithms for Indoor Location Systems on Smartphones
UOC Universitat Oberta de Catalunya
 
Anonymizing Graphs: Measuring Quality for Clustering
Anonymizing Graphs: Measuring Quality for ClusteringAnonymizing Graphs: Measuring Quality for Clustering
Anonymizing Graphs: Measuring Quality for Clustering
UOC Universitat Oberta de Catalunya
 
On the verification of UML/OCL class diagrams using constraint programming
On the verification of UML/OCL class diagrams using constraint programmingOn the verification of UML/OCL class diagrams using constraint programming
On the verification of UML/OCL class diagrams using constraint programming
UOC Universitat Oberta de Catalunya
 

More from UOC Universitat Oberta de Catalunya (20)

“Global Trends and Patterns of Violent Extremism: Finding New Responses”
“Global Trends and Patterns of Violent  Extremism: Finding New Responses”“Global Trends and Patterns of Violent  Extremism: Finding New Responses”
“Global Trends and Patterns of Violent Extremism: Finding New Responses”
 
Irrupción de la FP en línea
Irrupción de la FP en líneaIrrupción de la FP en línea
Irrupción de la FP en línea
 
Irrupció de la FP en línia
Irrupció de la FP en líniaIrrupció de la FP en línia
Irrupció de la FP en línia
 
Mobile ensembles: The uses of mobile phones for social protest by Spain’s ind...
Mobile ensembles: The uses of mobile phones for social protest by Spain’s ind...Mobile ensembles: The uses of mobile phones for social protest by Spain’s ind...
Mobile ensembles: The uses of mobile phones for social protest by Spain’s ind...
 
El principio de integridad en la contratación pública. Mecanismos para la pre...
El principio de integridad en la contratación pública. Mecanismos para la pre...El principio de integridad en la contratación pública. Mecanismos para la pre...
El principio de integridad en la contratación pública. Mecanismos para la pre...
 
Smart contradictions: The politics of making Barcelona a Self-sufficient city
Smart contradictions: The politics of making Barcelona a Self-sufficient citySmart contradictions: The politics of making Barcelona a Self-sufficient city
Smart contradictions: The politics of making Barcelona a Self-sufficient city
 
Gender Stereotypes and Attitudes Towards Information and Communication Techno...
Gender Stereotypes and Attitudes Towards Information and Communication Techno...Gender Stereotypes and Attitudes Towards Information and Communication Techno...
Gender Stereotypes and Attitudes Towards Information and Communication Techno...
 
Co-creation and Participation as a Means of Innovation in New Media: An Analy...
Co-creation and Participation as a Means of Innovation in New Media: An Analy...Co-creation and Participation as a Means of Innovation in New Media: An Analy...
Co-creation and Participation as a Means of Innovation in New Media: An Analy...
 
The end of scarcity? Water desalination as the new cornucopia for Mediterrane...
The end of scarcity? Water desalination as the new cornucopia for Mediterrane...The end of scarcity? Water desalination as the new cornucopia for Mediterrane...
The end of scarcity? Water desalination as the new cornucopia for Mediterrane...
 
Urban Ecology Under Fire: Water Supply in Madrid During the Spanish Civil War...
Urban Ecology Under Fire: Water Supply in Madrid During the Spanish Civil War...Urban Ecology Under Fire: Water Supply in Madrid During the Spanish Civil War...
Urban Ecology Under Fire: Water Supply in Madrid During the Spanish Civil War...
 
Little arrangements that matter. Rethinking autonomy-enabling innovations for...
Little arrangements that matter. Rethinking autonomy-enabling innovations for...Little arrangements that matter. Rethinking autonomy-enabling innovations for...
Little arrangements that matter. Rethinking autonomy-enabling innovations for...
 
La construcción colaborativa de proyectos como metodología para adquirir comp...
La construcción colaborativa de proyectos como metodología para adquirir comp...La construcción colaborativa de proyectos como metodología para adquirir comp...
La construcción colaborativa de proyectos como metodología para adquirir comp...
 
What leads people to keep on e-learning? An empirical analysis of users’ expe...
What leads people to keep on e-learning? An empirical analysis of users’ expe...What leads people to keep on e-learning? An empirical analysis of users’ expe...
What leads people to keep on e-learning? An empirical analysis of users’ expe...
 
Rethinking dropout in online higher education: The case of the Universitat Ob...
Rethinking dropout in online higher education: The case of the Universitat Ob...Rethinking dropout in online higher education: The case of the Universitat Ob...
Rethinking dropout in online higher education: The case of the Universitat Ob...
 
Framework for preserving security and privacy in peer-to-peer content distrib...
Framework for preserving security and privacy in peer-to-peer content distrib...Framework for preserving security and privacy in peer-to-peer content distrib...
Framework for preserving security and privacy in peer-to-peer content distrib...
 
Routing Fleets with Multiple Driving Ranges: is it possible to use greener fl...
Routing Fleets with Multiple Driving Ranges: is it possible to use greener fl...Routing Fleets with Multiple Driving Ranges: is it possible to use greener fl...
Routing Fleets with Multiple Driving Ranges: is it possible to use greener fl...
 
Another look at ‘being there’ experiences in digital media: exploring connect...
Another look at ‘being there’ experiences in digital media: exploring connect...Another look at ‘being there’ experiences in digital media: exploring connect...
Another look at ‘being there’ experiences in digital media: exploring connect...
 
RSS and Sensor Fusion Algorithms for Indoor Location Systems on Smartphones
RSS and Sensor Fusion Algorithms for Indoor Location Systems on SmartphonesRSS and Sensor Fusion Algorithms for Indoor Location Systems on Smartphones
RSS and Sensor Fusion Algorithms for Indoor Location Systems on Smartphones
 
Anonymizing Graphs: Measuring Quality for Clustering
Anonymizing Graphs: Measuring Quality for ClusteringAnonymizing Graphs: Measuring Quality for Clustering
Anonymizing Graphs: Measuring Quality for Clustering
 
On the verification of UML/OCL class diagrams using constraint programming
On the verification of UML/OCL class diagrams using constraint programmingOn the verification of UML/OCL class diagrams using constraint programming
On the verification of UML/OCL class diagrams using constraint programming
 

Recently uploaded

一比一原版不列颠哥伦比亚大学毕业证(UBC毕业证书)学历如何办理
一比一原版不列颠哥伦比亚大学毕业证(UBC毕业证书)学历如何办理一比一原版不列颠哥伦比亚大学毕业证(UBC毕业证书)学历如何办理
一比一原版不列颠哥伦比亚大学毕业证(UBC毕业证书)学历如何办理
bttak
 
一比一原版西三一大学毕业证(TWU毕业证书)学历如何办理
一比一原版西三一大学毕业证(TWU毕业证书)学历如何办理一比一原版西三一大学毕业证(TWU毕业证书)学历如何办理
一比一原版西三一大学毕业证(TWU毕业证书)学历如何办理
bttak
 
按照学校原版(UPenn文凭证书)宾夕法尼亚大学毕业证快速办理
按照学校原版(UPenn文凭证书)宾夕法尼亚大学毕业证快速办理按照学校原版(UPenn文凭证书)宾夕法尼亚大学毕业证快速办理
按照学校原版(UPenn文凭证书)宾夕法尼亚大学毕业证快速办理
uwoso
 
一比一原版圣托马斯大学毕业证(UST毕业证书)学历如何办理
一比一原版圣托马斯大学毕业证(UST毕业证书)学历如何办理一比一原版圣托马斯大学毕业证(UST毕业证书)学历如何办理
一比一原版圣托马斯大学毕业证(UST毕业证书)学历如何办理
bttak
 
Building a Raspberry Pi Robot with Dot NET 8, Blazor and SignalR
Building a Raspberry Pi Robot with Dot NET 8, Blazor and SignalRBuilding a Raspberry Pi Robot with Dot NET 8, Blazor and SignalR
Building a Raspberry Pi Robot with Dot NET 8, Blazor and SignalR
Peter Gallagher
 
欧洲杯体彩-欧洲杯体彩比赛投注-欧洲杯体彩比赛投注官网|【​网址​🎉ac99.net🎉​】
欧洲杯体彩-欧洲杯体彩比赛投注-欧洲杯体彩比赛投注官网|【​网址​🎉ac99.net🎉​】欧洲杯体彩-欧洲杯体彩比赛投注-欧洲杯体彩比赛投注官网|【​网址​🎉ac99.net🎉​】
欧洲杯体彩-欧洲杯体彩比赛投注-欧洲杯体彩比赛投注官网|【​网址​🎉ac99.net🎉​】
lopezkatherina914
 
欧洲杯投注-欧洲杯投注押注app-欧洲杯投注押注app官网|【​网址​🎉ac10.net🎉​】
欧洲杯投注-欧洲杯投注押注app-欧洲杯投注押注app官网|【​网址​🎉ac10.net🎉​】欧洲杯投注-欧洲杯投注押注app-欧洲杯投注押注app官网|【​网址​🎉ac10.net🎉​】
欧洲杯投注-欧洲杯投注押注app-欧洲杯投注押注app官网|【​网址​🎉ac10.net🎉​】
akrooshsaleem36
 
"IOS 18 CONTROL CENTRE REVAMP STREAMLINED IPHONE SHUTDOWN MADE EASIER"
"IOS 18 CONTROL CENTRE REVAMP STREAMLINED IPHONE SHUTDOWN MADE EASIER""IOS 18 CONTROL CENTRE REVAMP STREAMLINED IPHONE SHUTDOWN MADE EASIER"
"IOS 18 CONTROL CENTRE REVAMP STREAMLINED IPHONE SHUTDOWN MADE EASIER"
Emmanuel Onwumere
 
买(usyd毕业证书)澳洲悉尼大学毕业证研究生文凭证书原版一模一样
买(usyd毕业证书)澳洲悉尼大学毕业证研究生文凭证书原版一模一样买(usyd毕业证书)澳洲悉尼大学毕业证研究生文凭证书原版一模一样
买(usyd毕业证书)澳洲悉尼大学毕业证研究生文凭证书原版一模一样
nvoyobt
 
欧洲杯赌钱-欧洲杯赌钱冠军-欧洲杯赌钱冠军赔率|【​网址​🎉ac10.net🎉​】
欧洲杯赌钱-欧洲杯赌钱冠军-欧洲杯赌钱冠军赔率|【​网址​🎉ac10.net🎉​】欧洲杯赌钱-欧洲杯赌钱冠军-欧洲杯赌钱冠军赔率|【​网址​🎉ac10.net🎉​】
欧洲杯赌钱-欧洲杯赌钱冠军-欧洲杯赌钱冠军赔率|【​网址​🎉ac10.net🎉​】
hanniaarias53
 

Recently uploaded (10)

一比一原版不列颠哥伦比亚大学毕业证(UBC毕业证书)学历如何办理
一比一原版不列颠哥伦比亚大学毕业证(UBC毕业证书)学历如何办理一比一原版不列颠哥伦比亚大学毕业证(UBC毕业证书)学历如何办理
一比一原版不列颠哥伦比亚大学毕业证(UBC毕业证书)学历如何办理
 
一比一原版西三一大学毕业证(TWU毕业证书)学历如何办理
一比一原版西三一大学毕业证(TWU毕业证书)学历如何办理一比一原版西三一大学毕业证(TWU毕业证书)学历如何办理
一比一原版西三一大学毕业证(TWU毕业证书)学历如何办理
 
按照学校原版(UPenn文凭证书)宾夕法尼亚大学毕业证快速办理
按照学校原版(UPenn文凭证书)宾夕法尼亚大学毕业证快速办理按照学校原版(UPenn文凭证书)宾夕法尼亚大学毕业证快速办理
按照学校原版(UPenn文凭证书)宾夕法尼亚大学毕业证快速办理
 
一比一原版圣托马斯大学毕业证(UST毕业证书)学历如何办理
一比一原版圣托马斯大学毕业证(UST毕业证书)学历如何办理一比一原版圣托马斯大学毕业证(UST毕业证书)学历如何办理
一比一原版圣托马斯大学毕业证(UST毕业证书)学历如何办理
 
Building a Raspberry Pi Robot with Dot NET 8, Blazor and SignalR
Building a Raspberry Pi Robot with Dot NET 8, Blazor and SignalRBuilding a Raspberry Pi Robot with Dot NET 8, Blazor and SignalR
Building a Raspberry Pi Robot with Dot NET 8, Blazor and SignalR
 
欧洲杯体彩-欧洲杯体彩比赛投注-欧洲杯体彩比赛投注官网|【​网址​🎉ac99.net🎉​】
欧洲杯体彩-欧洲杯体彩比赛投注-欧洲杯体彩比赛投注官网|【​网址​🎉ac99.net🎉​】欧洲杯体彩-欧洲杯体彩比赛投注-欧洲杯体彩比赛投注官网|【​网址​🎉ac99.net🎉​】
欧洲杯体彩-欧洲杯体彩比赛投注-欧洲杯体彩比赛投注官网|【​网址​🎉ac99.net🎉​】
 
欧洲杯投注-欧洲杯投注押注app-欧洲杯投注押注app官网|【​网址​🎉ac10.net🎉​】
欧洲杯投注-欧洲杯投注押注app-欧洲杯投注押注app官网|【​网址​🎉ac10.net🎉​】欧洲杯投注-欧洲杯投注押注app-欧洲杯投注押注app官网|【​网址​🎉ac10.net🎉​】
欧洲杯投注-欧洲杯投注押注app-欧洲杯投注押注app官网|【​网址​🎉ac10.net🎉​】
 
"IOS 18 CONTROL CENTRE REVAMP STREAMLINED IPHONE SHUTDOWN MADE EASIER"
"IOS 18 CONTROL CENTRE REVAMP STREAMLINED IPHONE SHUTDOWN MADE EASIER""IOS 18 CONTROL CENTRE REVAMP STREAMLINED IPHONE SHUTDOWN MADE EASIER"
"IOS 18 CONTROL CENTRE REVAMP STREAMLINED IPHONE SHUTDOWN MADE EASIER"
 
买(usyd毕业证书)澳洲悉尼大学毕业证研究生文凭证书原版一模一样
买(usyd毕业证书)澳洲悉尼大学毕业证研究生文凭证书原版一模一样买(usyd毕业证书)澳洲悉尼大学毕业证研究生文凭证书原版一模一样
买(usyd毕业证书)澳洲悉尼大学毕业证研究生文凭证书原版一模一样
 
欧洲杯赌钱-欧洲杯赌钱冠军-欧洲杯赌钱冠军赔率|【​网址​🎉ac10.net🎉​】
欧洲杯赌钱-欧洲杯赌钱冠军-欧洲杯赌钱冠军赔率|【​网址​🎉ac10.net🎉​】欧洲杯赌钱-欧洲杯赌钱冠军-欧洲杯赌钱冠军赔率|【​网址​🎉ac10.net🎉​】
欧洲杯赌钱-欧洲杯赌钱冠军-欧洲杯赌钱冠军赔率|【​网址​🎉ac10.net🎉​】
 

Automated Prediction of Preferences Using Facial Expressions

  • 1. Automated Prediction of Preferences Using Facial Expressions David Masip, Michael S. North, Alexander Todorov, Daniel Osherson, PLOSOne 1 Automated Prediction of Preferences Using Facial Expressions
  • 2. Introduction: Reading minds Detailed problem: subtle facial expressions • State-of-the-art • Example Methods • Target phase • Perceiver phase • Algorithm Results • Hypothesis one: simple classifier • Hypothesis two: machine learning classifier Conclusions Índex 2 Automated Prediction of Preferences Using Facial Expressions
  • 3. 1. Reading minds Can we read the mind? The answer is NO. Not completely at least… Our face reflects somehow our feelings, emotions, … We propose to read/predict what people thinks about two stimuli in a very particular setting: Preferences We explore whether computers can read and infer what humans believe in a binary choosing scenario, and we use only subtle facial expressions and a laptop. 3 Automated Prediction of Preferences Using Facial Expressions
  • 4. 4 Facial expression is a powerful non verbal communication cue beyond natural language. “The expression of the Emotions in Man and Animals”. Charles Darwin Paul Ekman. Universality of Facial expression. 6 Universal human emotions. “We need to give computers the capacity to read our feelings and react, in ways that have come to seem startlingly human.” Rana El Kaliouby 1.1. Detailed problem Automated Prediction of Preferences Using Facial Expressions
  • 5. 5 FACS 46 atomic movements of facial muscles. Action Units = Building blocks of the emotions Facial emotions = combinations of AUs 1.1. Detailed problem Applications: We transmit more data with our expressions than with what we say. Facial expressions predict: the result of a negotiation, the winner of a congress elections, the election of a partner,… GOAL: apply Computer Vision algorithms to model user preferences in non-posed scenarios. Automated Prediction of Preferences Using Facial Expressions
  • 6. 6 Which cartoon this student enjoyed the most? Automated Prediction of Preferences Using Facial Expressions
  • 7. Methods: target phase Target phase: Students evaluate two visual stimuli. [People, Cartoons, Animals, Paintings] Visualization for 3 seconds in a screen (E-Prime SW) 7 Automated Prediction of Preferences Using Facial Expressions
  • 8. Methods: perceiver phase Students infer the preferences of other students from covertly recorded videos of target’s faces. They only see the target’s face, and guess the preference 8 Automated Prediction of Preferences Using Facial Expressions
  • 9. Methods: Algorithm Facial landmarks detection per frame Dispersion descriptor based on temporal landmarks displacements Model: 9 Face Detection Mesh Fitting Dynamic Landmark Descriptor Classifier Automated Prediction of Preferences Using Facial Expressions
  • 10. 10 Results Hypothesis one: Maximum – minimum displacement JESP is human accuracy Automated Prediction of Preferences Using Facial Expressions
  • 11. 11 Results Hypothesis two: apply SVM to the 66 differences between the maximum and minimum centered displacement. SVM: Standard Machine Learning classifier on a 132 dimensional space Automated Prediction of Preferences Using Facial Expressions
  • 12. Conclusions Complex subtle emotion reading technology Can we read minds from facial expression? Yes, if we lower the expectations [Binary preference selection problem] Applications: - Depression monitorization - Pain detection - Deception detection - Dynamically price advertising depending on how people responded to it, - Autism - Sony, Yahoo!, Motorola, Verizon, … “Research in this area provides a rare point of convergence between Computer Science and Social Psychology” 12 Automated Prediction of Preferences Using Facial Expressions