SlideShare une entreprise Scribd logo
1  sur  28
Télécharger pour lire hors ligne
Face
recognition_
The state of the art
and how we applied it
at Finnair
• Face Detection & Tracking
• Head pose and eye-gaze estimation
• Emotion recognition
• 2D & 3D Face recognition
• Face Morphing
All with real-time performance!
Background & State of the Art_
3D Face Recognition_
Source: Ayonix.com
From face landmarks
into a 3D model and
feature vector
Terminology:
• Match Rate
• False Negative
• False Positive
• Security & Surveillance
• AI & Robotics
• Consumer behavior
• Smart Shopping
• Convenience
Business Cases_
Domain specific
problem: Human-made
Identification_
+ Interaction with another human is
natural
+ Reacting to extraordinary situations is
much easier.
- We are vulnerable to tiredness and
biases.
Fixed camera
Identification_
+ Precise, no biases or overload
+ Works 24/7
- Lacks human interaction, no room for
improvising
What has been figured
TECH
SOFTWARE
HARDWARE
Current State
Analysis_
Walk in experience
What did we do differently?
strength in pattern-based classification with
strength in making choices
O U R A P P R O A C H
0 1
An invisible
walk-paced identification
focusing on
human interaction & convenience
S E R V I C E V I S I O N
Registration
App_
Premium Passengers of Finnair will
register themselves at home using the
Android App deployed to their phones.
First digital touchpoint
Arrive to the airport_
Embedded into the normal UX of the
passenger.
Check in desk 206
interface_
The “Hands in the pocket” experience
for the platinum and gold passengers
of Finnair at the priority check in desk
Second digital touchpoint
Technical Architecture
OVERVIEW
• PoC system architecture is
separated into two clients and one
backend server
• Android application is used to
register new people to the system
• Airport Client Application is used for
detecting faces from camera stream
and sending those for recognition.
Recognize
Backend
Processes the recognitions and
stores the data
Android
Airport Client Application
• Detects faces in camera stream
• Sends facial images for recognition
• Visualizes results
• Gathers feedback from the agent
Register
How did we do?
R E S U L T S
0 2
Passenger Feedback
“It's amazing that new
technologies are being
sought and tested actively”
4.6/5
Overall experience rating
4.75/5
Ease of use of the App
4.1/5
Not worried about privacy
01_Check in
attendants
"The app is easy to use,
fast and reliable. Would like
to use it in the future,
especially if it is integrated
to our systems.”
- Tiia, Check in agent
Publicity Overview
Our proof of concept has been featured in
various travel and aviation magazines
worldwide.
Big national and international media outlets
have featured the Proof of Concept such as
AP, HS and SVD.
Ten interview requests including big
technology and aviation magazines, including
PTW, ATW and ZD NET.
One more little thing..
03
Privacy_
• GRPD: Penalties up to 4% Revenue / 20MEur
• Scope: “Personal data is any information relating to an
individual, whether it relates to his or her private, professional
or public life. It can be anything from a name, a home address,
a photo, an email address, bank details, posts on social
networking websites, medical information, or a computer’s IP
address.“ Source: European Commission press release
• Privacy by design, Consent, Encryption,
Pseudonymisation, Right to be forgotten, …
What we learnt
04
Control the illumination
(as much as you can)
Study your
environment and users
Triggers can help to
achieve “real-time”
Control the number &
quality of the images
in the database
• Registration
• Self-adjusting
Test the algorithm
Test the code
Test the UX!!
Key Insights_
•We can do this in real time, in real world environment
•You can use an app for sourcing the images, but free form facial image sourcing does not work.
•Equal illumination on both side of the face is crucial
•Minimum 3 photos with the illumination variation in the database is a requirement
•Privacy is your major concern, not your customers
•We need to compromise from zero UI approach
•If you are wearing glasses, we have a problem 
Privacy_
Who cares?
• Data controller, Data processor
• System developers?
• End users, You and me?
How to “protect” yourself and your client?
• Privacy by Design
• Know the rules
• Know what you’re doing
• Don’t store ANY data you don’t need
Thank You!

Contenu connexe

Tendances

Machine Vision – Augment not replace Humans
Machine Vision – Augment not replace HumansMachine Vision – Augment not replace Humans
Machine Vision – Augment not replace HumansQualitasTechnology
 
HCI - Group Report for Metrolink App
HCI - Group Report for Metrolink AppHCI - Group Report for Metrolink App
HCI - Group Report for Metrolink AppDarran Mottershead
 
IBM Watson in the Cognitive Era
IBM Watson in the Cognitive EraIBM Watson in the Cognitive Era
IBM Watson in the Cognitive EraSteven Miller
 
Skinner sample long form
Skinner sample long formSkinner sample long form
Skinner sample long formRob Skinner
 
Fujitsu Scanners and Hyland Software Webinar Delivering Automation In The Len...
Fujitsu Scanners and Hyland Software Webinar Delivering Automation In The Len...Fujitsu Scanners and Hyland Software Webinar Delivering Automation In The Len...
Fujitsu Scanners and Hyland Software Webinar Delivering Automation In The Len...Kevin Neal
 
HCI - Individual Report for Metrolink App
HCI - Individual Report for Metrolink AppHCI - Individual Report for Metrolink App
HCI - Individual Report for Metrolink AppDarran Mottershead
 
BSM and IT Data Access Improvement at Swiss Insurer and Turkish Mobile Carrie...
BSM and IT Data Access Improvement at Swiss Insurer and Turkish Mobile Carrie...BSM and IT Data Access Improvement at Swiss Insurer and Turkish Mobile Carrie...
BSM and IT Data Access Improvement at Swiss Insurer and Turkish Mobile Carrie...Dana Gardner
 
NEC Digital Platform - Touchless Technologies for Federal Agencies
NEC Digital Platform - Touchless Technologies for Federal AgenciesNEC Digital Platform - Touchless Technologies for Federal Agencies
NEC Digital Platform - Touchless Technologies for Federal AgenciesInteractiveNEC
 
Did you Issue Smartphones to all of your Employees? Here are Two Reasons you ...
Did you Issue Smartphones to all of your Employees? Here are Two Reasons you ...Did you Issue Smartphones to all of your Employees? Here are Two Reasons you ...
Did you Issue Smartphones to all of your Employees? Here are Two Reasons you ...Kyron Baxter
 
Remixing Mobile User Experience
Remixing Mobile User ExperienceRemixing Mobile User Experience
Remixing Mobile User ExperienceJason Mesut
 
Agile on Fire: IT Enters the New Era of 'Continuous' Everything
Agile on Fire: IT Enters the New Era of 'Continuous' EverythingAgile on Fire: IT Enters the New Era of 'Continuous' Everything
Agile on Fire: IT Enters the New Era of 'Continuous' EverythingDana Gardner
 
Don't Mobilize Your Business – Reinvent It
Don't Mobilize Your Business – Reinvent ItDon't Mobilize Your Business – Reinvent It
Don't Mobilize Your Business – Reinvent ItDMI
 
User Experience for Internet of Things
User Experience for Internet of ThingsUser Experience for Internet of Things
User Experience for Internet of ThingsCatherine Robson
 

Tendances (14)

Machine Vision – Augment not replace Humans
Machine Vision – Augment not replace HumansMachine Vision – Augment not replace Humans
Machine Vision – Augment not replace Humans
 
HCI - Group Report for Metrolink App
HCI - Group Report for Metrolink AppHCI - Group Report for Metrolink App
HCI - Group Report for Metrolink App
 
IBM Watson in the Cognitive Era
IBM Watson in the Cognitive EraIBM Watson in the Cognitive Era
IBM Watson in the Cognitive Era
 
IT
ITIT
IT
 
Skinner sample long form
Skinner sample long formSkinner sample long form
Skinner sample long form
 
Fujitsu Scanners and Hyland Software Webinar Delivering Automation In The Len...
Fujitsu Scanners and Hyland Software Webinar Delivering Automation In The Len...Fujitsu Scanners and Hyland Software Webinar Delivering Automation In The Len...
Fujitsu Scanners and Hyland Software Webinar Delivering Automation In The Len...
 
HCI - Individual Report for Metrolink App
HCI - Individual Report for Metrolink AppHCI - Individual Report for Metrolink App
HCI - Individual Report for Metrolink App
 
BSM and IT Data Access Improvement at Swiss Insurer and Turkish Mobile Carrie...
BSM and IT Data Access Improvement at Swiss Insurer and Turkish Mobile Carrie...BSM and IT Data Access Improvement at Swiss Insurer and Turkish Mobile Carrie...
BSM and IT Data Access Improvement at Swiss Insurer and Turkish Mobile Carrie...
 
NEC Digital Platform - Touchless Technologies for Federal Agencies
NEC Digital Platform - Touchless Technologies for Federal AgenciesNEC Digital Platform - Touchless Technologies for Federal Agencies
NEC Digital Platform - Touchless Technologies for Federal Agencies
 
Did you Issue Smartphones to all of your Employees? Here are Two Reasons you ...
Did you Issue Smartphones to all of your Employees? Here are Two Reasons you ...Did you Issue Smartphones to all of your Employees? Here are Two Reasons you ...
Did you Issue Smartphones to all of your Employees? Here are Two Reasons you ...
 
Remixing Mobile User Experience
Remixing Mobile User ExperienceRemixing Mobile User Experience
Remixing Mobile User Experience
 
Agile on Fire: IT Enters the New Era of 'Continuous' Everything
Agile on Fire: IT Enters the New Era of 'Continuous' EverythingAgile on Fire: IT Enters the New Era of 'Continuous' Everything
Agile on Fire: IT Enters the New Era of 'Continuous' Everything
 
Don't Mobilize Your Business – Reinvent It
Don't Mobilize Your Business – Reinvent ItDon't Mobilize Your Business – Reinvent It
Don't Mobilize Your Business – Reinvent It
 
User Experience for Internet of Things
User Experience for Internet of ThingsUser Experience for Internet of Things
User Experience for Internet of Things
 

Similaire à Markus Paasovaara: Face recognition

ABTO Software computer vision 2016
ABTO Software computer vision 2016ABTO Software computer vision 2016
ABTO Software computer vision 2016ABTO Software
 
ppt minor project.pptx
ppt minor project.pptxppt minor project.pptx
ppt minor project.pptxDakshthakur9
 
Face Recognition Technology by Rohit
Face Recognition Technology by RohitFace Recognition Technology by Rohit
Face Recognition Technology by RohitRohit Shrivastava
 
Face recognition Technology By Rohit
Face recognition Technology By RohitFace recognition Technology By Rohit
Face recognition Technology By RohitRohit Shrivastava
 
Face Recognition System
Face Recognition SystemFace Recognition System
Face Recognition SystemStudentRocks
 
Inttelix Suspect Detection System
Inttelix Suspect Detection SystemInttelix Suspect Detection System
Inttelix Suspect Detection SystemInttelix
 
Inttelix Stranger Detection System
Inttelix Stranger Detection SystemInttelix Stranger Detection System
Inttelix Stranger Detection SystemInttelix
 
Face recognition technology - BEST PPT
Face recognition technology - BEST PPTFace recognition technology - BEST PPT
Face recognition technology - BEST PPTSiddharth Modi
 
FACE RECOGNITION TECHNOLOGY
FACE RECOGNITION TECHNOLOGYFACE RECOGNITION TECHNOLOGY
FACE RECOGNITION TECHNOLOGYJASHU JASWANTH
 
Development of Real Time Face Recognition System using OpenCV
Development of Real Time Face Recognition System using OpenCVDevelopment of Real Time Face Recognition System using OpenCV
Development of Real Time Face Recognition System using OpenCVIRJET Journal
 
Face recognition
Face recognition Face recognition
Face recognition Chandan A V
 
Face Recognition Technology
Face Recognition TechnologyFace Recognition Technology
Face Recognition TechnologyShashidhar Reddy
 
facerecognitiontechnology-131025121934-phpapp01.pdf
facerecognitiontechnology-131025121934-phpapp01.pdffacerecognitiontechnology-131025121934-phpapp01.pdf
facerecognitiontechnology-131025121934-phpapp01.pdfPoooi2
 
IRJET-Human Face Detection and Identification using Deep Metric Learning
IRJET-Human Face Detection and Identification using Deep Metric LearningIRJET-Human Face Detection and Identification using Deep Metric Learning
IRJET-Human Face Detection and Identification using Deep Metric LearningIRJET Journal
 
Movie on face recognition in e attendace
Movie on face recognition in e attendaceMovie on face recognition in e attendace
Movie on face recognition in e attendacesbk50000
 
Computer Vision Presentation Artificial Intelligence (AI)
Computer Vision Presentation Artificial Intelligence (AI)Computer Vision Presentation Artificial Intelligence (AI)
Computer Vision Presentation Artificial Intelligence (AI)AshTheMidBenchers
 
Face recognition application
Face recognition applicationFace recognition application
Face recognition applicationawadhesh kumar
 
Strategies for Choosing eKYC Solutions.pdf
Strategies for Choosing eKYC Solutions.pdfStrategies for Choosing eKYC Solutions.pdf
Strategies for Choosing eKYC Solutions.pdfKMSSolutionsMarketin
 

Similaire à Markus Paasovaara: Face recognition (20)

ABTO Software computer vision 2016
ABTO Software computer vision 2016ABTO Software computer vision 2016
ABTO Software computer vision 2016
 
Face recognition
Face recognitionFace recognition
Face recognition
 
ppt minor project.pptx
ppt minor project.pptxppt minor project.pptx
ppt minor project.pptx
 
Face Recognition Technology by Rohit
Face Recognition Technology by RohitFace Recognition Technology by Rohit
Face Recognition Technology by Rohit
 
Face recognition Technology By Rohit
Face recognition Technology By RohitFace recognition Technology By Rohit
Face recognition Technology By Rohit
 
Face Recognition System
Face Recognition SystemFace Recognition System
Face Recognition System
 
Inttelix Suspect Detection System
Inttelix Suspect Detection SystemInttelix Suspect Detection System
Inttelix Suspect Detection System
 
Inttelix Stranger Detection System
Inttelix Stranger Detection SystemInttelix Stranger Detection System
Inttelix Stranger Detection System
 
Face recognition technology - BEST PPT
Face recognition technology - BEST PPTFace recognition technology - BEST PPT
Face recognition technology - BEST PPT
 
FACE RECOGNITION TECHNOLOGY
FACE RECOGNITION TECHNOLOGYFACE RECOGNITION TECHNOLOGY
FACE RECOGNITION TECHNOLOGY
 
Development of Real Time Face Recognition System using OpenCV
Development of Real Time Face Recognition System using OpenCVDevelopment of Real Time Face Recognition System using OpenCV
Development of Real Time Face Recognition System using OpenCV
 
Face recognition
Face recognition Face recognition
Face recognition
 
Face Recognition Technology
Face Recognition TechnologyFace Recognition Technology
Face Recognition Technology
 
facerecognitiontechnology-131025121934-phpapp01.pdf
facerecognitiontechnology-131025121934-phpapp01.pdffacerecognitiontechnology-131025121934-phpapp01.pdf
facerecognitiontechnology-131025121934-phpapp01.pdf
 
IRJET-Human Face Detection and Identification using Deep Metric Learning
IRJET-Human Face Detection and Identification using Deep Metric LearningIRJET-Human Face Detection and Identification using Deep Metric Learning
IRJET-Human Face Detection and Identification using Deep Metric Learning
 
Movie on face recognition in e attendace
Movie on face recognition in e attendaceMovie on face recognition in e attendace
Movie on face recognition in e attendace
 
Computer Vision Presentation Artificial Intelligence (AI)
Computer Vision Presentation Artificial Intelligence (AI)Computer Vision Presentation Artificial Intelligence (AI)
Computer Vision Presentation Artificial Intelligence (AI)
 
Face recognition application
Face recognition applicationFace recognition application
Face recognition application
 
Strategies for Choosing eKYC Solutions.pdf
Strategies for Choosing eKYC Solutions.pdfStrategies for Choosing eKYC Solutions.pdf
Strategies for Choosing eKYC Solutions.pdf
 
Face recognition
Face recognitionFace recognition
Face recognition
 

Plus de Futurice

Future of Mobility - Futurice Stockholm
Future of Mobility - Futurice StockholmFuture of Mobility - Futurice Stockholm
Future of Mobility - Futurice StockholmFuturice
 
Future of Mobility - Futurice Stockholm
Future of Mobility - Futurice StockholmFuture of Mobility - Futurice Stockholm
Future of Mobility - Futurice StockholmFuturice
 
Pepperoni – A framework for spicing up your mobile apps with React Native
Pepperoni – A framework for spicing up your mobile apps with React NativePepperoni – A framework for spicing up your mobile apps with React Native
Pepperoni – A framework for spicing up your mobile apps with React NativeFuturice
 
Pepperoni 2.0 - How to spice up your mobile apps
Pepperoni 2.0 - How to spice up your mobile apps Pepperoni 2.0 - How to spice up your mobile apps
Pepperoni 2.0 - How to spice up your mobile apps Futurice
 
Reark : a Reference Architecture for Android using RxJava
Reark : a Reference Architecture for Android using RxJavaReark : a Reference Architecture for Android using RxJava
Reark : a Reference Architecture for Android using RxJavaFuturice
 
Futurice Retail Trends 2020
Futurice Retail Trends 2020Futurice Retail Trends 2020
Futurice Retail Trends 2020Futurice
 
Winning hearts with data driven services
Winning hearts with data driven servicesWinning hearts with data driven services
Winning hearts with data driven servicesFuturice
 
Testing Without Waste - Automatic Testing
Testing Without Waste - Automatic TestingTesting Without Waste - Automatic Testing
Testing Without Waste - Automatic TestingFuturice
 
Project thinking and digital service business
Project thinking and digital service businessProject thinking and digital service business
Project thinking and digital service businessFuturice
 
Agile Software Security
Agile Software SecurityAgile Software Security
Agile Software SecurityFuturice
 

Plus de Futurice (10)

Future of Mobility - Futurice Stockholm
Future of Mobility - Futurice StockholmFuture of Mobility - Futurice Stockholm
Future of Mobility - Futurice Stockholm
 
Future of Mobility - Futurice Stockholm
Future of Mobility - Futurice StockholmFuture of Mobility - Futurice Stockholm
Future of Mobility - Futurice Stockholm
 
Pepperoni – A framework for spicing up your mobile apps with React Native
Pepperoni – A framework for spicing up your mobile apps with React NativePepperoni – A framework for spicing up your mobile apps with React Native
Pepperoni – A framework for spicing up your mobile apps with React Native
 
Pepperoni 2.0 - How to spice up your mobile apps
Pepperoni 2.0 - How to spice up your mobile apps Pepperoni 2.0 - How to spice up your mobile apps
Pepperoni 2.0 - How to spice up your mobile apps
 
Reark : a Reference Architecture for Android using RxJava
Reark : a Reference Architecture for Android using RxJavaReark : a Reference Architecture for Android using RxJava
Reark : a Reference Architecture for Android using RxJava
 
Futurice Retail Trends 2020
Futurice Retail Trends 2020Futurice Retail Trends 2020
Futurice Retail Trends 2020
 
Winning hearts with data driven services
Winning hearts with data driven servicesWinning hearts with data driven services
Winning hearts with data driven services
 
Testing Without Waste - Automatic Testing
Testing Without Waste - Automatic TestingTesting Without Waste - Automatic Testing
Testing Without Waste - Automatic Testing
 
Project thinking and digital service business
Project thinking and digital service businessProject thinking and digital service business
Project thinking and digital service business
 
Agile Software Security
Agile Software SecurityAgile Software Security
Agile Software Security
 

Dernier

08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking MenDelhi Call girls
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 
A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024Results
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreternaman860154
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking MenDelhi Call girls
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...Martijn de Jong
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CVKhem
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUK Journal
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsJoaquim Jorge
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Miguel Araújo
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationSafe Software
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationMichael W. Hawkins
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxMalak Abu Hammad
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonAnna Loughnan Colquhoun
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityPrincipled Technologies
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfEnterprise Knowledge
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountPuma Security, LLC
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Igalia
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonetsnaman860154
 

Dernier (20)

08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CV
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptx
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path Mount
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonets
 

Markus Paasovaara: Face recognition

  • 1. Face recognition_ The state of the art and how we applied it at Finnair
  • 2.
  • 3. • Face Detection & Tracking • Head pose and eye-gaze estimation • Emotion recognition • 2D & 3D Face recognition • Face Morphing All with real-time performance! Background & State of the Art_
  • 4. 3D Face Recognition_ Source: Ayonix.com From face landmarks into a 3D model and feature vector Terminology: • Match Rate • False Negative • False Positive
  • 5. • Security & Surveillance • AI & Robotics • Consumer behavior • Smart Shopping • Convenience Business Cases_
  • 6. Domain specific problem: Human-made Identification_ + Interaction with another human is natural + Reacting to extraordinary situations is much easier. - We are vulnerable to tiredness and biases.
  • 7. Fixed camera Identification_ + Precise, no biases or overload + Works 24/7 - Lacks human interaction, no room for improvising
  • 8. What has been figured TECH SOFTWARE HARDWARE Current State Analysis_
  • 9. Walk in experience What did we do differently?
  • 10. strength in pattern-based classification with strength in making choices O U R A P P R O A C H 0 1
  • 11. An invisible walk-paced identification focusing on human interaction & convenience S E R V I C E V I S I O N
  • 12. Registration App_ Premium Passengers of Finnair will register themselves at home using the Android App deployed to their phones. First digital touchpoint
  • 13. Arrive to the airport_ Embedded into the normal UX of the passenger.
  • 14. Check in desk 206 interface_ The “Hands in the pocket” experience for the platinum and gold passengers of Finnair at the priority check in desk Second digital touchpoint
  • 15. Technical Architecture OVERVIEW • PoC system architecture is separated into two clients and one backend server • Android application is used to register new people to the system • Airport Client Application is used for detecting faces from camera stream and sending those for recognition. Recognize Backend Processes the recognitions and stores the data Android Airport Client Application • Detects faces in camera stream • Sends facial images for recognition • Visualizes results • Gathers feedback from the agent Register
  • 16. How did we do? R E S U L T S 0 2
  • 17. Passenger Feedback “It's amazing that new technologies are being sought and tested actively” 4.6/5 Overall experience rating 4.75/5 Ease of use of the App 4.1/5 Not worried about privacy
  • 18. 01_Check in attendants "The app is easy to use, fast and reliable. Would like to use it in the future, especially if it is integrated to our systems.” - Tiia, Check in agent
  • 19. Publicity Overview Our proof of concept has been featured in various travel and aviation magazines worldwide. Big national and international media outlets have featured the Proof of Concept such as AP, HS and SVD. Ten interview requests including big technology and aviation magazines, including PTW, ATW and ZD NET.
  • 20. One more little thing.. 03
  • 21. Privacy_ • GRPD: Penalties up to 4% Revenue / 20MEur • Scope: “Personal data is any information relating to an individual, whether it relates to his or her private, professional or public life. It can be anything from a name, a home address, a photo, an email address, bank details, posts on social networking websites, medical information, or a computer’s IP address.“ Source: European Commission press release • Privacy by design, Consent, Encryption, Pseudonymisation, Right to be forgotten, …
  • 23. Control the illumination (as much as you can) Study your environment and users Triggers can help to achieve “real-time”
  • 24. Control the number & quality of the images in the database • Registration • Self-adjusting
  • 25. Test the algorithm Test the code Test the UX!!
  • 26. Key Insights_ •We can do this in real time, in real world environment •You can use an app for sourcing the images, but free form facial image sourcing does not work. •Equal illumination on both side of the face is crucial •Minimum 3 photos with the illumination variation in the database is a requirement •Privacy is your major concern, not your customers •We need to compromise from zero UI approach •If you are wearing glasses, we have a problem 
  • 27. Privacy_ Who cares? • Data controller, Data processor • System developers? • End users, You and me? How to “protect” yourself and your client? • Privacy by Design • Know the rules • Know what you’re doing • Don’t store ANY data you don’t need