SlideShare a Scribd company logo
Template designed by
Face Recognition using C#
Matteo Valoriani
mvaloriani@gmail.com
@matteovaloriani
Luigi Oliveto
luigi.oliveto@gmail.com
@luigioliveto
Matteo Valoriani
CEO of Fifth Element
Speaker and Consultant
PhD at Politecnico of Milano
Microsoft MVP
Intel Software Innovator
email: mvaloriani@gmail.com
twitter: @MatteoValoriani
linkedin: https://it.linkedin.com/in/matteovaloriani
Nice to Meet You
2
Luigi Oliveto
Developer
Co-Speaker
Master of Science at Politecnico of Milano
email: luigi.oliveto@gmail.com
twitter: @LuigiOliveto
linkedin: https://it.linkedin.com/in/luigioliveto
Nice to Meet You
3
Face Detection vs Face Recognition vs Face Identification
Face Analysis HomeMade
• OpenCV/Emgu
Face Analysis with Cloud Services
• BetaFace
• Microsoft Face API
Face Analysis with Special Camera
• Kinect
• RealSense
Conclusions
• Common Problems and Limits
Agenda
Detection vs Analysis vs Recognition
Face detection is a computer technology that
identifies human faces in digital images.
Face Detection
Facial Point DetectionFace Detection/Tracking
Face Analysis is a computer technology that
analyze human faces in digital images and
elaborate physical and emotional characteristics.
Face Analysis
Gender/Age/Race AnalysisEmotion Analysis
Facial recognition system is a computer
application for automatically identifying or
verifying a person from a digital image or a video
frame from a video source.
Face Recognition
Face Similarity/GroupingFace Verification Face Identification
Face Analysis Home Made
OpenCV/Emgu
Emgu CV is a cross platform .Net wrapper to the OpenCV image
processing library.
What is EMGU
The basic layer (layer 1)
contains function, structure
and enumeration mappings
which directly reflect those in
OpenCV.
The second layer (layer 2)
contains classes that mix in
advantanges from the .NET
world.
EMGU Architecture
To start with you need to reference 3 EMGU DLL’s.
• Emgu.CV.dll
• Emgu.CV.UI.dll
• Emgu.Util.dll
using Emgu.CV;
using Emgu.Util;
using Emgu.CV.Structure;
Create a project with EMGU
cudart64_32_16.dll
cufft64_32_16.dll
cvextern.dll
npp64_32_16.dll
opencv_calib3d220.dll
opencv_contrib220.dll
opencv_core220.dll
opencv_features2d220.dll
opencv_flann220.dll
opencv_gpu220.dll
opencv_highgui220.dll
opencv_imgproc220.dll
opencv_legacy220.dll
opencv_ml220.dll
opencv_objdetect220.dll
opencv_video220.dll
Add > Existing Item
The goal of statistical classification is to use an object's
characteristics to identify which class (or group) it belongs to.
An object's characteristics are also known as feature values and
are typically presented to the machine in a vector called a feature
vector.
Machine Learning Classifier
Supervised Learning Model
OpenCV/EmguCV uses a type of face
detector called a Haar Cascade.
The Haar Cascade is a classifier (detector)
trained on thousands of human faces.
This training data is stored in an XML file,
and is later used by the classifier during
detection.
It’s the easiest ready to use face detection
method which is supported by
OpenCV/EmguCV and has great results.
Haar Feature-based Cascade Classifier
The Fisher Classifier is a linear classifier.
A linear classifier achieves this by
making a classification decision based
on the value of a linear combination of
the characteristics.
The Fisher Classifier
demo
Smile 
Face Analysis with Cloud Services
BetaFace
http://betaface.com/
SDK for Private Cloud Configuration
WebAPI for Public Cloud
BetaFace APIs
General face info:
- faces (positions, sizes, angles)
- face landmarks locations (22 basic, 101 pro)
- cropped face images
- gender, age, ethnicity, smile, glasses, mustache and beard detection
Extended measurements:
- face and facial features shapes description
- hair and skin color
- facial hair detection
- approximate hairstyle shape
- background color and clothes color.
BetaFace - Metadata
Following functions supported:
- upload image file or submit image url
- retrieve image and face metadata, including cropped face image
- compare single faces or groups of faces and receive similarity confidence along with match
decision.
- transform face image(s) - generate averages from two or more faces, change face
expression or otherwise modify them.
- add user defined metadata tags, store user-adjusted points and face info.
BetaFace - Metadata
JSON/XML response
JSON/XML response
<FaceInfo>
<angle>3.3149</angle>
<height>78.05</height>
<image_uid>2bdcd1ad-47a6-45f8-ba74-
86c765272422</image_uid>
<points>
<PointInfo>
<name>basic eye left</name>
<type>512</type>
<x>313.82</x>
<y>48.88</y>
</PointInfo>
…
</points>
<score>4.81</score>
<tags>
<TagInfo>
<confidence>0.07</confidence>
<name>age</name>
<value>31</value>
</TagInfo>
….
< /tags >
22 Points (Basic mode)
101 Points (Advanced Mode)
Basic:
Age - approximate age value
beard - yes, no
gender - male, female
glasses - yes, no
mustache - yes, no
smile - yes, no
race - asian-middle-eastern, asian,
african-american, hispanic, white, middle
eastern, other
1. Get XML string
2. Generate XSD
• https://devutilsonline.com/xsd-xml/generate-xsd-from-xml
3. Generate C# classes
• XML Schema Definition Tool (Xsd.exe)
Create C# Classes from XML
From XML to XSD
https://msdn.microsoft.com/en-us/library/x6c1kb0s(v=vs.110).aspx
From XSD to Class
FREE:
Current public API key limits: faces search/recognition requests - no limits; new images - 500 images per day (15000 images per month);
Same image with different set of processing flags counts as new image; images in processing queue - 500; transform requests - no limits.
Freemium: 0 EUR/month 500 IMAGE /day, 0.035 EUR extra
Basic: 199 EUR/month 40000 IMAGE/month 0.025 EUR extra
Premium: 399 EUR/month 100000 IMAGE/month 0.02 EUR extra.
IMAGE – Each new image processed via UploadImage, UploadNewImage_File or UploadNewImage_Url functions.
- uploading the same image with different detection_flags counts as IMAGE.
- uploading the same image with the same set of detection_flags while previous processing results are still in cache does not count as
IMAGE.
- no restrictions on recognize, GetRecognizeInfo or GetImageInfo requests; no restrictions on number of namespaces or their size
If you like to subscribe to one of those plans send email to info@betaface.com with your details for invoice and plan you selected. We will
send you your personal API key.
Current data storage policy: Source images are removed from cache shortly after processing. Faces that have no person/namespace
assigned and corresponding image metadata usually cleaned up after 10 days (face IDs and image IDs will be invalidated).
Licensing: Free VS PRO
Online test: http://www.betafaceapi.com/demo.html#
Documentation:
http://www.betafaceapi.com/service_json.svc/help
Links
Face Analysis with Cloud Services
Project Oxford
http://www.projectoxford.ai/
Face Detection
Face Recognition
• Face Verification
• Similar Face Searching
• Automatic Face Grouping
• Person Identification
Project Oxford Services
Powered by Azure
1. Access the Project Oxford Portal https://www.projectoxford.ai, and then click
on the "Sign up" button.
2. Sign in with your Microsoft account, or Sign up for a new Azure subscription if
you don't already have one.
3. Go down the list to select an offered service such as "Face APIs" from the list,
and then click through the various windows in order to make a purchase.
4. Click on the item to view the dashboard, and at the bottom of the page, click
on the 'Manage' button to go to the 'Developer Manage Keys' page.
5. Finally, Copy or regenerate subscription keys in the page.
Get Start
demo
Smile 
Face Analysis with Special Cameras
Kinect ONE
Face Analysis with Special Cameras
Real Sense F200
demo
Smile 
Q&A
Grazie a tutti per la partecipazione
Riceverete il link per il download a slide e demo via email nei
prossimi giorni
Per contattarmi
mvaloriani@gmail.com
luigi.oliveto@gmail.com
Grazie

More Related Content

What's hot

Face Recognition System for Door Unlocking
Face Recognition System for Door UnlockingFace Recognition System for Door Unlocking
Face Recognition System for Door Unlocking
Hassan Tariq
 
Facial Recognition System
Facial Recognition SystemFacial Recognition System
Facial Recognition SystemArun ACE
 
FACE RECOGNITION ACROSS NON-UNIFORM MOTION BLUR
FACE RECOGNITION ACROSS  NON-UNIFORM MOTION BLUR FACE RECOGNITION ACROSS  NON-UNIFORM MOTION BLUR
FACE RECOGNITION ACROSS NON-UNIFORM MOTION BLUR
Koduru KrisHna
 
Pattern recognition 3d face recognition
Pattern recognition 3d face recognitionPattern recognition 3d face recognition
Pattern recognition 3d face recognition
Mazin Alwaaly
 
Face Detection and Recognition System
Face Detection and Recognition SystemFace Detection and Recognition System
Face Detection and Recognition System
Zara Tariq
 
Automated Face Recognition System for Office Door Access Control Application
Automated Face Recognition System for Office Door Access Control Application Automated Face Recognition System for Office Door Access Control Application
Automated Face Recognition System for Office Door Access Control Application
Er. Ashish Pandey
 
Face Recognition
Face RecognitionFace Recognition
Face Recognition
arvind carpenter
 
Classroom Attendance using Face Detection and Raspberry-Pi
Classroom Attendance using Face Detection and Raspberry-PiClassroom Attendance using Face Detection and Raspberry-Pi
Classroom Attendance using Face Detection and Raspberry-Pi
IRJET Journal
 
Face detection and recognition with pi
Face detection and recognition with piFace detection and recognition with pi
Face detection and recognition with pi
hetvi naik
 
Attendence management system using face detection
Attendence management system using face detectionAttendence management system using face detection
Attendence management system using face detection
Saurabh Sutone
 
Facial recognition locker for android
Facial recognition locker for androidFacial recognition locker for android
Facial recognition locker for android
konark jain
 
Face recognition system using Hidden Markov Model
Face recognition system using Hidden Markov ModelFace recognition system using Hidden Markov Model
Face recognition system using Hidden Markov Model
Charmi Chokshi
 
Face Recognition System/Technology
Face Recognition System/TechnologyFace Recognition System/Technology
Face Recognition System/Technology
RahulSingh3034
 
Face recognition and math
Face recognition and mathFace recognition and math
Face recognition and math
Kejti Cela
 
Project Face Detection
Project Face Detection Project Face Detection
Project Face Detection Abu Saleh Musa
 
Face recognition
Face recognitionFace recognition
Face recognition
Avinash Prakash
 
Facial Recognition System For Access Control
Facial Recognition System For Access ControlFacial Recognition System For Access Control
Facial Recognition System For Access Control
Md. Saddam Hossain Noyon
 
Face detection system
Face detection systemFace detection system
Face detection system
Akshay Surve
 
Pattern recognition facial recognition
Pattern recognition facial recognitionPattern recognition facial recognition
Pattern recognition facial recognition
Mazin Alwaaly
 
Facial Recognition
Facial RecognitionFacial Recognition
Facial Recognition
Pallavi Agarwal
 

What's hot (20)

Face Recognition System for Door Unlocking
Face Recognition System for Door UnlockingFace Recognition System for Door Unlocking
Face Recognition System for Door Unlocking
 
Facial Recognition System
Facial Recognition SystemFacial Recognition System
Facial Recognition System
 
FACE RECOGNITION ACROSS NON-UNIFORM MOTION BLUR
FACE RECOGNITION ACROSS  NON-UNIFORM MOTION BLUR FACE RECOGNITION ACROSS  NON-UNIFORM MOTION BLUR
FACE RECOGNITION ACROSS NON-UNIFORM MOTION BLUR
 
Pattern recognition 3d face recognition
Pattern recognition 3d face recognitionPattern recognition 3d face recognition
Pattern recognition 3d face recognition
 
Face Detection and Recognition System
Face Detection and Recognition SystemFace Detection and Recognition System
Face Detection and Recognition System
 
Automated Face Recognition System for Office Door Access Control Application
Automated Face Recognition System for Office Door Access Control Application Automated Face Recognition System for Office Door Access Control Application
Automated Face Recognition System for Office Door Access Control Application
 
Face Recognition
Face RecognitionFace Recognition
Face Recognition
 
Classroom Attendance using Face Detection and Raspberry-Pi
Classroom Attendance using Face Detection and Raspberry-PiClassroom Attendance using Face Detection and Raspberry-Pi
Classroom Attendance using Face Detection and Raspberry-Pi
 
Face detection and recognition with pi
Face detection and recognition with piFace detection and recognition with pi
Face detection and recognition with pi
 
Attendence management system using face detection
Attendence management system using face detectionAttendence management system using face detection
Attendence management system using face detection
 
Facial recognition locker for android
Facial recognition locker for androidFacial recognition locker for android
Facial recognition locker for android
 
Face recognition system using Hidden Markov Model
Face recognition system using Hidden Markov ModelFace recognition system using Hidden Markov Model
Face recognition system using Hidden Markov Model
 
Face Recognition System/Technology
Face Recognition System/TechnologyFace Recognition System/Technology
Face Recognition System/Technology
 
Face recognition and math
Face recognition and mathFace recognition and math
Face recognition and math
 
Project Face Detection
Project Face Detection Project Face Detection
Project Face Detection
 
Face recognition
Face recognitionFace recognition
Face recognition
 
Facial Recognition System For Access Control
Facial Recognition System For Access ControlFacial Recognition System For Access Control
Facial Recognition System For Access Control
 
Face detection system
Face detection systemFace detection system
Face detection system
 
Pattern recognition facial recognition
Pattern recognition facial recognitionPattern recognition facial recognition
Pattern recognition facial recognition
 
Facial Recognition
Facial RecognitionFacial Recognition
Facial Recognition
 

Similar to Face recognition

Industrial Presentaion
Industrial Presentaion Industrial Presentaion
Industrial Presentaion
Hasitha Ediriweera
 
IRJET- Face-Track: Smart Attendance System using Face Recognition
IRJET- Face-Track: Smart Attendance System using Face RecognitionIRJET- Face-Track: Smart Attendance System using Face Recognition
IRJET- Face-Track: Smart Attendance System using Face Recognition
IRJET Journal
 
A guide to Face Detection in Python.pdf
A guide to Face Detection in Python.pdfA guide to Face Detection in Python.pdf
A guide to Face Detection in Python.pdf
3sitservices IT Software Company
 
Hyf project ideas_02
Hyf project ideas_02Hyf project ideas_02
Hyf project ideas_02
KatoK1
 
Resume
ResumeResume
Profile Identification through Face Recognition
Profile Identification through Face RecognitionProfile Identification through Face Recognition
Profile Identification through Face Recognition
ijtsrd
 
Resume_Rahul_Gavade
Resume_Rahul_GavadeResume_Rahul_Gavade
Resume_Rahul_GavadeRahul Gavade
 
IRJET- Computerized Attendance System using Face Recognition
IRJET- Computerized Attendance System using Face RecognitionIRJET- Computerized Attendance System using Face Recognition
IRJET- Computerized Attendance System using Face Recognition
IRJET Journal
 
IRJET- Computerized Attendance System using Face Recognition
IRJET- Computerized Attendance System using Face RecognitionIRJET- Computerized Attendance System using Face Recognition
IRJET- Computerized Attendance System using Face Recognition
IRJET Journal
 
MongoDB.local DC 2018: Building Intelligent Apps with MongoDB & Google Cloud
MongoDB.local DC 2018: Building Intelligent Apps with MongoDB & Google CloudMongoDB.local DC 2018: Building Intelligent Apps with MongoDB & Google Cloud
MongoDB.local DC 2018: Building Intelligent Apps with MongoDB & Google Cloud
MongoDB
 
Manoj(Java Developer)_Resume
Manoj(Java Developer)_ResumeManoj(Java Developer)_Resume
Manoj(Java Developer)_ResumeVamsi Manoj
 
IRJET- Credit Card Authentication using Facial Recognition
IRJET-  	  Credit Card Authentication using Facial RecognitionIRJET-  	  Credit Card Authentication using Facial Recognition
IRJET- Credit Card Authentication using Facial Recognition
IRJET Journal
 
Building Intelligent Apps with MongoDB and Google Cloud - Jane Fine
Building Intelligent Apps with MongoDB and Google Cloud - Jane FineBuilding Intelligent Apps with MongoDB and Google Cloud - Jane Fine
Building Intelligent Apps with MongoDB and Google Cloud - Jane Fine
MongoDB
 
Online examination documentation
Online examination documentationOnline examination documentation
Online examination documentation
Wakimul Alam
 
Face Recognition Home Security System(Slide)
Face Recognition Home Security System(Slide)Face Recognition Home Security System(Slide)
Face Recognition Home Security System(Slide)
Suman Mia
 

Similar to Face recognition (20)

Industrial Presentaion
Industrial Presentaion Industrial Presentaion
Industrial Presentaion
 
Resume-Updated
Resume-Updated Resume-Updated
Resume-Updated
 
IRJET- Face-Track: Smart Attendance System using Face Recognition
IRJET- Face-Track: Smart Attendance System using Face RecognitionIRJET- Face-Track: Smart Attendance System using Face Recognition
IRJET- Face-Track: Smart Attendance System using Face Recognition
 
Resume_Sathesh Babu
Resume_Sathesh BabuResume_Sathesh Babu
Resume_Sathesh Babu
 
A guide to Face Detection in Python.pdf
A guide to Face Detection in Python.pdfA guide to Face Detection in Python.pdf
A guide to Face Detection in Python.pdf
 
Hyf project ideas_02
Hyf project ideas_02Hyf project ideas_02
Hyf project ideas_02
 
Resume
ResumeResume
Resume
 
Profile Identification through Face Recognition
Profile Identification through Face RecognitionProfile Identification through Face Recognition
Profile Identification through Face Recognition
 
Resume_Rahul_Gavade
Resume_Rahul_GavadeResume_Rahul_Gavade
Resume_Rahul_Gavade
 
IRJET- Computerized Attendance System using Face Recognition
IRJET- Computerized Attendance System using Face RecognitionIRJET- Computerized Attendance System using Face Recognition
IRJET- Computerized Attendance System using Face Recognition
 
IRJET- Computerized Attendance System using Face Recognition
IRJET- Computerized Attendance System using Face RecognitionIRJET- Computerized Attendance System using Face Recognition
IRJET- Computerized Attendance System using Face Recognition
 
MongoDB.local DC 2018: Building Intelligent Apps with MongoDB & Google Cloud
MongoDB.local DC 2018: Building Intelligent Apps with MongoDB & Google CloudMongoDB.local DC 2018: Building Intelligent Apps with MongoDB & Google Cloud
MongoDB.local DC 2018: Building Intelligent Apps with MongoDB & Google Cloud
 
Stanly_Bangalore_6_YearsExp_Dotnet -Wipro
Stanly_Bangalore_6_YearsExp_Dotnet -WiproStanly_Bangalore_6_YearsExp_Dotnet -Wipro
Stanly_Bangalore_6_YearsExp_Dotnet -Wipro
 
Senior Test Engineer
Senior Test EngineerSenior Test Engineer
Senior Test Engineer
 
Manoj(Java Developer)_Resume
Manoj(Java Developer)_ResumeManoj(Java Developer)_Resume
Manoj(Java Developer)_Resume
 
IRJET- Credit Card Authentication using Facial Recognition
IRJET-  	  Credit Card Authentication using Facial RecognitionIRJET-  	  Credit Card Authentication using Facial Recognition
IRJET- Credit Card Authentication using Facial Recognition
 
Building Intelligent Apps with MongoDB and Google Cloud - Jane Fine
Building Intelligent Apps with MongoDB and Google Cloud - Jane FineBuilding Intelligent Apps with MongoDB and Google Cloud - Jane Fine
Building Intelligent Apps with MongoDB and Google Cloud - Jane Fine
 
Online examination documentation
Online examination documentationOnline examination documentation
Online examination documentation
 
Face Recognition Home Security System(Slide)
Face Recognition Home Security System(Slide)Face Recognition Home Security System(Slide)
Face Recognition Home Security System(Slide)
 
Resume
ResumeResume
Resume
 

More from Matteo Valoriani

Immerge yourself in a new Reality
Immerge yourself in a new RealityImmerge yourself in a new Reality
Immerge yourself in a new Reality
Matteo Valoriani
 
How Augment your Reality: Different perspective on the Reality / Virtuality C...
How Augment your Reality: Different perspective on the Reality / Virtuality C...How Augment your Reality: Different perspective on the Reality / Virtuality C...
How Augment your Reality: Different perspective on the Reality / Virtuality C...
Matteo Valoriani
 
Hour ofcode
Hour ofcodeHour ofcode
Hour ofcode
Matteo Valoriani
 
Debug, Analyze and Optimize Games with Intel Tools
Debug, Analyze and Optimize Games with Intel Tools Debug, Analyze and Optimize Games with Intel Tools
Debug, Analyze and Optimize Games with Intel Tools
Matteo Valoriani
 
More Personal Computing: Windows 10, Kinect and Wearables
More Personal Computing: Windows 10, Kinect and WearablesMore Personal Computing: Windows 10, Kinect and Wearables
More Personal Computing: Windows 10, Kinect and Wearables
Matteo Valoriani
 
Introduction to development
Introduction to developmentIntroduction to development
Introduction to development
Matteo Valoriani
 
Etna dev 2016 - Deep Dive Holographic Applications
Etna dev 2016 - Deep Dive Holographic ApplicationsEtna dev 2016 - Deep Dive Holographic Applications
Etna dev 2016 - Deep Dive Holographic Applications
Matteo Valoriani
 
Etna dev 2016 - Introduction to Holographic Development
Etna dev 2016 - Introduction to Holographic DevelopmentEtna dev 2016 - Introduction to Holographic Development
Etna dev 2016 - Introduction to Holographic Development
Matteo Valoriani
 
Etna dev 2016 - Introduction to Mixed Reality with HoloLens
Etna dev 2016 - Introduction to Mixed Reality with HoloLensEtna dev 2016 - Introduction to Mixed Reality with HoloLens
Etna dev 2016 - Introduction to Mixed Reality with HoloLens
Matteo Valoriani
 
Mixed Reality from demo to product
Mixed Reality from demo to productMixed Reality from demo to product
Mixed Reality from demo to product
Matteo Valoriani
 
Intel RealSense Hands-on Lab - Rome
Intel RealSense Hands-on Lab - RomeIntel RealSense Hands-on Lab - Rome
Intel RealSense Hands-on Lab - Rome
Matteo Valoriani
 
Develop store apps with kinect for windows v2
Develop store apps with kinect for windows v2Develop store apps with kinect for windows v2
Develop store apps with kinect for windows v2
Matteo Valoriani
 
Programming with kinect v2
Programming with kinect v2Programming with kinect v2
Programming with kinect v2
Matteo Valoriani
 
Programming with RealSense using .NET
Programming with RealSense using .NETProgramming with RealSense using .NET
Programming with RealSense using .NET
Matteo Valoriani
 
Communitydays2015
Communitydays2015Communitydays2015
Communitydays2015
Matteo Valoriani
 
Tecnologie e Startup: ICT è solo una commodity?
Tecnologie e Startup: ICT è solo una commodity? Tecnologie e Startup: ICT è solo una commodity?
Tecnologie e Startup: ICT è solo una commodity?
Matteo Valoriani
 
Intel real sense handson
Intel real sense handsonIntel real sense handson
Intel real sense handson
Matteo Valoriani
 
Corso pratico di C# - 2013
Corso pratico di C# - 2013Corso pratico di C# - 2013
Corso pratico di C# - 2013
Matteo Valoriani
 

More from Matteo Valoriani (20)

Immerge yourself in a new Reality
Immerge yourself in a new RealityImmerge yourself in a new Reality
Immerge yourself in a new Reality
 
How Augment your Reality: Different perspective on the Reality / Virtuality C...
How Augment your Reality: Different perspective on the Reality / Virtuality C...How Augment your Reality: Different perspective on the Reality / Virtuality C...
How Augment your Reality: Different perspective on the Reality / Virtuality C...
 
Hour ofcode
Hour ofcodeHour ofcode
Hour ofcode
 
Debug, Analyze and Optimize Games with Intel Tools
Debug, Analyze and Optimize Games with Intel Tools Debug, Analyze and Optimize Games with Intel Tools
Debug, Analyze and Optimize Games with Intel Tools
 
More Personal Computing: Windows 10, Kinect and Wearables
More Personal Computing: Windows 10, Kinect and WearablesMore Personal Computing: Windows 10, Kinect and Wearables
More Personal Computing: Windows 10, Kinect and Wearables
 
Introduction to development
Introduction to developmentIntroduction to development
Introduction to development
 
Etna dev 2016 - Deep Dive Holographic Applications
Etna dev 2016 - Deep Dive Holographic ApplicationsEtna dev 2016 - Deep Dive Holographic Applications
Etna dev 2016 - Deep Dive Holographic Applications
 
Etna dev 2016 - Introduction to Holographic Development
Etna dev 2016 - Introduction to Holographic DevelopmentEtna dev 2016 - Introduction to Holographic Development
Etna dev 2016 - Introduction to Holographic Development
 
Etna dev 2016 - Introduction to Mixed Reality with HoloLens
Etna dev 2016 - Introduction to Mixed Reality with HoloLensEtna dev 2016 - Introduction to Mixed Reality with HoloLens
Etna dev 2016 - Introduction to Mixed Reality with HoloLens
 
Mixed Reality from demo to product
Mixed Reality from demo to productMixed Reality from demo to product
Mixed Reality from demo to product
 
Intel RealSense Hands-on Lab - Rome
Intel RealSense Hands-on Lab - RomeIntel RealSense Hands-on Lab - Rome
Intel RealSense Hands-on Lab - Rome
 
Develop store apps with kinect for windows v2
Develop store apps with kinect for windows v2Develop store apps with kinect for windows v2
Develop store apps with kinect for windows v2
 
Programming with kinect v2
Programming with kinect v2Programming with kinect v2
Programming with kinect v2
 
Programming with RealSense using .NET
Programming with RealSense using .NETProgramming with RealSense using .NET
Programming with RealSense using .NET
 
Communitydays2015
Communitydays2015Communitydays2015
Communitydays2015
 
Tecnologie e Startup: ICT è solo una commodity?
Tecnologie e Startup: ICT è solo una commodity? Tecnologie e Startup: ICT è solo una commodity?
Tecnologie e Startup: ICT è solo una commodity?
 
Intel real sense handson
Intel real sense handsonIntel real sense handson
Intel real sense handson
 
Communityday2013
Communityday2013Communityday2013
Communityday2013
 
Communitydays2014
Communitydays2014Communitydays2014
Communitydays2014
 
Corso pratico di C# - 2013
Corso pratico di C# - 2013Corso pratico di C# - 2013
Corso pratico di C# - 2013
 

Recently uploaded

From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
Product School
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
ThousandEyes
 
Search and Society: Reimagining Information Access for Radical Futures
Search and Society: Reimagining Information Access for Radical FuturesSearch and Society: Reimagining Information Access for Radical Futures
Search and Society: Reimagining Information Access for Radical Futures
Bhaskar Mitra
 
When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...
Elena Simperl
 
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
BookNet Canada
 
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Tobias Schneck
 
Mission to Decommission: Importance of Decommissioning Products to Increase E...
Mission to Decommission: Importance of Decommissioning Products to Increase E...Mission to Decommission: Importance of Decommissioning Products to Increase E...
Mission to Decommission: Importance of Decommissioning Products to Increase E...
Product School
 
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered QualitySoftware Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Inflectra
 
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
Product School
 
Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...
Product School
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
UiPathCommunity
 
Accelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish CachingAccelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish Caching
Thijs Feryn
 
Connector Corner: Automate dynamic content and events by pushing a button
Connector Corner: Automate dynamic content and events by pushing a buttonConnector Corner: Automate dynamic content and events by pushing a button
Connector Corner: Automate dynamic content and events by pushing a button
DianaGray10
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
Jemma Hussein Allen
 
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
91mobiles
 
Knowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and backKnowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and back
Elena Simperl
 
GraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge GraphGraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge Graph
Guy Korland
 
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
DanBrown980551
 

Recently uploaded (20)

From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
 
Search and Society: Reimagining Information Access for Radical Futures
Search and Society: Reimagining Information Access for Radical FuturesSearch and Society: Reimagining Information Access for Radical Futures
Search and Society: Reimagining Information Access for Radical Futures
 
When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...
 
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
 
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
 
Mission to Decommission: Importance of Decommissioning Products to Increase E...
Mission to Decommission: Importance of Decommissioning Products to Increase E...Mission to Decommission: Importance of Decommissioning Products to Increase E...
Mission to Decommission: Importance of Decommissioning Products to Increase E...
 
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered QualitySoftware Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
 
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
 
Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
 
Accelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish CachingAccelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish Caching
 
Connector Corner: Automate dynamic content and events by pushing a button
Connector Corner: Automate dynamic content and events by pushing a buttonConnector Corner: Automate dynamic content and events by pushing a button
Connector Corner: Automate dynamic content and events by pushing a button
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
 
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
 
Knowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and backKnowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and back
 
GraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge GraphGraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge Graph
 
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
 

Face recognition

  • 1. Template designed by Face Recognition using C# Matteo Valoriani mvaloriani@gmail.com @matteovaloriani Luigi Oliveto luigi.oliveto@gmail.com @luigioliveto
  • 2. Matteo Valoriani CEO of Fifth Element Speaker and Consultant PhD at Politecnico of Milano Microsoft MVP Intel Software Innovator email: mvaloriani@gmail.com twitter: @MatteoValoriani linkedin: https://it.linkedin.com/in/matteovaloriani Nice to Meet You 2
  • 3. Luigi Oliveto Developer Co-Speaker Master of Science at Politecnico of Milano email: luigi.oliveto@gmail.com twitter: @LuigiOliveto linkedin: https://it.linkedin.com/in/luigioliveto Nice to Meet You 3
  • 4. Face Detection vs Face Recognition vs Face Identification Face Analysis HomeMade • OpenCV/Emgu Face Analysis with Cloud Services • BetaFace • Microsoft Face API Face Analysis with Special Camera • Kinect • RealSense Conclusions • Common Problems and Limits Agenda
  • 5. Detection vs Analysis vs Recognition
  • 6. Face detection is a computer technology that identifies human faces in digital images. Face Detection Facial Point DetectionFace Detection/Tracking
  • 7. Face Analysis is a computer technology that analyze human faces in digital images and elaborate physical and emotional characteristics. Face Analysis Gender/Age/Race AnalysisEmotion Analysis
  • 8. Facial recognition system is a computer application for automatically identifying or verifying a person from a digital image or a video frame from a video source. Face Recognition Face Similarity/GroupingFace Verification Face Identification
  • 9. Face Analysis Home Made OpenCV/Emgu
  • 10. Emgu CV is a cross platform .Net wrapper to the OpenCV image processing library. What is EMGU
  • 11. The basic layer (layer 1) contains function, structure and enumeration mappings which directly reflect those in OpenCV. The second layer (layer 2) contains classes that mix in advantanges from the .NET world. EMGU Architecture
  • 12. To start with you need to reference 3 EMGU DLL’s. • Emgu.CV.dll • Emgu.CV.UI.dll • Emgu.Util.dll using Emgu.CV; using Emgu.Util; using Emgu.CV.Structure; Create a project with EMGU
  • 14. The goal of statistical classification is to use an object's characteristics to identify which class (or group) it belongs to. An object's characteristics are also known as feature values and are typically presented to the machine in a vector called a feature vector. Machine Learning Classifier
  • 16. OpenCV/EmguCV uses a type of face detector called a Haar Cascade. The Haar Cascade is a classifier (detector) trained on thousands of human faces. This training data is stored in an XML file, and is later used by the classifier during detection. It’s the easiest ready to use face detection method which is supported by OpenCV/EmguCV and has great results. Haar Feature-based Cascade Classifier
  • 17. The Fisher Classifier is a linear classifier. A linear classifier achieves this by making a classification decision based on the value of a linear combination of the characteristics. The Fisher Classifier
  • 19. Face Analysis with Cloud Services BetaFace http://betaface.com/
  • 20. SDK for Private Cloud Configuration WebAPI for Public Cloud BetaFace APIs
  • 21. General face info: - faces (positions, sizes, angles) - face landmarks locations (22 basic, 101 pro) - cropped face images - gender, age, ethnicity, smile, glasses, mustache and beard detection Extended measurements: - face and facial features shapes description - hair and skin color - facial hair detection - approximate hairstyle shape - background color and clothes color. BetaFace - Metadata
  • 22. Following functions supported: - upload image file or submit image url - retrieve image and face metadata, including cropped face image - compare single faces or groups of faces and receive similarity confidence along with match decision. - transform face image(s) - generate averages from two or more faces, change face expression or otherwise modify them. - add user defined metadata tags, store user-adjusted points and face info. BetaFace - Metadata
  • 24. JSON/XML response <FaceInfo> <angle>3.3149</angle> <height>78.05</height> <image_uid>2bdcd1ad-47a6-45f8-ba74- 86c765272422</image_uid> <points> <PointInfo> <name>basic eye left</name> <type>512</type> <x>313.82</x> <y>48.88</y> </PointInfo> … </points> <score>4.81</score> <tags> <TagInfo> <confidence>0.07</confidence> <name>age</name> <value>31</value> </TagInfo> …. < /tags > 22 Points (Basic mode) 101 Points (Advanced Mode) Basic: Age - approximate age value beard - yes, no gender - male, female glasses - yes, no mustache - yes, no smile - yes, no race - asian-middle-eastern, asian, african-american, hispanic, white, middle eastern, other
  • 25. 1. Get XML string 2. Generate XSD • https://devutilsonline.com/xsd-xml/generate-xsd-from-xml 3. Generate C# classes • XML Schema Definition Tool (Xsd.exe) Create C# Classes from XML
  • 26. From XML to XSD
  • 28. FREE: Current public API key limits: faces search/recognition requests - no limits; new images - 500 images per day (15000 images per month); Same image with different set of processing flags counts as new image; images in processing queue - 500; transform requests - no limits. Freemium: 0 EUR/month 500 IMAGE /day, 0.035 EUR extra Basic: 199 EUR/month 40000 IMAGE/month 0.025 EUR extra Premium: 399 EUR/month 100000 IMAGE/month 0.02 EUR extra. IMAGE – Each new image processed via UploadImage, UploadNewImage_File or UploadNewImage_Url functions. - uploading the same image with different detection_flags counts as IMAGE. - uploading the same image with the same set of detection_flags while previous processing results are still in cache does not count as IMAGE. - no restrictions on recognize, GetRecognizeInfo or GetImageInfo requests; no restrictions on number of namespaces or their size If you like to subscribe to one of those plans send email to info@betaface.com with your details for invoice and plan you selected. We will send you your personal API key. Current data storage policy: Source images are removed from cache shortly after processing. Faces that have no person/namespace assigned and corresponding image metadata usually cleaned up after 10 days (face IDs and image IDs will be invalidated). Licensing: Free VS PRO
  • 30. Face Analysis with Cloud Services Project Oxford http://www.projectoxford.ai/
  • 31. Face Detection Face Recognition • Face Verification • Similar Face Searching • Automatic Face Grouping • Person Identification Project Oxford Services
  • 33. 1. Access the Project Oxford Portal https://www.projectoxford.ai, and then click on the "Sign up" button. 2. Sign in with your Microsoft account, or Sign up for a new Azure subscription if you don't already have one. 3. Go down the list to select an offered service such as "Face APIs" from the list, and then click through the various windows in order to make a purchase. 4. Click on the item to view the dashboard, and at the bottom of the page, click on the 'Manage' button to go to the 'Developer Manage Keys' page. 5. Finally, Copy or regenerate subscription keys in the page. Get Start
  • 35. Face Analysis with Special Cameras Kinect ONE
  • 36. Face Analysis with Special Cameras Real Sense F200
  • 38. Q&A
  • 39. Grazie a tutti per la partecipazione Riceverete il link per il download a slide e demo via email nei prossimi giorni Per contattarmi mvaloriani@gmail.com luigi.oliveto@gmail.com Grazie

Editor's Notes

  1. Detects human faces in an image and returns face locations, face landmarks, and optional attributes including head-pose, gender, and age. Analyzes two faces and determine whether they are from the same person. Finds similar-looking faces of a specified face from a list of candidate faces. Divides candidate faces into groups based on face similarity. Identifies persons from a person group by one or more input faces.