SlideShare a Scribd company logo
1 of 33
Download to read offline
Face Recognition
&
Deep Learning
sanparith.marukatat@nectec.or.th
Standard procedure
• Image capturing: camera, webcam, surveillance
• Face detection: locate faces in the image
• Face alignment: normalize size, rectify rotation
• Face matching
• 1:1 Face verification
• 1:N Face recognition
Viola-Jones Haar-like detector

(OpenCV haarcascade_frontalface_alt2.xml)
face size~35x35 to 80x80 pixels
too small
occlusion
rotation
Recognition = compare these
faces to known faces
Controlled environment
face size 218x218 pixels
Viola-Jones eye detector
Eyes distance = 81 pixels
Eyes angle = -0.7 degrees
Face size = 180x200 pixels
Eyes distance = 100 pixels
Eyes angle = 0 degrees
Comparing face
• Face image
• Bitmap of size 180x200 pixels
• Grayscale (0-255)
• 36,000 values/face image
• Given 2 face images x1 and x2
• x1(x,y) - x2(x,y)
• | x1(x,y) - x2(x,y) |
• (x1(x,y) - x2(x,y))
2
• What should be used?
Basic Maths
• 1 Face image = 1 vector
• 36,000 dimensions (d)
• matrix with 1 column
• Distance
• Euclidean distance
• Norm-p distance
• Norm-1 distance
• Norm-infinity distance
Pixels importance and projection
• Not all pixels have the same importance
• Pixel with low variation -> not important
• Pixel with large variation -> could be important
Projection
When ||w||=1, wTx is the
projection of x on axis w
w
Subspace projection
• What should be the axis w?
• How many axis do we need?
Principal Component Analysis
PCA (1)
• Basic idea
• Measure of information = variance
• Variance of z1,…,zN for real numbers zt
• Given a set of face vectors x1,…,xN and axis w

Variance of w
T
x1,…,w
T
xN is
Covariance matrix
Principal Component Analysis
PCA (2)
• Best axis w is obtained by maximizing w
T
Cw
with constraint ||w||=1
• w is an eigenvector of C : Cw = a w
• Variance w
T
Cw=a is the corresponding eigenvalue of w
• PCA
• Construct Covariance matrix C
• Eigen-decompose C
• Select m largest eigenvectors
Eigenface (1)
• What is the problem with face data?
• Solution
Dot matrix
dxd matrix
NxN matrix
Eigenface (2)
• We work with vectors of projected values
x1 x2 …
x40
x Enrollment
Template
Eigenface (3)
• Vector of raw intensity: 36,000 dimensions
• Vector of Eigenface coefficients: 10 dimensions
• Large Eigenface = large variation
• Small Eigenface = noise
Related techniques
• Fisherface (LDA)
• Nullspace LDA
• Laplacianface
• Locality Sensitive Discriminant Analysis
• 2DPCA
• 2DLDA
• 2DPCA+2DLDA
Result on ORL (~10 years ago)
Techniques Accuracy #dim
Eigenface 90-95 200
Fisherface 91-97 50
NLDA 92-97 40
Laplacianface 89-95 50
LSDA 91-97 50
2DPCA 91.5
2DLDA 90.5
2DPCA+2DLDA 93.5
Limitations
• Occlusion: glasses, beard
• Lighting condition
• Facial expression
• Pose
• Make-up
Evaluation
• Accuracy: find closest template and check the ID
• Verification (access control)
• Live captured image VS. stored image
• We have distance -> Should we accept or not?
• False Accept (FA) VS. False Reject (FR)
• From a set of face images
• Compute distances between all pair
• Select threshold T that gives 0 FA and X FR
• Number of tries
distance
T
Labeled Faces in the Wild
• Large number of subjects (>5,000)
• Unconstrained conditions
• Human performance 97-99%
• Traditional methods fail
• New alignment technique: funneling
LFW results
Use outside data
to train the model
Deep Learning
Neural Network timeline
McCulloch & Pitts
Neuron model (1943)
Perceptron limitation
(1969)
Backprop algorithm
70-80’s
SVM (1992)
Deep Learning
(2006)
• Return of Neural Network
• Focus on Deep Structure
• Take advantage of today computing power
Neural Networks (1)
• Neurons are connected via synapse
• A neuron receives signals from other neurons
• When the activation reaches a threshold, it
fires a signal to other neurons
http://en.wikipedia.org/wiki/Neuron
Neural Networks (2)
• Universal Approximator
• Classical structure: MLP
• #hidden nodes, learning rate
• Backprop algorithm
• Gradient
• Direction of change that increases value of objective function
• Vector of partial derivatives wrt. each parameters
• Work on all structures, all objective functions
• Stoping criteria, local optima, gradient vanishing/exploding
Deep Learning
• 2006 Hinton et al.: layer by layer construction -> pre-training
• Stack of RBMs, Stack of Autoencoders
• Convolutional NN (CNN)
• Shared weights
• Take advantage of GPU
CNN today
• Common components
• Convolution layer, Max-pooling layer
• ReLU
• Drop-out, Sampling+flip training data
• GPU
• Tools: Caffe, TensorFlow, Theano, Torch
• Structure: LeNet, AlexNet, GoogLeNet
LeNet
LeNet
AlexNet
LeNet
AlexNet
GoogLeNet
LeNet
AlexNet
GoogLeNet
Microsoft deep residual network: 150 layers!
DeepID

(Sun et al. CVPR 2014)
• 160 dim, 60 regions,
flipped
• 19,200 dimensions!!
• Input to other model
• CelebFace
• Refine training
Learning
technique
for
deep structure
Big data
Computing

power
GPU, etc.

More Related Content

What's hot

Using Feature Grouping as a Stochastic Regularizer for High Dimensional Noisy...
Using Feature Grouping as a Stochastic Regularizer for High Dimensional Noisy...Using Feature Grouping as a Stochastic Regularizer for High Dimensional Noisy...
Using Feature Grouping as a Stochastic Regularizer for High Dimensional Noisy...
WiMLDSMontreal
 
Aaron Roth, Associate Professor, University of Pennsylvania, at MLconf NYC 2017
Aaron Roth, Associate Professor, University of Pennsylvania, at MLconf NYC 2017Aaron Roth, Associate Professor, University of Pennsylvania, at MLconf NYC 2017
Aaron Roth, Associate Professor, University of Pennsylvania, at MLconf NYC 2017
MLconf
 

What's hot (20)

Challenging Common Assumptions in the Unsupervised Learning of Disentangled R...
Challenging Common Assumptions in the Unsupervised Learning of Disentangled R...Challenging Common Assumptions in the Unsupervised Learning of Disentangled R...
Challenging Common Assumptions in the Unsupervised Learning of Disentangled R...
 
Hands-On Machine Learning with Scikit-Learn and TensorFlow - Chapter8
Hands-On Machine Learning with Scikit-Learn and TensorFlow - Chapter8Hands-On Machine Learning with Scikit-Learn and TensorFlow - Chapter8
Hands-On Machine Learning with Scikit-Learn and TensorFlow - Chapter8
 
Machine Learning Essentials Demystified part2 | Big Data Demystified
Machine Learning Essentials Demystified part2 | Big Data DemystifiedMachine Learning Essentials Demystified part2 | Big Data Demystified
Machine Learning Essentials Demystified part2 | Big Data Demystified
 
Deep learning to the rescue - solving long standing problems of recommender ...
Deep learning to the rescue - solving long standing problems of recommender ...Deep learning to the rescue - solving long standing problems of recommender ...
Deep learning to the rescue - solving long standing problems of recommender ...
 
Using Feature Grouping as a Stochastic Regularizer for High Dimensional Noisy...
Using Feature Grouping as a Stochastic Regularizer for High Dimensional Noisy...Using Feature Grouping as a Stochastic Regularizer for High Dimensional Noisy...
Using Feature Grouping as a Stochastic Regularizer for High Dimensional Noisy...
 
Master Defense Slides (translated)
Master Defense Slides (translated)Master Defense Slides (translated)
Master Defense Slides (translated)
 
Transfer Learning and Fine Tuning for Cross Domain Image Classification with ...
Transfer Learning and Fine Tuning for Cross Domain Image Classification with ...Transfer Learning and Fine Tuning for Cross Domain Image Classification with ...
Transfer Learning and Fine Tuning for Cross Domain Image Classification with ...
 
Matineh Shaker, Artificial Intelligence Scientist, Bonsai at MLconf SF 2017
Matineh Shaker, Artificial Intelligence Scientist, Bonsai at MLconf SF 2017Matineh Shaker, Artificial Intelligence Scientist, Bonsai at MLconf SF 2017
Matineh Shaker, Artificial Intelligence Scientist, Bonsai at MLconf SF 2017
 
Neural Networks made easy
Neural Networks made easyNeural Networks made easy
Neural Networks made easy
 
Clustering: A Scikit Learn Tutorial
Clustering: A Scikit Learn TutorialClustering: A Scikit Learn Tutorial
Clustering: A Scikit Learn Tutorial
 
GRU4Rec v2 - Recurrent Neural Networks with Top-k Gains for Session-based Rec...
GRU4Rec v2 - Recurrent Neural Networks with Top-k Gains for Session-based Rec...GRU4Rec v2 - Recurrent Neural Networks with Top-k Gains for Session-based Rec...
GRU4Rec v2 - Recurrent Neural Networks with Top-k Gains for Session-based Rec...
 
Boosted tree
Boosted treeBoosted tree
Boosted tree
 
K-means Clustering with Scikit-Learn
K-means Clustering with Scikit-LearnK-means Clustering with Scikit-Learn
K-means Clustering with Scikit-Learn
 
Sara Hooker & Sean McPherson, Delta Analytics, at MLconf Seattle 2017
Sara Hooker & Sean McPherson, Delta Analytics, at MLconf Seattle 2017Sara Hooker & Sean McPherson, Delta Analytics, at MLconf Seattle 2017
Sara Hooker & Sean McPherson, Delta Analytics, at MLconf Seattle 2017
 
Aaron Roth, Associate Professor, University of Pennsylvania, at MLconf NYC 2017
Aaron Roth, Associate Professor, University of Pennsylvania, at MLconf NYC 2017Aaron Roth, Associate Professor, University of Pennsylvania, at MLconf NYC 2017
Aaron Roth, Associate Professor, University of Pennsylvania, at MLconf NYC 2017
 
Introduction to Neural Network
Introduction to Neural NetworkIntroduction to Neural Network
Introduction to Neural Network
 
Sergei Vassilvitskii, Research Scientist, Google at MLconf NYC - 4/15/16
Sergei Vassilvitskii, Research Scientist, Google at MLconf NYC - 4/15/16Sergei Vassilvitskii, Research Scientist, Google at MLconf NYC - 4/15/16
Sergei Vassilvitskii, Research Scientist, Google at MLconf NYC - 4/15/16
 
Introduction of "TrailBlazer" algorithm
Introduction of "TrailBlazer" algorithmIntroduction of "TrailBlazer" algorithm
Introduction of "TrailBlazer" algorithm
 
Embed, Encode, Attend, Predict – applying the 4 step NLP recipe for text clas...
Embed, Encode, Attend, Predict – applying the 4 step NLP recipe for text clas...Embed, Encode, Attend, Predict – applying the 4 step NLP recipe for text clas...
Embed, Encode, Attend, Predict – applying the 4 step NLP recipe for text clas...
 
Dueling Network Architectures for Deep Reinforcement Learning
Dueling Network Architectures for Deep Reinforcement LearningDueling Network Architectures for Deep Reinforcement Learning
Dueling Network Architectures for Deep Reinforcement Learning
 

Viewers also liked

Pattern Recognition and Machine Learning : Graphical Models
Pattern Recognition and Machine Learning : Graphical ModelsPattern Recognition and Machine Learning : Graphical Models
Pattern Recognition and Machine Learning : Graphical Models
butest
 
DIY Deep Learning with Caffe Workshop
DIY Deep Learning with Caffe WorkshopDIY Deep Learning with Caffe Workshop
DIY Deep Learning with Caffe Workshop
odsc
 
Rattani - Ph.D. Defense Slides
Rattani - Ph.D. Defense SlidesRattani - Ph.D. Defense Slides
Rattani - Ph.D. Defense Slides
Pluribus One
 

Viewers also liked (20)

Structure Learning of Bayesian Networks with p Nodes from n Samples when n&lt...
Structure Learning of Bayesian Networks with p Nodes from n Samples when n&lt...Structure Learning of Bayesian Networks with p Nodes from n Samples when n&lt...
Structure Learning of Bayesian Networks with p Nodes from n Samples when n&lt...
 
Semi fragile watermarking
Semi fragile watermarkingSemi fragile watermarking
Semi fragile watermarking
 
Optimization in deep learning
Optimization in deep learningOptimization in deep learning
Optimization in deep learning
 
[AI07] Revolutionizing Image Processing with Cognitive Toolkit
[AI07] Revolutionizing Image Processing with Cognitive Toolkit[AI07] Revolutionizing Image Processing with Cognitive Toolkit
[AI07] Revolutionizing Image Processing with Cognitive Toolkit
 
портфоліо Бабич О.А.
портфоліо Бабич О.А.портфоліо Бабич О.А.
портфоліо Бабич О.А.
 
Facebook Deep face
Facebook Deep faceFacebook Deep face
Facebook Deep face
 
Pattern Recognition and Machine Learning : Graphical Models
Pattern Recognition and Machine Learning : Graphical ModelsPattern Recognition and Machine Learning : Graphical Models
Pattern Recognition and Machine Learning : Graphical Models
 
Muzammil Abdulrahman PPT On Gabor Wavelet Transform (GWT) Based Facial Expres...
Muzammil Abdulrahman PPT On Gabor Wavelet Transform (GWT) Based Facial Expres...Muzammil Abdulrahman PPT On Gabor Wavelet Transform (GWT) Based Facial Expres...
Muzammil Abdulrahman PPT On Gabor Wavelet Transform (GWT) Based Facial Expres...
 
Caffe - A deep learning framework (Ramin Fahimi)
Caffe - A deep learning framework (Ramin Fahimi)Caffe - A deep learning framework (Ramin Fahimi)
Caffe - A deep learning framework (Ramin Fahimi)
 
Center loss for Face Recognition
Center loss for Face RecognitionCenter loss for Face Recognition
Center loss for Face Recognition
 
Face Recognition Based on Deep Learning (Yurii Pashchenko Technology Stream)
Face Recognition Based on Deep Learning (Yurii Pashchenko Technology Stream) Face Recognition Based on Deep Learning (Yurii Pashchenko Technology Stream)
Face Recognition Based on Deep Learning (Yurii Pashchenko Technology Stream)
 
Caffe framework tutorial2
Caffe framework tutorial2Caffe framework tutorial2
Caffe framework tutorial2
 
Processor, Compiler and Python Programming Language
Processor, Compiler and Python Programming LanguageProcessor, Compiler and Python Programming Language
Processor, Compiler and Python Programming Language
 
DIY Deep Learning with Caffe Workshop
DIY Deep Learning with Caffe WorkshopDIY Deep Learning with Caffe Workshop
DIY Deep Learning with Caffe Workshop
 
Using Gradient Descent for Optimization and Learning
Using Gradient Descent for Optimization and LearningUsing Gradient Descent for Optimization and Learning
Using Gradient Descent for Optimization and Learning
 
Caffe framework tutorial
Caffe framework tutorialCaffe framework tutorial
Caffe framework tutorial
 
Computer vision, machine, and deep learning
Computer vision, machine, and deep learningComputer vision, machine, and deep learning
Computer vision, machine, and deep learning
 
Rattani - Ph.D. Defense Slides
Rattani - Ph.D. Defense SlidesRattani - Ph.D. Defense Slides
Rattani - Ph.D. Defense Slides
 
怖くない誤差逆伝播法 Chainerを添えて
怖くない誤差逆伝播法 Chainerを添えて怖くない誤差逆伝播法 Chainerを添えて
怖くない誤差逆伝播法 Chainerを添えて
 
Pattern Recognition and Machine Learning: Section 3.3
Pattern Recognition and Machine Learning: Section 3.3Pattern Recognition and Machine Learning: Section 3.3
Pattern Recognition and Machine Learning: Section 3.3
 

Similar to Face recognition and deep learning โดย ดร. สรรพฤทธิ์ มฤคทัต NECTEC

Cahall Final Intern Presentation
Cahall Final Intern PresentationCahall Final Intern Presentation
Cahall Final Intern Presentation
Daniel Cahall
 
Defense_Talk
Defense_TalkDefense_Talk
Defense_Talk
castanan2
 

Similar to Face recognition and deep learning โดย ดร. สรรพฤทธิ์ มฤคทัต NECTEC (20)

CAMCOS_final Presentation_Group2.pptx
CAMCOS_final Presentation_Group2.pptxCAMCOS_final Presentation_Group2.pptx
CAMCOS_final Presentation_Group2.pptx
 
cnn.pptx
cnn.pptxcnn.pptx
cnn.pptx
 
Introduction to Neural Networks and Deep Learning
Introduction to Neural Networks and Deep LearningIntroduction to Neural Networks and Deep Learning
Introduction to Neural Networks and Deep Learning
 
Deep learning
Deep learningDeep learning
Deep learning
 
Cahall Final Intern Presentation
Cahall Final Intern PresentationCahall Final Intern Presentation
Cahall Final Intern Presentation
 
Modeling full scale-data(2)
Modeling full scale-data(2)Modeling full scale-data(2)
Modeling full scale-data(2)
 
Deep learning with TensorFlow
Deep learning with TensorFlowDeep learning with TensorFlow
Deep learning with TensorFlow
 
Part2
Part2Part2
Part2
 
Defense_Talk
Defense_TalkDefense_Talk
Defense_Talk
 
Hardware Acceleration for Machine Learning
Hardware Acceleration for Machine LearningHardware Acceleration for Machine Learning
Hardware Acceleration for Machine Learning
 
pca.ppt
pca.pptpca.ppt
pca.ppt
 
The following ppt is about principal component analysis
The following ppt is about principal component analysisThe following ppt is about principal component analysis
The following ppt is about principal component analysis
 
Machine Learning from a Software Engineer's perspective
Machine Learning from a Software Engineer's perspectiveMachine Learning from a Software Engineer's perspective
Machine Learning from a Software Engineer's perspective
 
Machine learning from a software engineer's perspective - Marijn van Zelst - ...
Machine learning from a software engineer's perspective - Marijn van Zelst - ...Machine learning from a software engineer's perspective - Marijn van Zelst - ...
Machine learning from a software engineer's perspective - Marijn van Zelst - ...
 
Fuzzy Logic Based Edge Detection
Fuzzy Logic Based Edge DetectionFuzzy Logic Based Edge Detection
Fuzzy Logic Based Edge Detection
 
Handwritten mathematical symbol recognition
Handwritten mathematical symbol recognitionHandwritten mathematical symbol recognition
Handwritten mathematical symbol recognition
 
Fast Single-pass K-means Clusterting at Oxford
Fast Single-pass K-means Clusterting at Oxford Fast Single-pass K-means Clusterting at Oxford
Fast Single-pass K-means Clusterting at Oxford
 
Automated attendance system based on facial recognition
Automated attendance system based on facial recognitionAutomated attendance system based on facial recognition
Automated attendance system based on facial recognition
 
AlexNet
AlexNetAlexNet
AlexNet
 
Image processing 1-lectures
Image processing  1-lecturesImage processing  1-lectures
Image processing 1-lectures
 

More from BAINIDA

Advanced quantitative research methods in political science and pa
Advanced quantitative  research methods in political science and paAdvanced quantitative  research methods in political science and pa
Advanced quantitative research methods in political science and pa
BAINIDA
 

More from BAINIDA (20)

Mixed methods in social and behavioral sciences
Mixed methods in social and behavioral sciencesMixed methods in social and behavioral sciences
Mixed methods in social and behavioral sciences
 
Advanced quantitative research methods in political science and pa
Advanced quantitative  research methods in political science and paAdvanced quantitative  research methods in political science and pa
Advanced quantitative research methods in political science and pa
 
Latest thailand election2019report
Latest thailand election2019reportLatest thailand election2019report
Latest thailand election2019report
 
Data science in medicine
Data science in medicineData science in medicine
Data science in medicine
 
Nursing data science
Nursing data scienceNursing data science
Nursing data science
 
Financial time series analysis with R@the 3rd NIDA BADS conference by Asst. p...
Financial time series analysis with R@the 3rd NIDA BADS conference by Asst. p...Financial time series analysis with R@the 3rd NIDA BADS conference by Asst. p...
Financial time series analysis with R@the 3rd NIDA BADS conference by Asst. p...
 
Statistics and big data for justice and fairness
Statistics and big data for justice and fairnessStatistics and big data for justice and fairness
Statistics and big data for justice and fairness
 
Data science and big data for business and industrial application
Data science and big data  for business and industrial applicationData science and big data  for business and industrial application
Data science and big data for business and industrial application
 
Update trend: Free digital marketing metrics for start-up
Update trend: Free digital marketing metrics for start-upUpdate trend: Free digital marketing metrics for start-up
Update trend: Free digital marketing metrics for start-up
 
Advent of ds and stat adjustment
Advent of ds and stat adjustmentAdvent of ds and stat adjustment
Advent of ds and stat adjustment
 
เมื่อ Data Science เข้ามา สถิติศาสตร์จะปรับตัวอย่างไร
เมื่อ Data Science เข้ามา สถิติศาสตร์จะปรับตัวอย่างไร เมื่อ Data Science เข้ามา สถิติศาสตร์จะปรับตัวอย่างไร
เมื่อ Data Science เข้ามา สถิติศาสตร์จะปรับตัวอย่างไร
 
Data visualization. map
Data visualization. map Data visualization. map
Data visualization. map
 
Dark data by Worapol Alex Pongpech
Dark data by Worapol Alex PongpechDark data by Worapol Alex Pongpech
Dark data by Worapol Alex Pongpech
 
Deepcut Thai word Segmentation @ NIDA
Deepcut Thai word Segmentation @ NIDADeepcut Thai word Segmentation @ NIDA
Deepcut Thai word Segmentation @ NIDA
 
Professionals and wanna be in Business Analytics and Data Science
Professionals and wanna be in Business Analytics and Data ScienceProfessionals and wanna be in Business Analytics and Data Science
Professionals and wanna be in Business Analytics and Data Science
 
Visualizing for impact final
Visualizing for impact finalVisualizing for impact final
Visualizing for impact final
 
Python programming workshop
Python programming workshopPython programming workshop
Python programming workshop
 
Second prize business plan @ the First NIDA business analytics and data scien...
Second prize business plan @ the First NIDA business analytics and data scien...Second prize business plan @ the First NIDA business analytics and data scien...
Second prize business plan @ the First NIDA business analytics and data scien...
 
Second prize data analysis @ the First NIDA business analytics and data scie...
Second prize data analysis @ the First NIDA  business analytics and data scie...Second prize data analysis @ the First NIDA  business analytics and data scie...
Second prize data analysis @ the First NIDA business analytics and data scie...
 
แผนธุรกิจ ของทีมที่ได้รางวัลชนะเลิศ The First NIDA Business Analytics and Dat...
แผนธุรกิจ ของทีมที่ได้รางวัลชนะเลิศ The First NIDA Business Analytics and Dat...แผนธุรกิจ ของทีมที่ได้รางวัลชนะเลิศ The First NIDA Business Analytics and Dat...
แผนธุรกิจ ของทีมที่ได้รางวัลชนะเลิศ The First NIDA Business Analytics and Dat...
 

Recently uploaded

Seal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptxSeal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptx
negromaestrong
 
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in DelhiRussian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
kauryashika82
 
The basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptxThe basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptx
heathfieldcps1
 
1029-Danh muc Sach Giao Khoa khoi 6.pdf
1029-Danh muc Sach Giao Khoa khoi  6.pdf1029-Danh muc Sach Giao Khoa khoi  6.pdf
1029-Danh muc Sach Giao Khoa khoi 6.pdf
QucHHunhnh
 

Recently uploaded (20)

Making communications land - Are they received and understood as intended? we...
Making communications land - Are they received and understood as intended? we...Making communications land - Are they received and understood as intended? we...
Making communications land - Are they received and understood as intended? we...
 
Seal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptxSeal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptx
 
PROCESS RECORDING FORMAT.docx
PROCESS      RECORDING        FORMAT.docxPROCESS      RECORDING        FORMAT.docx
PROCESS RECORDING FORMAT.docx
 
Accessible Digital Futures project (20/03/2024)
Accessible Digital Futures project (20/03/2024)Accessible Digital Futures project (20/03/2024)
Accessible Digital Futures project (20/03/2024)
 
SOC 101 Demonstration of Learning Presentation
SOC 101 Demonstration of Learning PresentationSOC 101 Demonstration of Learning Presentation
SOC 101 Demonstration of Learning Presentation
 
ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.
 
This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.
 
How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17
 
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in DelhiRussian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
 
SKILL OF INTRODUCING THE LESSON MICRO SKILLS.pptx
SKILL OF INTRODUCING THE LESSON MICRO SKILLS.pptxSKILL OF INTRODUCING THE LESSON MICRO SKILLS.pptx
SKILL OF INTRODUCING THE LESSON MICRO SKILLS.pptx
 
psychiatric nursing HISTORY COLLECTION .docx
psychiatric  nursing HISTORY  COLLECTION  .docxpsychiatric  nursing HISTORY  COLLECTION  .docx
psychiatric nursing HISTORY COLLECTION .docx
 
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdf
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdfUGC NET Paper 1 Mathematical Reasoning & Aptitude.pdf
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdf
 
Introduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The BasicsIntroduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The Basics
 
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
 
Asian American Pacific Islander Month DDSD 2024.pptx
Asian American Pacific Islander Month DDSD 2024.pptxAsian American Pacific Islander Month DDSD 2024.pptx
Asian American Pacific Islander Month DDSD 2024.pptx
 
The basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptxThe basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptx
 
Application orientated numerical on hev.ppt
Application orientated numerical on hev.pptApplication orientated numerical on hev.ppt
Application orientated numerical on hev.ppt
 
General Principles of Intellectual Property: Concepts of Intellectual Proper...
General Principles of Intellectual Property: Concepts of Intellectual  Proper...General Principles of Intellectual Property: Concepts of Intellectual  Proper...
General Principles of Intellectual Property: Concepts of Intellectual Proper...
 
Food safety_Challenges food safety laboratories_.pdf
Food safety_Challenges food safety laboratories_.pdfFood safety_Challenges food safety laboratories_.pdf
Food safety_Challenges food safety laboratories_.pdf
 
1029-Danh muc Sach Giao Khoa khoi 6.pdf
1029-Danh muc Sach Giao Khoa khoi  6.pdf1029-Danh muc Sach Giao Khoa khoi  6.pdf
1029-Danh muc Sach Giao Khoa khoi 6.pdf
 

Face recognition and deep learning โดย ดร. สรรพฤทธิ์ มฤคทัต NECTEC

  • 2. Standard procedure • Image capturing: camera, webcam, surveillance • Face detection: locate faces in the image • Face alignment: normalize size, rectify rotation • Face matching • 1:1 Face verification • 1:N Face recognition
  • 3. Viola-Jones Haar-like detector
 (OpenCV haarcascade_frontalface_alt2.xml) face size~35x35 to 80x80 pixels too small occlusion rotation Recognition = compare these faces to known faces
  • 4. Controlled environment face size 218x218 pixels Viola-Jones eye detector Eyes distance = 81 pixels Eyes angle = -0.7 degrees Face size = 180x200 pixels Eyes distance = 100 pixels Eyes angle = 0 degrees
  • 5.
  • 6. Comparing face • Face image • Bitmap of size 180x200 pixels • Grayscale (0-255) • 36,000 values/face image • Given 2 face images x1 and x2 • x1(x,y) - x2(x,y) • | x1(x,y) - x2(x,y) | • (x1(x,y) - x2(x,y)) 2 • What should be used?
  • 7. Basic Maths • 1 Face image = 1 vector • 36,000 dimensions (d) • matrix with 1 column • Distance • Euclidean distance • Norm-p distance • Norm-1 distance • Norm-infinity distance
  • 8. Pixels importance and projection • Not all pixels have the same importance • Pixel with low variation -> not important • Pixel with large variation -> could be important Projection When ||w||=1, wTx is the projection of x on axis w w
  • 9. Subspace projection • What should be the axis w? • How many axis do we need?
  • 10. Principal Component Analysis PCA (1) • Basic idea • Measure of information = variance • Variance of z1,…,zN for real numbers zt • Given a set of face vectors x1,…,xN and axis w
 Variance of w T x1,…,w T xN is Covariance matrix
  • 11. Principal Component Analysis PCA (2) • Best axis w is obtained by maximizing w T Cw with constraint ||w||=1 • w is an eigenvector of C : Cw = a w • Variance w T Cw=a is the corresponding eigenvalue of w • PCA • Construct Covariance matrix C • Eigen-decompose C • Select m largest eigenvectors
  • 12. Eigenface (1) • What is the problem with face data? • Solution Dot matrix dxd matrix NxN matrix
  • 13. Eigenface (2) • We work with vectors of projected values x1 x2 … x40 x Enrollment Template
  • 14. Eigenface (3) • Vector of raw intensity: 36,000 dimensions • Vector of Eigenface coefficients: 10 dimensions • Large Eigenface = large variation • Small Eigenface = noise
  • 15. Related techniques • Fisherface (LDA) • Nullspace LDA • Laplacianface • Locality Sensitive Discriminant Analysis • 2DPCA • 2DLDA • 2DPCA+2DLDA
  • 16. Result on ORL (~10 years ago) Techniques Accuracy #dim Eigenface 90-95 200 Fisherface 91-97 50 NLDA 92-97 40 Laplacianface 89-95 50 LSDA 91-97 50 2DPCA 91.5 2DLDA 90.5 2DPCA+2DLDA 93.5
  • 17. Limitations • Occlusion: glasses, beard • Lighting condition • Facial expression • Pose • Make-up
  • 18. Evaluation • Accuracy: find closest template and check the ID • Verification (access control) • Live captured image VS. stored image • We have distance -> Should we accept or not? • False Accept (FA) VS. False Reject (FR) • From a set of face images • Compute distances between all pair • Select threshold T that gives 0 FA and X FR • Number of tries distance T
  • 19. Labeled Faces in the Wild • Large number of subjects (>5,000) • Unconstrained conditions • Human performance 97-99% • Traditional methods fail • New alignment technique: funneling
  • 20. LFW results Use outside data to train the model
  • 22. Neural Network timeline McCulloch & Pitts Neuron model (1943) Perceptron limitation (1969) Backprop algorithm 70-80’s SVM (1992) Deep Learning (2006)
  • 23. • Return of Neural Network • Focus on Deep Structure • Take advantage of today computing power
  • 24. Neural Networks (1) • Neurons are connected via synapse • A neuron receives signals from other neurons • When the activation reaches a threshold, it fires a signal to other neurons http://en.wikipedia.org/wiki/Neuron
  • 25. Neural Networks (2) • Universal Approximator • Classical structure: MLP • #hidden nodes, learning rate • Backprop algorithm • Gradient • Direction of change that increases value of objective function • Vector of partial derivatives wrt. each parameters • Work on all structures, all objective functions • Stoping criteria, local optima, gradient vanishing/exploding
  • 26. Deep Learning • 2006 Hinton et al.: layer by layer construction -> pre-training • Stack of RBMs, Stack of Autoencoders • Convolutional NN (CNN) • Shared weights • Take advantage of GPU
  • 27. CNN today • Common components • Convolution layer, Max-pooling layer • ReLU • Drop-out, Sampling+flip training data • GPU • Tools: Caffe, TensorFlow, Theano, Torch • Structure: LeNet, AlexNet, GoogLeNet
  • 28. LeNet
  • 32. DeepID
 (Sun et al. CVPR 2014) • 160 dim, 60 regions, flipped • 19,200 dimensions!! • Input to other model • CelebFace • Refine training