SlideShare ist ein Scribd-Unternehmen logo
1 von 16
A STUDY ON FACE RECOGNITION
TECHNIQUE BASED ON EIGENFACE
By:
Sadique Nayeem
Pondicherry University
Outline
Overview
Eigenface Algorithm
Implementation
Image Database
Experimental Result
Future Enhancement
Conclusions
2
Overview
Face recognition system consist of three component.
 Face Representation: How to model a face?
 Template-based approaches
 Feature-based approaches
 Appearance-based approaches
 Face Detection: To locate a face in image.
 Manipulation of images in “face space”
 Utilization of elliptical shape of human head
 Face Identification: Compare given image with
database.
 Performance affected by scale, pose, illumination, facial expression, and
disguise, etc.
3
Eigenfaces Approach
 In the language of information theory…
 the main objective is to mine the relevant information in a face image,
encode it as efficiently as possible and compare one face encoding with
a database of face images encoded in the same process.
 In mathematical terms…
 Find the principal components of the face distribution, or the
eigenvectors of the covariance matrix of the set of face images, called
e ig e nface s.
 Eigenfaces are a set of features that characterize the variation between
face images. Each training face image can be represented in terms of a
linear combination of the eigenfaces, so can the new input image.
 Compare the feature weights of the new input image with those of the
known individuals
4
Eigenface Initialization
The eigenfaces approach for face recognition involves the following
initialization operations:
 Acquire a set of training images.
 Calculate the eigenfaces from the training set, keeping only the
best M images with the highest eigenvalues. These M images
define the “face space”. As new faces are experienced, the
eigenfaces can be updated.
 Calculate the corresponding distribution in M-dimensional weight
space for each known individual (training image), by projecting their
face images onto the face space.
5
Eigenface Recognition
Having initialized the system, the following steps are used to recognize
new face images:
 Given an image to be recognized, calculate a set of weights of the
Meigenfaces by projecting it onto each of the eigenfaces.
 Determine if the image is a face at all by checking to see if the
image is sufficiently close to the face space.
 If it is a face, classify the weight pattern as either a known person or
as unknown.
6
Figure : Eigenfaces of Essex face database
-'face94'
Image Database
Name
of
database
Source Image
format
Image
size
Image
type
Number
of unique
individual
Total
numbe
rof
images
Variations Sample
Image
IFD IIT
Kanpur
[3]
JPG 110 X 75 Color 60 660 8 pose,
3 emotion
Essex
face
databas
e
-face94
University
of Essex,
UK [4]
JPG 90 X 100 Color 152 3040 facial
expression,
slight head
tilt.
Yale Yale
university
[5]
GIF 320 X
243
Grey 15 165 facial
expression,
w/o glasses
Face
1999
California
Institute
of
Technolo
gy [6]
JPG 300X198 Color 26 450 lighting,
expression,
background
7
Experimental Result
8
Eigenface face recognition with different sample images
Name
of
databas
e
Total
No. of
unique
person
No. of
samples
of each
image in
training
set
No. of
image in
training
set
No. of False
recognition
Accuracy rate (%)
IFD 60 1 60 31 49.18
2 120 25 59.01
3 180 16 73.77
4 240 16 73.77
5 300 12 80.32
6 360 8 86.88
7 420 3 95.08
8 480 2 96.72
9 540 1 98.36
10 600 1 98.36
11 660 1 98.36
Esse
x face
152 1 152 47 69.07
2 304 29 80.92
3 456 12 92.10
4 608 11 92.76
5 760 11 92.76
6 912 10 93.42
7 1064 10 93.42
8 1216 9 94.07
9 1368 8 94.73
10 1520 8 94.73
11 1672 6 96.05
Yale 15 1 15 8 46.66
2 30 2 86.66
3 45 3 80.00
4 60 3 80.00
5 75 2 86.66
6 90 1 93.33
7 105 2 86.66
8 120 1 93.33
9 135 1 93.33
10 150 1 93.33
11 165 1 93.33
Face
1999
26 1 26 17 34.61
2 52 15 42.30
3 78 14 46.15
4 104 9 65.38
5 130 9 65.38
6 156 8 69.23
7 182 5 80.76
8 208 5 80.76
9 234 3 88.46
10 260 2 92.30
11 286 1 96.15
Eigenface face recognition with different sample images
Name
of
databas
e
Total
No. of
unique
person
No. of
samples
of each
image in
training
set
No. of
image in
training
set
No. of False
recognition
Accuracy rate (%)
Experimental Result (cont..)
9
Number of samples
Future Enhancement
 According to the experimental result, recognition with one sample
per person does not give better recognition rate in all cases.
 But, in real time application only one sample per person will be
available ( as in case of voter card, Driving license, passport or
ADHAAR Card).
 So, recognition from single sample per person is needed.
 One sample per person is easy to collect, save storage cost and
save computational cost.
10
Courtesy: http://images.google.co.in/
Problem Statement
 This problem can be defined as follows:
“Given a stored database of faces with only one image per person,
the goal is to identify a person from the database later in time in
any different and unpredictable poses, lighting, disguise, etc
from the individual image.”
11
Proposed Idea
 1.2 billion population of India is being enrolled for ADHAAR Card with
different biometric.
 Face image is also being collected.
 The ADHAAR Card or UID no. can be used as a platform on which
different application can be developed as under:
12
ADHAAR CARD or UID NUMBER
Proposed Idea (contd.)
 To restrain the crime, ADHAAR Card can be the best source for
identification.
 Individual images in ADHAAR Card may work as training set.
 CCTV images from crime scene can be used as test image.
 Procedure:
 Capture the video from the CCTV camera.
 Detect the human face in the CCTV video.
 Take the CCTV image as the test image.
 Do the preprocessing on the CCTV image i.e
 Crop both the eyes, eyebrow, nose, and mouth.
 Load the ADHAAR based Face image as the training image
 Crop both the eyes, eyebrow, nose, and mouth
 Apply the Eigenface PCA for the Recognition
13
Conclusions
 Eigenface PCA is one of the most successful technique and it gives
better result for more number of samples in training set.
 It does not produce good result for single sample per person.
 The need for real time application can be given by only single sample
per person.
 Taking ADHAAR Card as a platform, Artificial Face Recognition
system can be developed by using PCA on reconstructed image.
14
Reference
1. “Eigenfaces for recognition”, M. Turk and A. Pentland, Jo urnalo f Co g nitive
Ne uro scie nce , vo l. 3, No . 1 , 1 9 9 1
2. “Automatic recognition and analysis of human faces and facial expressions: A
survey”, A. Samal and P. A. Iyengar, Patte rn Re co g nitio n, 25(1 ): 6 5-7 7 , 1 9 9 2
3. “The Indian Face Database”, Vidit Jain, Amitabha Mukherjee, 2002, http://vis-
www. cs. um ass. e du/~ vidit/IndianFace Database /
4. “Essex face database -face94”, University of Essex, UK,
http: //cswww. e sse x. ac. uk/m v/allface s/inde x. htm l
5. “Yale Database”, http: //cvc. yale . e du/pro je cts/yale face s/yale face s. htm l
6. “FACE 1999”, http: //www. visio n. calte ch. e du/htm l-file s/archive . htm l
15
Thank You !
16

Weitere ähnliche Inhalte

Was ist angesagt?

Predicting Emotions through Facial Expressions
Predicting Emotions through Facial Expressions  Predicting Emotions through Facial Expressions
Predicting Emotions through Facial Expressions twinkle singh
 
Facial expression recognition system : survey
Facial expression recognition system : surveyFacial expression recognition system : survey
Facial expression recognition system : surveyMohamed Alhmdany
 
Facial expression recognition on real world face images (OPTIK)
Facial expression recognition on real world face images (OPTIK)Facial expression recognition on real world face images (OPTIK)
Facial expression recognition on real world face images (OPTIK)Sohail Ahmed
 
Facial expression recognition based on image feature
Facial expression recognition based on image featureFacial expression recognition based on image feature
Facial expression recognition based on image featureTasnim Tara
 
Face Detection Using MATLAB (SUD)
Face Detection Using MATLAB (SUD)Face Detection Using MATLAB (SUD)
Face Detection Using MATLAB (SUD)Sudhanshu Saxena
 
Report Face Detection
Report Face DetectionReport Face Detection
Report Face DetectionJugal Patel
 
Face recognition across non uniform motion blur, illumination, and pose
Face recognition across non uniform motion blur, illumination, and poseFace recognition across non uniform motion blur, illumination, and pose
Face recognition across non uniform motion blur, illumination, and posePvrtechnologies Nellore
 
Facial expression recognition based on local binary patterns final
Facial expression recognition based on local binary patterns finalFacial expression recognition based on local binary patterns final
Facial expression recognition based on local binary patterns finalahmad abdelhafeez
 
Facial Expression Recognition System
Facial Expression Recognition SystemFacial Expression Recognition System
Facial Expression Recognition SystemMukul Mathur
 
FACE RECOGNITION USING NEURAL NETWORK
FACE RECOGNITION USING NEURAL NETWORKFACE RECOGNITION USING NEURAL NETWORK
FACE RECOGNITION USING NEURAL NETWORKTITHI DAN
 
Facial emotion recognition
Facial emotion recognitionFacial emotion recognition
Facial emotion recognitionRahin Patel
 
Facial recognition
Facial recognitionFacial recognition
Facial recognitionSonam1891
 
Face recogntion using PCA algorithm
Face recogntion using PCA algorithmFace recogntion using PCA algorithm
Face recogntion using PCA algorithmAshwini Awatare
 
A novel approach for performance parameter estimation of face recognition bas...
A novel approach for performance parameter estimation of face recognition bas...A novel approach for performance parameter estimation of face recognition bas...
A novel approach for performance parameter estimation of face recognition bas...IJMER
 

Was ist angesagt? (20)

Predicting Emotions through Facial Expressions
Predicting Emotions through Facial Expressions  Predicting Emotions through Facial Expressions
Predicting Emotions through Facial Expressions
 
Facial expression recognition system : survey
Facial expression recognition system : surveyFacial expression recognition system : survey
Facial expression recognition system : survey
 
Facial expression recognition on real world face images (OPTIK)
Facial expression recognition on real world face images (OPTIK)Facial expression recognition on real world face images (OPTIK)
Facial expression recognition on real world face images (OPTIK)
 
Face recognition
Face recognition Face recognition
Face recognition
 
Facial expression recognition based on image feature
Facial expression recognition based on image featureFacial expression recognition based on image feature
Facial expression recognition based on image feature
 
Ch 2
Ch 2Ch 2
Ch 2
 
Ch 1
Ch 1Ch 1
Ch 1
 
Face Detection Using MATLAB (SUD)
Face Detection Using MATLAB (SUD)Face Detection Using MATLAB (SUD)
Face Detection Using MATLAB (SUD)
 
Report Face Detection
Report Face DetectionReport Face Detection
Report Face Detection
 
Face Detection
Face DetectionFace Detection
Face Detection
 
face detection
face detectionface detection
face detection
 
Face recognition across non uniform motion blur, illumination, and pose
Face recognition across non uniform motion blur, illumination, and poseFace recognition across non uniform motion blur, illumination, and pose
Face recognition across non uniform motion blur, illumination, and pose
 
Facial expression recognition based on local binary patterns final
Facial expression recognition based on local binary patterns finalFacial expression recognition based on local binary patterns final
Facial expression recognition based on local binary patterns final
 
Facial Expression Recognition System
Facial Expression Recognition SystemFacial Expression Recognition System
Facial Expression Recognition System
 
FACE RECOGNITION USING NEURAL NETWORK
FACE RECOGNITION USING NEURAL NETWORKFACE RECOGNITION USING NEURAL NETWORK
FACE RECOGNITION USING NEURAL NETWORK
 
Facial emotion recognition
Facial emotion recognitionFacial emotion recognition
Facial emotion recognition
 
Facial recognition
Facial recognitionFacial recognition
Facial recognition
 
Face recogntion using PCA algorithm
Face recogntion using PCA algorithmFace recogntion using PCA algorithm
Face recogntion using PCA algorithm
 
Infarec
InfarecInfarec
Infarec
 
A novel approach for performance parameter estimation of face recognition bas...
A novel approach for performance parameter estimation of face recognition bas...A novel approach for performance parameter estimation of face recognition bas...
A novel approach for performance parameter estimation of face recognition bas...
 

Ähnlich wie Eigenface Face Recognition Using Single Sample Images

Study and Analysis of Novel Face Recognition Techniques using PCA, LDA and Ge...
Study and Analysis of Novel Face Recognition Techniques using PCA, LDA and Ge...Study and Analysis of Novel Face Recognition Techniques using PCA, LDA and Ge...
Study and Analysis of Novel Face Recognition Techniques using PCA, LDA and Ge...sadique_ghitm
 
Implementation of Face Recognition in Cloud Vision Using Eigen Faces
Implementation of Face Recognition in Cloud Vision Using Eigen FacesImplementation of Face Recognition in Cloud Vision Using Eigen Faces
Implementation of Face Recognition in Cloud Vision Using Eigen FacesIJERA Editor
 
Face and Eye Detection Varying Scenarios With Haar Classifier_2015
Face and Eye Detection Varying Scenarios With Haar Classifier_2015Face and Eye Detection Varying Scenarios With Haar Classifier_2015
Face and Eye Detection Varying Scenarios With Haar Classifier_2015Showrav Mazumder
 
Improved Approach for Eigenface Recognition
Improved Approach for Eigenface RecognitionImproved Approach for Eigenface Recognition
Improved Approach for Eigenface RecognitionBRNSSPublicationHubI
 
Face recognition system
Face recognition systemFace recognition system
Face recognition systemYogesh Lamture
 
Paper id 24201475
Paper id 24201475Paper id 24201475
Paper id 24201475IJRAT
 
HUMAN FACE RECOGNITION USING IMAGE PROCESSING PCA AND NEURAL NETWORK
HUMAN FACE RECOGNITION USING IMAGE PROCESSING PCA AND NEURAL NETWORKHUMAN FACE RECOGNITION USING IMAGE PROCESSING PCA AND NEURAL NETWORK
HUMAN FACE RECOGNITION USING IMAGE PROCESSING PCA AND NEURAL NETWORKijiert bestjournal
 
AN IMPROVED TECHNIQUE FOR HUMAN FACE RECOGNITION USING IMAGE PROCESSING
AN IMPROVED TECHNIQUE FOR HUMAN FACE RECOGNITION USING IMAGE PROCESSINGAN IMPROVED TECHNIQUE FOR HUMAN FACE RECOGNITION USING IMAGE PROCESSING
AN IMPROVED TECHNIQUE FOR HUMAN FACE RECOGNITION USING IMAGE PROCESSINGijiert bestjournal
 
Criminal Detection System
Criminal Detection SystemCriminal Detection System
Criminal Detection SystemIntrader Amit
 
FACE DETECTION USING PRINCIPAL COMPONENT ANALYSIS
FACE DETECTION USING PRINCIPAL COMPONENT ANALYSISFACE DETECTION USING PRINCIPAL COMPONENT ANALYSIS
FACE DETECTION USING PRINCIPAL COMPONENT ANALYSISIAEME Publication
 
Human Face Detection and Tracking for Age Rank, Weight and Gender Estimation ...
Human Face Detection and Tracking for Age Rank, Weight and Gender Estimation ...Human Face Detection and Tracking for Age Rank, Weight and Gender Estimation ...
Human Face Detection and Tracking for Age Rank, Weight and Gender Estimation ...IJERA Editor
 
Face Recognition Using Gabor features And PCA
Face Recognition Using Gabor features And PCAFace Recognition Using Gabor features And PCA
Face Recognition Using Gabor features And PCAIOSR Journals
 
Facial recognition system
Facial recognition systemFacial recognition system
Facial recognition systemDivya Sushma
 
A study of techniques for facial detection and expression classification
A study of techniques for facial detection and expression classificationA study of techniques for facial detection and expression classification
A study of techniques for facial detection and expression classificationIJCSES Journal
 
International Journal of Engineering Research and Development
International Journal of Engineering Research and DevelopmentInternational Journal of Engineering Research and Development
International Journal of Engineering Research and DevelopmentIJERD Editor
 

Ähnlich wie Eigenface Face Recognition Using Single Sample Images (20)

Study and Analysis of Novel Face Recognition Techniques using PCA, LDA and Ge...
Study and Analysis of Novel Face Recognition Techniques using PCA, LDA and Ge...Study and Analysis of Novel Face Recognition Techniques using PCA, LDA and Ge...
Study and Analysis of Novel Face Recognition Techniques using PCA, LDA and Ge...
 
Implementation of Face Recognition in Cloud Vision Using Eigen Faces
Implementation of Face Recognition in Cloud Vision Using Eigen FacesImplementation of Face Recognition in Cloud Vision Using Eigen Faces
Implementation of Face Recognition in Cloud Vision Using Eigen Faces
 
Face and Eye Detection Varying Scenarios With Haar Classifier_2015
Face and Eye Detection Varying Scenarios With Haar Classifier_2015Face and Eye Detection Varying Scenarios With Haar Classifier_2015
Face and Eye Detection Varying Scenarios With Haar Classifier_2015
 
Improved Approach for Eigenface Recognition
Improved Approach for Eigenface RecognitionImproved Approach for Eigenface Recognition
Improved Approach for Eigenface Recognition
 
Face recognition system
Face recognition systemFace recognition system
Face recognition system
 
Paper id 24201475
Paper id 24201475Paper id 24201475
Paper id 24201475
 
HUMAN FACE RECOGNITION USING IMAGE PROCESSING PCA AND NEURAL NETWORK
HUMAN FACE RECOGNITION USING IMAGE PROCESSING PCA AND NEURAL NETWORKHUMAN FACE RECOGNITION USING IMAGE PROCESSING PCA AND NEURAL NETWORK
HUMAN FACE RECOGNITION USING IMAGE PROCESSING PCA AND NEURAL NETWORK
 
AN IMPROVED TECHNIQUE FOR HUMAN FACE RECOGNITION USING IMAGE PROCESSING
AN IMPROVED TECHNIQUE FOR HUMAN FACE RECOGNITION USING IMAGE PROCESSINGAN IMPROVED TECHNIQUE FOR HUMAN FACE RECOGNITION USING IMAGE PROCESSING
AN IMPROVED TECHNIQUE FOR HUMAN FACE RECOGNITION USING IMAGE PROCESSING
 
Criminal Detection System
Criminal Detection SystemCriminal Detection System
Criminal Detection System
 
FACE DETECTION USING PRINCIPAL COMPONENT ANALYSIS
FACE DETECTION USING PRINCIPAL COMPONENT ANALYSISFACE DETECTION USING PRINCIPAL COMPONENT ANALYSIS
FACE DETECTION USING PRINCIPAL COMPONENT ANALYSIS
 
Human Face Detection and Tracking for Age Rank, Weight and Gender Estimation ...
Human Face Detection and Tracking for Age Rank, Weight and Gender Estimation ...Human Face Detection and Tracking for Age Rank, Weight and Gender Estimation ...
Human Face Detection and Tracking for Age Rank, Weight and Gender Estimation ...
 
Face Recognition Using Gabor features And PCA
Face Recognition Using Gabor features And PCAFace Recognition Using Gabor features And PCA
Face Recognition Using Gabor features And PCA
 
Real time facial expression analysis using pca
Real time facial expression analysis using pcaReal time facial expression analysis using pca
Real time facial expression analysis using pca
 
Facial recognition system
Facial recognition systemFacial recognition system
Facial recognition system
 
50120140504002
5012014050400250120140504002
50120140504002
 
A study of techniques for facial detection and expression classification
A study of techniques for facial detection and expression classificationA study of techniques for facial detection and expression classification
A study of techniques for facial detection and expression classification
 
Paper of Final Year Project.pdf
Paper of Final Year Project.pdfPaper of Final Year Project.pdf
Paper of Final Year Project.pdf
 
D1061825
D1061825D1061825
D1061825
 
International Journal of Engineering Research and Development
International Journal of Engineering Research and DevelopmentInternational Journal of Engineering Research and Development
International Journal of Engineering Research and Development
 
184
184184
184
 

Mehr von sadique_ghitm

Organizational Behaviour
Organizational BehaviourOrganizational Behaviour
Organizational Behavioursadique_ghitm
 
Digital India Initiative
Digital India Initiative Digital India Initiative
Digital India Initiative sadique_ghitm
 
Pumping lemma for regular language
Pumping lemma for regular languagePumping lemma for regular language
Pumping lemma for regular languagesadique_ghitm
 
Entity Relationship Diagrams
Entity Relationship DiagramsEntity Relationship Diagrams
Entity Relationship Diagramssadique_ghitm
 
Data Flow Diagram (DFD)
Data Flow Diagram (DFD)Data Flow Diagram (DFD)
Data Flow Diagram (DFD)sadique_ghitm
 
Detecting HTTP Botnet using Artificial Immune System (AIS)
Detecting HTTP Botnet using Artificial Immune System (AIS)Detecting HTTP Botnet using Artificial Immune System (AIS)
Detecting HTTP Botnet using Artificial Immune System (AIS)sadique_ghitm
 
Handling of Incident, Challenges, Risks, Vulnerability and Implementing Detec...
Handling of Incident, Challenges, Risks, Vulnerability and Implementing Detec...Handling of Incident, Challenges, Risks, Vulnerability and Implementing Detec...
Handling of Incident, Challenges, Risks, Vulnerability and Implementing Detec...sadique_ghitm
 
Face recognition: A Comparison of Appearance Based Approaches
Face recognition: A Comparison of Appearance Based ApproachesFace recognition: A Comparison of Appearance Based Approaches
Face recognition: A Comparison of Appearance Based Approachessadique_ghitm
 
Design and analysis of a mobile file sharing system for opportunistic networks
Design and analysis of a mobile file sharing system for opportunistic networksDesign and analysis of a mobile file sharing system for opportunistic networks
Design and analysis of a mobile file sharing system for opportunistic networkssadique_ghitm
 
A hybrid genetic algorithm and chaotic function model for image encryption
A hybrid genetic algorithm and chaotic function model for image encryptionA hybrid genetic algorithm and chaotic function model for image encryption
A hybrid genetic algorithm and chaotic function model for image encryptionsadique_ghitm
 
A controlled experiment in assessing and estimating software maintenance tasks
A controlled experiment in assessing and estimating software maintenance tasks A controlled experiment in assessing and estimating software maintenance tasks
A controlled experiment in assessing and estimating software maintenance tasks sadique_ghitm
 

Mehr von sadique_ghitm (15)

Attitude
AttitudeAttitude
Attitude
 
Personality
PersonalityPersonality
Personality
 
Organizational Behaviour
Organizational BehaviourOrganizational Behaviour
Organizational Behaviour
 
Digital India Initiative
Digital India Initiative Digital India Initiative
Digital India Initiative
 
Pumping lemma for regular language
Pumping lemma for regular languagePumping lemma for regular language
Pumping lemma for regular language
 
Entity Relationship Diagrams
Entity Relationship DiagramsEntity Relationship Diagrams
Entity Relationship Diagrams
 
Data Flow Diagram (DFD)
Data Flow Diagram (DFD)Data Flow Diagram (DFD)
Data Flow Diagram (DFD)
 
Detecting HTTP Botnet using Artificial Immune System (AIS)
Detecting HTTP Botnet using Artificial Immune System (AIS)Detecting HTTP Botnet using Artificial Immune System (AIS)
Detecting HTTP Botnet using Artificial Immune System (AIS)
 
Handling of Incident, Challenges, Risks, Vulnerability and Implementing Detec...
Handling of Incident, Challenges, Risks, Vulnerability and Implementing Detec...Handling of Incident, Challenges, Risks, Vulnerability and Implementing Detec...
Handling of Incident, Challenges, Risks, Vulnerability and Implementing Detec...
 
Computer Worms
Computer WormsComputer Worms
Computer Worms
 
Face recognition: A Comparison of Appearance Based Approaches
Face recognition: A Comparison of Appearance Based ApproachesFace recognition: A Comparison of Appearance Based Approaches
Face recognition: A Comparison of Appearance Based Approaches
 
Design and analysis of a mobile file sharing system for opportunistic networks
Design and analysis of a mobile file sharing system for opportunistic networksDesign and analysis of a mobile file sharing system for opportunistic networks
Design and analysis of a mobile file sharing system for opportunistic networks
 
A hybrid genetic algorithm and chaotic function model for image encryption
A hybrid genetic algorithm and chaotic function model for image encryptionA hybrid genetic algorithm and chaotic function model for image encryption
A hybrid genetic algorithm and chaotic function model for image encryption
 
A controlled experiment in assessing and estimating software maintenance tasks
A controlled experiment in assessing and estimating software maintenance tasks A controlled experiment in assessing and estimating software maintenance tasks
A controlled experiment in assessing and estimating software maintenance tasks
 
Holographic Memory
Holographic MemoryHolographic Memory
Holographic Memory
 

Kürzlich hochgeladen

4.18.24 Movement Legacies, Reflection, and Review.pptx
4.18.24 Movement Legacies, Reflection, and Review.pptx4.18.24 Movement Legacies, Reflection, and Review.pptx
4.18.24 Movement Legacies, Reflection, and Review.pptxmary850239
 
ClimART Action | eTwinning Project
ClimART Action    |    eTwinning ProjectClimART Action    |    eTwinning Project
ClimART Action | eTwinning Projectjordimapav
 
Textual Evidence in Reading and Writing of SHS
Textual Evidence in Reading and Writing of SHSTextual Evidence in Reading and Writing of SHS
Textual Evidence in Reading and Writing of SHSMae Pangan
 
Keynote by Prof. Wurzer at Nordex about IP-design
Keynote by Prof. Wurzer at Nordex about IP-designKeynote by Prof. Wurzer at Nordex about IP-design
Keynote by Prof. Wurzer at Nordex about IP-designMIPLM
 
How to Add Barcode on PDF Report in Odoo 17
How to Add Barcode on PDF Report in Odoo 17How to Add Barcode on PDF Report in Odoo 17
How to Add Barcode on PDF Report in Odoo 17Celine George
 
ENG 5 Q4 WEEk 1 DAY 1 Restate sentences heard in one’s own words. Use appropr...
ENG 5 Q4 WEEk 1 DAY 1 Restate sentences heard in one’s own words. Use appropr...ENG 5 Q4 WEEk 1 DAY 1 Restate sentences heard in one’s own words. Use appropr...
ENG 5 Q4 WEEk 1 DAY 1 Restate sentences heard in one’s own words. Use appropr...JojoEDelaCruz
 
Choosing the Right CBSE School A Comprehensive Guide for Parents
Choosing the Right CBSE School A Comprehensive Guide for ParentsChoosing the Right CBSE School A Comprehensive Guide for Parents
Choosing the Right CBSE School A Comprehensive Guide for Parentsnavabharathschool99
 
Active Learning Strategies (in short ALS).pdf
Active Learning Strategies (in short ALS).pdfActive Learning Strategies (in short ALS).pdf
Active Learning Strategies (in short ALS).pdfPatidar M
 
The Contemporary World: The Globalization of World Politics
The Contemporary World: The Globalization of World PoliticsThe Contemporary World: The Globalization of World Politics
The Contemporary World: The Globalization of World PoliticsRommel Regala
 
Daily Lesson Plan in Mathematics Quarter 4
Daily Lesson Plan in Mathematics Quarter 4Daily Lesson Plan in Mathematics Quarter 4
Daily Lesson Plan in Mathematics Quarter 4JOYLYNSAMANIEGO
 
Oppenheimer Film Discussion for Philosophy and Film
Oppenheimer Film Discussion for Philosophy and FilmOppenheimer Film Discussion for Philosophy and Film
Oppenheimer Film Discussion for Philosophy and FilmStan Meyer
 
EMBODO Lesson Plan Grade 9 Law of Sines.docx
EMBODO Lesson Plan Grade 9 Law of Sines.docxEMBODO Lesson Plan Grade 9 Law of Sines.docx
EMBODO Lesson Plan Grade 9 Law of Sines.docxElton John Embodo
 
TEACHER REFLECTION FORM (NEW SET........).docx
TEACHER REFLECTION FORM (NEW SET........).docxTEACHER REFLECTION FORM (NEW SET........).docx
TEACHER REFLECTION FORM (NEW SET........).docxruthvilladarez
 
USPS® Forced Meter Migration - How to Know if Your Postage Meter Will Soon be...
USPS® Forced Meter Migration - How to Know if Your Postage Meter Will Soon be...USPS® Forced Meter Migration - How to Know if Your Postage Meter Will Soon be...
USPS® Forced Meter Migration - How to Know if Your Postage Meter Will Soon be...Postal Advocate Inc.
 
Transaction Management in Database Management System
Transaction Management in Database Management SystemTransaction Management in Database Management System
Transaction Management in Database Management SystemChristalin Nelson
 
ICS2208 Lecture6 Notes for SL spaces.pdf
ICS2208 Lecture6 Notes for SL spaces.pdfICS2208 Lecture6 Notes for SL spaces.pdf
ICS2208 Lecture6 Notes for SL spaces.pdfVanessa Camilleri
 
Incoming and Outgoing Shipments in 3 STEPS Using Odoo 17
Incoming and Outgoing Shipments in 3 STEPS Using Odoo 17Incoming and Outgoing Shipments in 3 STEPS Using Odoo 17
Incoming and Outgoing Shipments in 3 STEPS Using Odoo 17Celine George
 
ANG SEKTOR NG agrikultura.pptx QUARTER 4
ANG SEKTOR NG agrikultura.pptx QUARTER 4ANG SEKTOR NG agrikultura.pptx QUARTER 4
ANG SEKTOR NG agrikultura.pptx QUARTER 4MiaBumagat1
 
Field Attribute Index Feature in Odoo 17
Field Attribute Index Feature in Odoo 17Field Attribute Index Feature in Odoo 17
Field Attribute Index Feature in Odoo 17Celine George
 

Kürzlich hochgeladen (20)

4.18.24 Movement Legacies, Reflection, and Review.pptx
4.18.24 Movement Legacies, Reflection, and Review.pptx4.18.24 Movement Legacies, Reflection, and Review.pptx
4.18.24 Movement Legacies, Reflection, and Review.pptx
 
ClimART Action | eTwinning Project
ClimART Action    |    eTwinning ProjectClimART Action    |    eTwinning Project
ClimART Action | eTwinning Project
 
Textual Evidence in Reading and Writing of SHS
Textual Evidence in Reading and Writing of SHSTextual Evidence in Reading and Writing of SHS
Textual Evidence in Reading and Writing of SHS
 
Keynote by Prof. Wurzer at Nordex about IP-design
Keynote by Prof. Wurzer at Nordex about IP-designKeynote by Prof. Wurzer at Nordex about IP-design
Keynote by Prof. Wurzer at Nordex about IP-design
 
How to Add Barcode on PDF Report in Odoo 17
How to Add Barcode on PDF Report in Odoo 17How to Add Barcode on PDF Report in Odoo 17
How to Add Barcode on PDF Report in Odoo 17
 
ENG 5 Q4 WEEk 1 DAY 1 Restate sentences heard in one’s own words. Use appropr...
ENG 5 Q4 WEEk 1 DAY 1 Restate sentences heard in one’s own words. Use appropr...ENG 5 Q4 WEEk 1 DAY 1 Restate sentences heard in one’s own words. Use appropr...
ENG 5 Q4 WEEk 1 DAY 1 Restate sentences heard in one’s own words. Use appropr...
 
Choosing the Right CBSE School A Comprehensive Guide for Parents
Choosing the Right CBSE School A Comprehensive Guide for ParentsChoosing the Right CBSE School A Comprehensive Guide for Parents
Choosing the Right CBSE School A Comprehensive Guide for Parents
 
Active Learning Strategies (in short ALS).pdf
Active Learning Strategies (in short ALS).pdfActive Learning Strategies (in short ALS).pdf
Active Learning Strategies (in short ALS).pdf
 
Paradigm shift in nursing research by RS MEHTA
Paradigm shift in nursing research by RS MEHTAParadigm shift in nursing research by RS MEHTA
Paradigm shift in nursing research by RS MEHTA
 
The Contemporary World: The Globalization of World Politics
The Contemporary World: The Globalization of World PoliticsThe Contemporary World: The Globalization of World Politics
The Contemporary World: The Globalization of World Politics
 
Daily Lesson Plan in Mathematics Quarter 4
Daily Lesson Plan in Mathematics Quarter 4Daily Lesson Plan in Mathematics Quarter 4
Daily Lesson Plan in Mathematics Quarter 4
 
Oppenheimer Film Discussion for Philosophy and Film
Oppenheimer Film Discussion for Philosophy and FilmOppenheimer Film Discussion for Philosophy and Film
Oppenheimer Film Discussion for Philosophy and Film
 
EMBODO Lesson Plan Grade 9 Law of Sines.docx
EMBODO Lesson Plan Grade 9 Law of Sines.docxEMBODO Lesson Plan Grade 9 Law of Sines.docx
EMBODO Lesson Plan Grade 9 Law of Sines.docx
 
TEACHER REFLECTION FORM (NEW SET........).docx
TEACHER REFLECTION FORM (NEW SET........).docxTEACHER REFLECTION FORM (NEW SET........).docx
TEACHER REFLECTION FORM (NEW SET........).docx
 
USPS® Forced Meter Migration - How to Know if Your Postage Meter Will Soon be...
USPS® Forced Meter Migration - How to Know if Your Postage Meter Will Soon be...USPS® Forced Meter Migration - How to Know if Your Postage Meter Will Soon be...
USPS® Forced Meter Migration - How to Know if Your Postage Meter Will Soon be...
 
Transaction Management in Database Management System
Transaction Management in Database Management SystemTransaction Management in Database Management System
Transaction Management in Database Management System
 
ICS2208 Lecture6 Notes for SL spaces.pdf
ICS2208 Lecture6 Notes for SL spaces.pdfICS2208 Lecture6 Notes for SL spaces.pdf
ICS2208 Lecture6 Notes for SL spaces.pdf
 
Incoming and Outgoing Shipments in 3 STEPS Using Odoo 17
Incoming and Outgoing Shipments in 3 STEPS Using Odoo 17Incoming and Outgoing Shipments in 3 STEPS Using Odoo 17
Incoming and Outgoing Shipments in 3 STEPS Using Odoo 17
 
ANG SEKTOR NG agrikultura.pptx QUARTER 4
ANG SEKTOR NG agrikultura.pptx QUARTER 4ANG SEKTOR NG agrikultura.pptx QUARTER 4
ANG SEKTOR NG agrikultura.pptx QUARTER 4
 
Field Attribute Index Feature in Odoo 17
Field Attribute Index Feature in Odoo 17Field Attribute Index Feature in Odoo 17
Field Attribute Index Feature in Odoo 17
 

Eigenface Face Recognition Using Single Sample Images

  • 1. A STUDY ON FACE RECOGNITION TECHNIQUE BASED ON EIGENFACE By: Sadique Nayeem Pondicherry University
  • 3. Overview Face recognition system consist of three component.  Face Representation: How to model a face?  Template-based approaches  Feature-based approaches  Appearance-based approaches  Face Detection: To locate a face in image.  Manipulation of images in “face space”  Utilization of elliptical shape of human head  Face Identification: Compare given image with database.  Performance affected by scale, pose, illumination, facial expression, and disguise, etc. 3
  • 4. Eigenfaces Approach  In the language of information theory…  the main objective is to mine the relevant information in a face image, encode it as efficiently as possible and compare one face encoding with a database of face images encoded in the same process.  In mathematical terms…  Find the principal components of the face distribution, or the eigenvectors of the covariance matrix of the set of face images, called e ig e nface s.  Eigenfaces are a set of features that characterize the variation between face images. Each training face image can be represented in terms of a linear combination of the eigenfaces, so can the new input image.  Compare the feature weights of the new input image with those of the known individuals 4
  • 5. Eigenface Initialization The eigenfaces approach for face recognition involves the following initialization operations:  Acquire a set of training images.  Calculate the eigenfaces from the training set, keeping only the best M images with the highest eigenvalues. These M images define the “face space”. As new faces are experienced, the eigenfaces can be updated.  Calculate the corresponding distribution in M-dimensional weight space for each known individual (training image), by projecting their face images onto the face space. 5
  • 6. Eigenface Recognition Having initialized the system, the following steps are used to recognize new face images:  Given an image to be recognized, calculate a set of weights of the Meigenfaces by projecting it onto each of the eigenfaces.  Determine if the image is a face at all by checking to see if the image is sufficiently close to the face space.  If it is a face, classify the weight pattern as either a known person or as unknown. 6 Figure : Eigenfaces of Essex face database -'face94'
  • 7. Image Database Name of database Source Image format Image size Image type Number of unique individual Total numbe rof images Variations Sample Image IFD IIT Kanpur [3] JPG 110 X 75 Color 60 660 8 pose, 3 emotion Essex face databas e -face94 University of Essex, UK [4] JPG 90 X 100 Color 152 3040 facial expression, slight head tilt. Yale Yale university [5] GIF 320 X 243 Grey 15 165 facial expression, w/o glasses Face 1999 California Institute of Technolo gy [6] JPG 300X198 Color 26 450 lighting, expression, background 7
  • 8. Experimental Result 8 Eigenface face recognition with different sample images Name of databas e Total No. of unique person No. of samples of each image in training set No. of image in training set No. of False recognition Accuracy rate (%) IFD 60 1 60 31 49.18 2 120 25 59.01 3 180 16 73.77 4 240 16 73.77 5 300 12 80.32 6 360 8 86.88 7 420 3 95.08 8 480 2 96.72 9 540 1 98.36 10 600 1 98.36 11 660 1 98.36 Esse x face 152 1 152 47 69.07 2 304 29 80.92 3 456 12 92.10 4 608 11 92.76 5 760 11 92.76 6 912 10 93.42 7 1064 10 93.42 8 1216 9 94.07 9 1368 8 94.73 10 1520 8 94.73 11 1672 6 96.05 Yale 15 1 15 8 46.66 2 30 2 86.66 3 45 3 80.00 4 60 3 80.00 5 75 2 86.66 6 90 1 93.33 7 105 2 86.66 8 120 1 93.33 9 135 1 93.33 10 150 1 93.33 11 165 1 93.33 Face 1999 26 1 26 17 34.61 2 52 15 42.30 3 78 14 46.15 4 104 9 65.38 5 130 9 65.38 6 156 8 69.23 7 182 5 80.76 8 208 5 80.76 9 234 3 88.46 10 260 2 92.30 11 286 1 96.15 Eigenface face recognition with different sample images Name of databas e Total No. of unique person No. of samples of each image in training set No. of image in training set No. of False recognition Accuracy rate (%)
  • 10. Future Enhancement  According to the experimental result, recognition with one sample per person does not give better recognition rate in all cases.  But, in real time application only one sample per person will be available ( as in case of voter card, Driving license, passport or ADHAAR Card).  So, recognition from single sample per person is needed.  One sample per person is easy to collect, save storage cost and save computational cost. 10 Courtesy: http://images.google.co.in/
  • 11. Problem Statement  This problem can be defined as follows: “Given a stored database of faces with only one image per person, the goal is to identify a person from the database later in time in any different and unpredictable poses, lighting, disguise, etc from the individual image.” 11
  • 12. Proposed Idea  1.2 billion population of India is being enrolled for ADHAAR Card with different biometric.  Face image is also being collected.  The ADHAAR Card or UID no. can be used as a platform on which different application can be developed as under: 12 ADHAAR CARD or UID NUMBER
  • 13. Proposed Idea (contd.)  To restrain the crime, ADHAAR Card can be the best source for identification.  Individual images in ADHAAR Card may work as training set.  CCTV images from crime scene can be used as test image.  Procedure:  Capture the video from the CCTV camera.  Detect the human face in the CCTV video.  Take the CCTV image as the test image.  Do the preprocessing on the CCTV image i.e  Crop both the eyes, eyebrow, nose, and mouth.  Load the ADHAAR based Face image as the training image  Crop both the eyes, eyebrow, nose, and mouth  Apply the Eigenface PCA for the Recognition 13
  • 14. Conclusions  Eigenface PCA is one of the most successful technique and it gives better result for more number of samples in training set.  It does not produce good result for single sample per person.  The need for real time application can be given by only single sample per person.  Taking ADHAAR Card as a platform, Artificial Face Recognition system can be developed by using PCA on reconstructed image. 14
  • 15. Reference 1. “Eigenfaces for recognition”, M. Turk and A. Pentland, Jo urnalo f Co g nitive Ne uro scie nce , vo l. 3, No . 1 , 1 9 9 1 2. “Automatic recognition and analysis of human faces and facial expressions: A survey”, A. Samal and P. A. Iyengar, Patte rn Re co g nitio n, 25(1 ): 6 5-7 7 , 1 9 9 2 3. “The Indian Face Database”, Vidit Jain, Amitabha Mukherjee, 2002, http://vis- www. cs. um ass. e du/~ vidit/IndianFace Database / 4. “Essex face database -face94”, University of Essex, UK, http: //cswww. e sse x. ac. uk/m v/allface s/inde x. htm l 5. “Yale Database”, http: //cvc. yale . e du/pro je cts/yale face s/yale face s. htm l 6. “FACE 1999”, http: //www. visio n. calte ch. e du/htm l-file s/archive . htm l 15