SlideShare a Scribd company logo
1 of 44
Advanced Eigenface
Face Recognition System
Peixi Xiong
Northwestern University
Background
• Facial Recognition is widely used since its convenience.
Motivation
Problems:
• Low Recognition Rate
• Time Consuming
Motivation
• Database in Varying Pose
• Lack of Illumination
• Glasses Interferences
• Database in Larger scale
Advantage and Drawback of the PCA Face
Recognition
• Advantage
• Drawback
Drawback
• Time Consuming
• Varying Pose and Illumination
• Frontal Views/Face Expression and Disguise
Brief Analysis of the Database and the
Original System
• Good Illumination
• Varying Pose (Tilted Face )
• NOT Only the Frontal Views
Close All
Traversing the
File
Check
Toolbox
Build Face
Part Detector
Crop the Face
There is a
Face
Check if it is
Frontal Face
Yes, it is
Frontal Face
Check if it is
tilted
Yes, it is a
Tilted Face
Output
No, it is not.
Do Rotation
Output
Illumination
Correction*
Glasses
Removal
No, it is Side
Face
Drop It
There is no
Face
Drop It
The Pre-Processing
System
Build Face Part Detector/Crop the Face
• Output the Face Boundary, Left eye Boundary, Right eye Boundary,
Mouth Boundary and Nose Boundary
• The relevant information is included in the documentation of Matlab,
vision.CascadeObjectDetector System object.
Close All
Traversing the
File
Check
Toolbox
Build Face
Part Detector
Crop the Face
There is a
Face
Check if it is
Frontal Face
Yes, it is
Frontal Face
Check if it is
tilted
Yes, it is a
Tilted Face
Output
No, it is not.
Do Rotation
Output
Illumination
Correction*
Glasses
Removal
No, it is Side
Face
Drop It
There is no
Face
Drop It
The Pre-Processing
System
Detect If It Is Frontal Face
• Detect Box
• Check if Two Eyes Boxes Exist
• Location of Mouth & Nose
Details-Types of Side Faces
The Second Type
• Get Vertical Center of Mouth and Nose
• Calculate Absolute Distance of Two Middle Lines
• ‘Relative’ Distance
Relative Distance = Absolute Distance/ Face Width
• Set Threshold
Close All
Traversing the
File
Check
Toolbox
Build Face
Part Detector
Crop the Face
There is a
Face
Check if it is
Frontal Face
Yes, it is
Frontal Face
Check if it is
tilted
Yes, it is a
Tilted Face
Output
No, it is not.
Do Rotation
Output
Illumination
Correction*
Glasses
Removal
No, it is Side
Face
Drop It
There is no
Face
Drop It
The Pre-Processing
System
• Check Location of Left Eye&Right Eye
(the boundary box)
• Get Center points
• Link
• Check the Angle
• imrotate()
• Rebuild Face Part Detector&Recrop the Face
Detect If It Is Tilted Face
Close All
Traversing the
File
Check
Toolbox
Build Face
Part Detector
Crop the Face
There is a
Face
Check if it is
Frontal Face
Yes, it is
Frontal Face
Check if it is
tilted
Yes, it is a
Tilted Face
Output
No, it is not.
Do Rotation
Output
Illumination
Correction*
Glasses
Removal
No, it is Side
Face
Drop It
There is no
Face
Drop It
The Pre-Processing
System
Illumination-Correction
• 𝐼 𝑚, 𝑛 = 𝑅 𝑚, 𝑛 𝐿(𝑚, 𝑛)
• Low Frequency Component & High Frequency Component
• DCT Normalization (Discrete Cosine Transform Normalization)
• log 𝐼 𝑚, 𝑛 = log 𝑅 𝑚, 𝑛 + log 𝐿(𝑚, 𝑛))
K. P. Horn, Robot Vision. Cambridge, MA: MIT Press, 1986.
Details
• Installation
• Do Image Histogram Normalization
• Create & Save Zigzag Map
• Transform to Logarithm & Frequency Domains
• Set Zero to the Relevant Coefficient
• Inverse DCT
• Post-Processing
Result
Part II
Preprocessing
• Crop the face[1]
• Convert RGB to Grayscale
Edge Detection
• Not Continuous
Fill
• Fill the eyeglasses inner part
• Why ?
• Some flaw on edge detection
Method -- Imfill
• How to Compensate?
Method--dilate
• Expand the mask
Possible problem
• Nose
• Mouth
• Hair
• Other flaws
• delete the parts
Compensate
• Recover masked skin
• Smooth
Recover Masked Skin
• Get mean within 5*5 box
• Special case:
• Not only one pixel in box
• Recursively find the other pixels’ mean
Find Masked Pixel
Get Mean Value
Recursion
Ignore the
Recursion
=
Recover & Smooth
• Gaussian filter
Question?
• How to remove wrong mask
Skin Color Detection:
Lighting
Compensation
Color
Transformastion
Skin Color Detection
Variance-based
Segmentation
Component
Grouping
Face Boundary
Detection
Resize Graph
Comparing
Experimental Results Analysis
• ROC Curve
• CMC Curve
ROC Curve
ROC Curve of advanced
system is closer to the
broader than original system
CMC Curve
CMC Curve of advanced
system is closer to broader
than traditional system.
Main Work
• Delete Side-face
• Crop Face
• Tiled-face Rotation
• Illumination Correction
• Glasses Removal
• Properties Analysis
Q&A
Thank you!

More Related Content

Similar to Advanced Recognition System

Detection and recognition of face using neural network
Detection and recognition of face using neural networkDetection and recognition of face using neural network
Detection and recognition of face using neural networkSmriti Tikoo
 
Root Cause Analysis - Tools, Tips and Tricks to Get to the Bottom of Root Cause
Root Cause Analysis - Tools, Tips and Tricks to Get to the Bottom of Root CauseRoot Cause Analysis - Tools, Tips and Tricks to Get to the Bottom of Root Cause
Root Cause Analysis - Tools, Tips and Tricks to Get to the Bottom of Root CauseCraig Thornton
 
Stereo matching for 2d face recognition
Stereo  matching  for  2d  face  recognitionStereo  matching  for  2d  face  recognition
Stereo matching for 2d face recognitionstudent
 
Benchmarking: You're Doing It Wrong (StrangeLoop 2014)
Benchmarking: You're Doing It Wrong (StrangeLoop 2014)Benchmarking: You're Doing It Wrong (StrangeLoop 2014)
Benchmarking: You're Doing It Wrong (StrangeLoop 2014)Aysylu Greenberg
 
Image Processing Introduction
Image Processing IntroductionImage Processing Introduction
Image Processing IntroductionAhmed Gad
 
Lecture 10 ming yang - face recognition systems
Lecture 10   ming yang - face recognition systemsLecture 10   ming yang - face recognition systems
Lecture 10 ming yang - face recognition systemsmustafa sarac
 
Facial recognition locker for android
Facial recognition locker for androidFacial recognition locker for android
Facial recognition locker for androidkonark jain
 
Poka yoke error proofing
Poka yoke error proofing Poka yoke error proofing
Poka yoke error proofing ssusercee91d
 
Video Face Recognition , Pattern Recognition Final Report
Video Face Recognition , Pattern Recognition Final ReportVideo Face Recognition , Pattern Recognition Final Report
Video Face Recognition , Pattern Recognition Final ReportWin Yu
 
Kadir Akdeniz - Dynamic, Adaptive and Personalized User Interface for Communi...
Kadir Akdeniz - Dynamic, Adaptive and Personalized User Interface for Communi...Kadir Akdeniz - Dynamic, Adaptive and Personalized User Interface for Communi...
Kadir Akdeniz - Dynamic, Adaptive and Personalized User Interface for Communi...Kadir Akdeniz
 
Lecture 01 frank dellaert - 3 d reconstruction and mapping: a factor graph ...
Lecture 01   frank dellaert - 3 d reconstruction and mapping: a factor graph ...Lecture 01   frank dellaert - 3 d reconstruction and mapping: a factor graph ...
Lecture 01 frank dellaert - 3 d reconstruction and mapping: a factor graph ...mustafa sarac
 
Face Detection techniques
Face Detection techniquesFace Detection techniques
Face Detection techniquesAbhineet Bhamra
 
Automatic Generation Cleaning & Generalization of 50 Contours for NRCan's Geo...
Automatic Generation Cleaning & Generalization of 50 Contours for NRCan's Geo...Automatic Generation Cleaning & Generalization of 50 Contours for NRCan's Geo...
Automatic Generation Cleaning & Generalization of 50 Contours for NRCan's Geo...Safe Software
 

Similar to Advanced Recognition System (20)

Detection and recognition of face using neural network
Detection and recognition of face using neural networkDetection and recognition of face using neural network
Detection and recognition of face using neural network
 
TPI Kaizen Event
TPI Kaizen EventTPI Kaizen Event
TPI Kaizen Event
 
Cvpr2018 face recognition
Cvpr2018 face recognitionCvpr2018 face recognition
Cvpr2018 face recognition
 
Root Cause Analysis - Tools, Tips and Tricks to Get to the Bottom of Root Cause
Root Cause Analysis - Tools, Tips and Tricks to Get to the Bottom of Root CauseRoot Cause Analysis - Tools, Tips and Tricks to Get to the Bottom of Root Cause
Root Cause Analysis - Tools, Tips and Tricks to Get to the Bottom of Root Cause
 
Root Cause Analysis تحليل أسباب جذور المشكلة
Root Cause Analysis تحليل أسباب جذور المشكلةRoot Cause Analysis تحليل أسباب جذور المشكلة
Root Cause Analysis تحليل أسباب جذور المشكلة
 
Face recognition
Face recognition Face recognition
Face recognition
 
Final year ppt
Final year pptFinal year ppt
Final year ppt
 
Stereo matching for 2d face recognition
Stereo  matching  for  2d  face  recognitionStereo  matching  for  2d  face  recognition
Stereo matching for 2d face recognition
 
Benchmarking: You're Doing It Wrong (StrangeLoop 2014)
Benchmarking: You're Doing It Wrong (StrangeLoop 2014)Benchmarking: You're Doing It Wrong (StrangeLoop 2014)
Benchmarking: You're Doing It Wrong (StrangeLoop 2014)
 
Image Processing Introduction
Image Processing IntroductionImage Processing Introduction
Image Processing Introduction
 
Lecture 10 ming yang - face recognition systems
Lecture 10   ming yang - face recognition systemsLecture 10   ming yang - face recognition systems
Lecture 10 ming yang - face recognition systems
 
Facial recognition locker for android
Facial recognition locker for androidFacial recognition locker for android
Facial recognition locker for android
 
Poka yoke error proofing
Poka yoke error proofing Poka yoke error proofing
Poka yoke error proofing
 
Physics artifacts
Physics artifactsPhysics artifacts
Physics artifacts
 
Video Face Recognition , Pattern Recognition Final Report
Video Face Recognition , Pattern Recognition Final ReportVideo Face Recognition , Pattern Recognition Final Report
Video Face Recognition , Pattern Recognition Final Report
 
Kadir Akdeniz - Dynamic, Adaptive and Personalized User Interface for Communi...
Kadir Akdeniz - Dynamic, Adaptive and Personalized User Interface for Communi...Kadir Akdeniz - Dynamic, Adaptive and Personalized User Interface for Communi...
Kadir Akdeniz - Dynamic, Adaptive and Personalized User Interface for Communi...
 
Lecture 01 frank dellaert - 3 d reconstruction and mapping: a factor graph ...
Lecture 01   frank dellaert - 3 d reconstruction and mapping: a factor graph ...Lecture 01   frank dellaert - 3 d reconstruction and mapping: a factor graph ...
Lecture 01 frank dellaert - 3 d reconstruction and mapping: a factor graph ...
 
Astigcorrection
AstigcorrectionAstigcorrection
Astigcorrection
 
Face Detection techniques
Face Detection techniquesFace Detection techniques
Face Detection techniques
 
Automatic Generation Cleaning & Generalization of 50 Contours for NRCan's Geo...
Automatic Generation Cleaning & Generalization of 50 Contours for NRCan's Geo...Automatic Generation Cleaning & Generalization of 50 Contours for NRCan's Geo...
Automatic Generation Cleaning & Generalization of 50 Contours for NRCan's Geo...
 

Advanced Recognition System