SlideShare ist ein Scribd-Unternehmen logo
1 von 25
Downloaden Sie, um offline zu lesen
Two Feature Extraction Methods

            Lian, Xiaochen
        skylian1985@163.com

       Department of Computer Science
        Shanghai Jiao Tong University


              July 13, 2007




        Lian, Xiaochen   Two Feature Extraction Methods
Attention Based Method
                   Statistics Based Method


Outline



  1   Attention Based Method
        Why Attention?
        Model of Attention
        Application in Face Recognition


  2   Statistics Based Method
        Basic Idea
        Feature Selection Process




                           Lian, Xiaochen    Two Feature Extraction Methods
Why Attention?
                   Attention Based Method
                                             Model of Attention
                   Statistics Based Method
                                             Application in Face Recognition


Outline



  1   Attention Based Method
        Why Attention?
        Model of Attention
        Application in Face Recognition


  2   Statistics Based Method
        Basic Idea
        Feature Selection Process




                           Lian, Xiaochen    Two Feature Extraction Methods
Why Attention?
                  Attention Based Method
                                            Model of Attention
                  Statistics Based Method
                                            Application in Face Recognition


Why Attention?




  When recognizing a person, we compare the face with those
  stored in memory. We always can not remember all the details of a
  face. It is the conspicuous parts that impress themselves on us.




                          Lian, Xiaochen    Two Feature Extraction Methods
Why Attention?
                  Attention Based Method
                                            Model of Attention
                  Statistics Based Method
                                            Application in Face Recognition


Model of Attention
  How do human vision system ïŹnd salient regions in a scene? Koch
  and Ullman[?] proposed a biologically plausible architecture.




               Figure: General architecture ofExtraction Methods
                        Lian, Xiaochen Two Feature
                                                   the model
Why Attention?
                   Attention Based Method
                                              Model of Attention
                   Statistics Based Method
                                              Application in Face Recognition


Channels
  The original image is decomposed into three channels.
      Intensity I : Consider the brightness of a pixel, which is
      obtained as I = (r + g + b)/3.
      Color: Red-Green color and Blue-Yellow opponencies.
                                                r−g
                               RG =
                                             max(r, g, b)
                                             b − min(r, g)
                               BY =
                                             max(r, g, b)


      Orientation: Four orientation channels correspond to gabor
      ïŹlters oriented at 0, 45, 90, and 135 degrees. This
      representation is able to capture the critical distinctions in
      orientation.
                           Lian, Xiaochen     Two Feature Extraction Methods
Why Attention?
           Attention Based Method
                                     Model of Attention
           Statistics Based Method
                                     Application in Face Recognition


Channels




                       Figure: Channels
                   Lian, Xiaochen    Two Feature Extraction Methods
Why Attention?
                    Attention Based Method
                                              Model of Attention
                    Statistics Based Method
                                              Application in Face Recognition


Image Pyramid



  The Gaussian pyramid is created to a depth of nine levels, with
  level 0 having a scale of 1 : 1 (the original input image) and level 8
  being 1 : 256. This is done by ïŹltering the images with gaussian
  ïŹlter and then resize it. We use gaussian ïŹlter to eliminate noise,
  and the resizing is for biological purpose.
  There are seven pyramids, one for intensity MI , two for color MRG
  and MBY , and four for orientation MΞ (Ξ ∈ {0, 45, 90, 135}).




                            Lian, Xiaochen    Two Feature Extraction Methods
Why Attention?
            Attention Based Method
                                      Model of Attention
            Statistics Based Method
                                      Application in Face Recognition


Image Pyramid




                    Figure: Image pyramid
                    Lian, Xiaochen    Two Feature Extraction Methods
Why Attention?
                   Attention Based Method
                                             Model of Attention
                   Statistics Based Method
                                             Application in Face Recognition


Center Surround Difference
  It is a cross-scale difference between two images, denoted by “ ”:
  expanding the smaller image into the larger one by interpolation,
  then followed by pixel-pixel substraction.




                   Figure: Center Surround Difference


                           Lian, Xiaochen    Two Feature Extraction Methods
Why Attention?
                Attention Based Method
                                          Model of Attention
                Statistics Based Method
                                          Application in Face Recognition


Normalization




                     Figure: Normalization effect




                        Lian, Xiaochen    Two Feature Extraction Methods
Why Attention?
                   Attention Based Method
                                             Model of Attention
                   Statistics Based Method
                                             Application in Face Recognition


Normalization
  Difference-of-Gaussians ïŹlter is usually used to detect blob.
                       c2 −(x2 +y2 )/(2σ2 )   c2
                                                    e−(x +y )/(2σinh )
                                                        2  2     2
        DoG(x, y) =     ex
                          2
                            e           ex −   inh
                                                 2
                      2πσex                  2πσinh




                           Lian, Xiaochen    Two Feature Extraction Methods
Why Attention?
                   Attention Based Method
                                             Model of Attention
                   Statistics Based Method
                                             Application in Face Recognition


Saliency Map
  Combine the images from all the channels linearly.




                            Figure: Saliency Map
                           Lian, Xiaochen    Two Feature Extraction Methods
Why Attention?
                 Attention Based Method
                                           Model of Attention
                 Statistics Based Method
                                           Application in Face Recognition




Figure: Faces and the corresponding saliency Map(from ORL face
database)


                         Lian, Xiaochen    Two Feature Extraction Methods
Why Attention?
             Attention Based Method
                                       Model of Attention
             Statistics Based Method
                                       Application in Face Recognition


Experiment Result




                         Figure: Error rate




                     Figure: Rank error rate


                     Lian, Xiaochen    Two Feature Extraction Methods
Why Attention?
                 Attention Based Method
                                           Model of Attention
                 Statistics Based Method
                                           Application in Face Recognition


Lots of Problems!




     How to do recognition? Different people have different sets of
     features. Simply applying Euclid Distance yields bad
     performance: the error rate is high for a 40-person database.
     The performance suffers pose and expression severely.




                         Lian, Xiaochen    Two Feature Extraction Methods
Attention Based Method    Basic Idea
                   Statistics Based Method   Feature Selection Process


Outline



  1   Attention Based Method
        Why Attention?
        Model of Attention
        Application in Face Recognition


  2   Statistics Based Method
        Basic Idea
        Feature Selection Process




                           Lian, Xiaochen    Two Feature Extraction Methods
Attention Based Method    Basic Idea
                      Statistics Based Method   Feature Selection Process


Basic Idea



  Suppose S = {x1 , x2 , · · · , xn } be n features for the collected data.
  The objective of feature selection is to ïŹnd a subset
  Sd = {xi1 , xi2 , · · · , xid }, which sufïŹce to represent the original data.
  The performance of Sd can be evaluated by the percentage of the
  variation in xi that can be accounted for by the elements by Sd . If
  that percentage is large enough, Sd can then be the ïŹnal choice;
  otherwise, new signiïŹcant variables need to be added into Sd .




                              Lian, Xiaochen    Two Feature Extraction Methods
Attention Based Method      Basic Idea
                    Statistics Based Method     Feature Selection Process


Feature Similarity Measure


  The squared-correlation coefïŹcient between two random vectors x
  and y is
                                                (xt y)2
                              sc(x, y) =                   .
                                              (xt x)(yt y)
  This measure has the following properties:
      0 ≀ |sc(x, y)| ≀ 1.
      |sc(x, y)| if and only if x and y are linearly related.
      The measure is invariant to scaling and translation.
      The measure is sensitive to rotation.




                            Lian, Xiaochen      Two Feature Extraction Methods
Attention Based Method         Basic Idea
                     Statistics Based Method        Feature Selection Process


Step-By-Step Selection




  At the ïŹrst step, let
                                               i=1 sc(xi , xj )
                                               n
                              Cj,1 =                              ,
                                                    n
                                i1 = arg max {Cj,1 }.
                                               1≀j≀n

  Select xi1 as the ïŹrst signiïŹcant variable.




                             Lian, Xiaochen         Two Feature Extraction Methods
Attention Based Method        Basic Idea
                    Statistics Based Method       Feature Selection Process


Step-By-Step Selection

  Assume the ïŹrst m − 1 most signiïŹcant variables, z1 , · · · , zm−1 , has
  been chosen. The m-th signiïŹcant feature zm will be chosen in such
  a manner: The subset Sm−1 + {zm } should be the most
  representative subset compared with any other subsets formed by
  adding a candidate feature to Sm−1 .
  Let αj ∈ S − Sm−1 and

                                              i=1 sc(xi , αj )
                                              n
                             Cj,m =                              ,
                                                   n

                              im = arg max {Cj,m }.
                                              1≀j≀n

  The m-th signiïŹcant feature can then be xim .


                            Lian, Xiaochen        Two Feature Extraction Methods
Attention Based Method    Basic Idea
Statistics Based Method   Feature Selection Process




        Lian, Xiaochen    Two Feature Extraction Methods
Attention Based Method    Basic Idea
                 Statistics Based Method   Feature Selection Process


Some Discussion



     The squared-correlation coefïŹcient is used to measure the
     linear correlation between variables. Need new method for
     nonlinear relationships.
     The greedy search process do not assure the optimal
     selection.
     The complexity is O(n2 N), where n is the number of features,
     and N is the number of samples. When n become large, the
     algorithm will be inefïŹcient.




                         Lian, Xiaochen    Two Feature Extraction Methods
Attention Based Method    Basic Idea
              Statistics Based Method   Feature Selection Process




C. Koch, and S. Ullman, “Shifts in Selective Visual Attention:
Towards the Underlying Neural Circuitry,” Human Neurobiology, vol.
4, pp. 219-227, 1985. pp. 89-102, 1977.

Laurent Itti, and Christof Koch, “A saliency-based search mechanism
for overt and covert shitfs of visual attention,” Vision Research,
40(2000).

Dirk Walther, and Christof Koch, “Modeling attention to salient
proto-objects,” Neural Networks, 19(2006).

Laurent Itti, Christof Koch, and Ernst Niebur, “A Model of
Saliency-Based Visual Attention for Rapid Scene Analysis,” IEEE
Trans. Pattern Analysis and Machine Intelligence, vol. 20, No. 11,
Nov. 1998.



                      Lian, Xiaochen    Two Feature Extraction Methods
Attention Based Method    Basic Idea
             Statistics Based Method   Feature Selection Process




Hua-Liang, and Stephen A. Billings, “Feature Subset Selection
and Ranking for Data Dimensionality Reduction,” IEEE Trans.
Pattern Analysis and Machine Intelligence, vol. 29, no.1, Jan.
2007.
Pabitra Mitra, C.A. Mrthy, and Sankar K. Pal “Unsupervised
Feature Selection Using Feature Similarity,” IEEE Trans.
Pattern Analysis and Machine Intelligence, vol. 24, No. 3, Mar.
2002.




                     Lian, Xiaochen    Two Feature Extraction Methods

Weitere Àhnliche Inhalte

Was ist angesagt?

Image feature extraction
Image feature extractionImage feature extraction
Image feature extractionRushin Shah
 
U-Netpresentation.pptx
U-Netpresentation.pptxU-Netpresentation.pptx
U-Netpresentation.pptxNoorUlHaq47
 
Support Vector Machine - How Support Vector Machine works | SVM in Machine Le...
Support Vector Machine - How Support Vector Machine works | SVM in Machine Le...Support Vector Machine - How Support Vector Machine works | SVM in Machine Le...
Support Vector Machine - How Support Vector Machine works | SVM in Machine Le...Simplilearn
 
Transfer Learning and Fine-tuning Deep Neural Networks
 Transfer Learning and Fine-tuning Deep Neural Networks Transfer Learning and Fine-tuning Deep Neural Networks
Transfer Learning and Fine-tuning Deep Neural NetworksPyData
 
Machine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural NetworksMachine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural NetworksFrancesco Collova'
 
Deep neural networks
Deep neural networksDeep neural networks
Deep neural networksSi Haem
 
Deep Learning Tutorial
Deep Learning TutorialDeep Learning Tutorial
Deep Learning TutorialAmr Rashed
 
Object recognition
Object recognitionObject recognition
Object recognitionsaniacorreya
 
Deep Learning: Application & Opportunity
Deep Learning: Application & OpportunityDeep Learning: Application & Opportunity
Deep Learning: Application & OpportunityiTrain
 
Object detection with deep learning
Object detection with deep learningObject detection with deep learning
Object detection with deep learningSushant Shrivastava
 
Image classification with Deep Neural Networks
Image classification with Deep Neural NetworksImage classification with Deep Neural Networks
Image classification with Deep Neural NetworksYogendra Tamang
 
Region based segmentation
Region based segmentationRegion based segmentation
Region based segmentationramya marichamy
 
Overview of Convolutional Neural Networks
Overview of Convolutional Neural NetworksOverview of Convolutional Neural Networks
Overview of Convolutional Neural Networksananth
 
Introduction to Machine Learning Classifiers
Introduction to Machine Learning ClassifiersIntroduction to Machine Learning Classifiers
Introduction to Machine Learning ClassifiersFunctional Imperative
 
Image processing fundamentals
Image processing fundamentalsImage processing fundamentals
Image processing fundamentalsA B Shinde
 
Deep Learning in Computer Vision
Deep Learning in Computer VisionDeep Learning in Computer Vision
Deep Learning in Computer VisionSungjoon Choi
 
Dip Image Segmentation
Dip Image SegmentationDip Image Segmentation
Dip Image SegmentationMubbasher Khaliq
 
Support vector machine
Support vector machineSupport vector machine
Support vector machineRishabh Gupta
 

Was ist angesagt? (20)

Image feature extraction
Image feature extractionImage feature extraction
Image feature extraction
 
U-Netpresentation.pptx
U-Netpresentation.pptxU-Netpresentation.pptx
U-Netpresentation.pptx
 
Support Vector Machine - How Support Vector Machine works | SVM in Machine Le...
Support Vector Machine - How Support Vector Machine works | SVM in Machine Le...Support Vector Machine - How Support Vector Machine works | SVM in Machine Le...
Support Vector Machine - How Support Vector Machine works | SVM in Machine Le...
 
Transfer Learning and Fine-tuning Deep Neural Networks
 Transfer Learning and Fine-tuning Deep Neural Networks Transfer Learning and Fine-tuning Deep Neural Networks
Transfer Learning and Fine-tuning Deep Neural Networks
 
Machine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural NetworksMachine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural Networks
 
Deep neural networks
Deep neural networksDeep neural networks
Deep neural networks
 
Deep Learning Tutorial
Deep Learning TutorialDeep Learning Tutorial
Deep Learning Tutorial
 
Object recognition
Object recognitionObject recognition
Object recognition
 
Deep Learning: Application & Opportunity
Deep Learning: Application & OpportunityDeep Learning: Application & Opportunity
Deep Learning: Application & Opportunity
 
Hog
HogHog
Hog
 
Object detection with deep learning
Object detection with deep learningObject detection with deep learning
Object detection with deep learning
 
IMAGE SEGMENTATION.
IMAGE SEGMENTATION.IMAGE SEGMENTATION.
IMAGE SEGMENTATION.
 
Image classification with Deep Neural Networks
Image classification with Deep Neural NetworksImage classification with Deep Neural Networks
Image classification with Deep Neural Networks
 
Region based segmentation
Region based segmentationRegion based segmentation
Region based segmentation
 
Overview of Convolutional Neural Networks
Overview of Convolutional Neural NetworksOverview of Convolutional Neural Networks
Overview of Convolutional Neural Networks
 
Introduction to Machine Learning Classifiers
Introduction to Machine Learning ClassifiersIntroduction to Machine Learning Classifiers
Introduction to Machine Learning Classifiers
 
Image processing fundamentals
Image processing fundamentalsImage processing fundamentals
Image processing fundamentals
 
Deep Learning in Computer Vision
Deep Learning in Computer VisionDeep Learning in Computer Vision
Deep Learning in Computer Vision
 
Dip Image Segmentation
Dip Image SegmentationDip Image Segmentation
Dip Image Segmentation
 
Support vector machine
Support vector machineSupport vector machine
Support vector machine
 

Andere mochten auch

Neural network & its applications
Neural network & its applications Neural network & its applications
Neural network & its applications Ahmed_hashmi
 
Pattern recognition
Pattern recognitionPattern recognition
Pattern recognitionArmando Vieira
 
Introduction to pattern recognition
Introduction to pattern recognitionIntroduction to pattern recognition
Introduction to pattern recognitionLuĂ­s Gustavo Martins
 
LISP: Introduction to lisp
LISP: Introduction to lispLISP: Introduction to lisp
LISP: Introduction to lispDataminingTools Inc
 
Neural networks
Neural networksNeural networks
Neural networksSlideshare
 
ARTIFICIAL INTELLIGENCE & NEURAL NETWORKS
ARTIFICIAL INTELLIGENCE & NEURAL NETWORKSARTIFICIAL INTELLIGENCE & NEURAL NETWORKS
ARTIFICIAL INTELLIGENCE & NEURAL NETWORKSEr Kaushal
 
Artificial neural networks
Artificial neural networksArtificial neural networks
Artificial neural networksstellajoseph
 
Artificial intelligence NEURAL NETWORKS
Artificial intelligence NEURAL NETWORKSArtificial intelligence NEURAL NETWORKS
Artificial intelligence NEURAL NETWORKSREHMAT ULLAH
 
Artificial intelligence Speech recognition system
Artificial intelligence Speech recognition systemArtificial intelligence Speech recognition system
Artificial intelligence Speech recognition systemREHMAT ULLAH
 
Artificial intelligence Pattern recognition system
Artificial intelligence Pattern recognition systemArtificial intelligence Pattern recognition system
Artificial intelligence Pattern recognition systemREHMAT ULLAH
 
Chapter 5 - Fuzzy Logic
Chapter 5 - Fuzzy LogicChapter 5 - Fuzzy Logic
Chapter 5 - Fuzzy LogicAshique Rasool
 
Fuzzy logic
Fuzzy logicFuzzy logic
Fuzzy logicBabu Appat
 
Pattern Recognition
Pattern RecognitionPattern Recognition
Pattern RecognitionTalal Alsubaie
 
Speech recognition
Speech recognitionSpeech recognition
Speech recognitionCharu Joshi
 
Artificial neural network
Artificial neural networkArtificial neural network
Artificial neural networkDEEPASHRI HK
 

Andere mochten auch (16)

Neural network & its applications
Neural network & its applications Neural network & its applications
Neural network & its applications
 
Pattern recognition
Pattern recognitionPattern recognition
Pattern recognition
 
Introduction to pattern recognition
Introduction to pattern recognitionIntroduction to pattern recognition
Introduction to pattern recognition
 
LISP: Introduction to lisp
LISP: Introduction to lispLISP: Introduction to lisp
LISP: Introduction to lisp
 
Neural networks
Neural networksNeural networks
Neural networks
 
ARTIFICIAL INTELLIGENCE & NEURAL NETWORKS
ARTIFICIAL INTELLIGENCE & NEURAL NETWORKSARTIFICIAL INTELLIGENCE & NEURAL NETWORKS
ARTIFICIAL INTELLIGENCE & NEURAL NETWORKS
 
Artificial neural networks
Artificial neural networksArtificial neural networks
Artificial neural networks
 
Artificial intelligence NEURAL NETWORKS
Artificial intelligence NEURAL NETWORKSArtificial intelligence NEURAL NETWORKS
Artificial intelligence NEURAL NETWORKS
 
Artificial intelligence Speech recognition system
Artificial intelligence Speech recognition systemArtificial intelligence Speech recognition system
Artificial intelligence Speech recognition system
 
Artificial intelligence Pattern recognition system
Artificial intelligence Pattern recognition systemArtificial intelligence Pattern recognition system
Artificial intelligence Pattern recognition system
 
Fuzzy logic ppt
Fuzzy logic pptFuzzy logic ppt
Fuzzy logic ppt
 
Chapter 5 - Fuzzy Logic
Chapter 5 - Fuzzy LogicChapter 5 - Fuzzy Logic
Chapter 5 - Fuzzy Logic
 
Fuzzy logic
Fuzzy logicFuzzy logic
Fuzzy logic
 
Pattern Recognition
Pattern RecognitionPattern Recognition
Pattern Recognition
 
Speech recognition
Speech recognitionSpeech recognition
Speech recognition
 
Artificial neural network
Artificial neural networkArtificial neural network
Artificial neural network
 

Ähnlich wie Feature Extraction

INTELLIGENT FACE RECOGNITION TECHNIQUES
INTELLIGENT FACE RECOGNITION TECHNIQUESINTELLIGENT FACE RECOGNITION TECHNIQUES
INTELLIGENT FACE RECOGNITION TECHNIQUESChirag Jain
 
IRJET- Face Spoof Detection using Machine Learning with Colour Features
IRJET-  	  Face Spoof Detection using Machine Learning with Colour FeaturesIRJET-  	  Face Spoof Detection using Machine Learning with Colour Features
IRJET- Face Spoof Detection using Machine Learning with Colour FeaturesIRJET Journal
 
Optimization of Facial Landmark for Sentiment Analysis on Images with Human F...
Optimization of Facial Landmark for Sentiment Analysis on Images with Human F...Optimization of Facial Landmark for Sentiment Analysis on Images with Human F...
Optimization of Facial Landmark for Sentiment Analysis on Images with Human F...adewole63
 
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
 
Innovative Analytic and Holistic Combined Face Recognition and Verification M...
Innovative Analytic and Holistic Combined Face Recognition and Verification M...Innovative Analytic and Holistic Combined Face Recognition and Verification M...
Innovative Analytic and Holistic Combined Face Recognition and Verification M...ijbuiiir1
 
Hl2413221328
Hl2413221328Hl2413221328
Hl2413221328IJERA Editor
 
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
 
A Robust & Fast Face Detection System
A Robust & Fast Face Detection SystemA Robust & Fast Face Detection System
A Robust & Fast Face Detection SystemIDES Editor
 
International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)IJERD Editor
 
Facial expression recongnition Techniques, Database and Classifiers
Facial expression recongnition Techniques, Database and Classifiers Facial expression recongnition Techniques, Database and Classifiers
Facial expression recongnition Techniques, Database and Classifiers Rupinder Saini
 
IRJET - Emotion Recognising System-Crowd Behavior Analysis
IRJET -  	  Emotion Recognising System-Crowd Behavior AnalysisIRJET -  	  Emotion Recognising System-Crowd Behavior Analysis
IRJET - Emotion Recognising System-Crowd Behavior AnalysisIRJET Journal
 
Face Recognition Using Simplified Fuzzy Artmap
Face Recognition Using Simplified Fuzzy ArtmapFace Recognition Using Simplified Fuzzy Artmap
Face Recognition Using Simplified Fuzzy Artmapsipij
 
Welcome to International Journal of Engineering Research and Development (IJERD)
Welcome to International Journal of Engineering Research and Development (IJERD)Welcome to International Journal of Engineering Research and Development (IJERD)
Welcome to International Journal of Engineering Research and Development (IJERD)IJERD Editor
 
LEARNING BASES OF ACTICITY
LEARNING BASES OF ACTICITYLEARNING BASES OF ACTICITY
LEARNING BASES OF ACTICITYPadma Kannan
 
Face Recognition System Using Local Ternary Pattern and Signed Number Multipl...
Face Recognition System Using Local Ternary Pattern and Signed Number Multipl...Face Recognition System Using Local Ternary Pattern and Signed Number Multipl...
Face Recognition System Using Local Ternary Pattern and Signed Number Multipl...inventionjournals
 
IRJET- An Overview on Automated Emotion Recognition System
IRJET-  	  An Overview on Automated Emotion Recognition SystemIRJET-  	  An Overview on Automated Emotion Recognition System
IRJET- An Overview on Automated Emotion Recognition SystemIRJET Journal
 

Ähnlich wie Feature Extraction (20)

INTELLIGENT FACE RECOGNITION TECHNIQUES
INTELLIGENT FACE RECOGNITION TECHNIQUESINTELLIGENT FACE RECOGNITION TECHNIQUES
INTELLIGENT FACE RECOGNITION TECHNIQUES
 
Human Face Detection And Identification Of Facial Expressions Using MATLAB
Human Face Detection And Identification Of Facial Expressions Using MATLABHuman Face Detection And Identification Of Facial Expressions Using MATLAB
Human Face Detection And Identification Of Facial Expressions Using MATLAB
 
IRJET- Face Spoof Detection using Machine Learning with Colour Features
IRJET-  	  Face Spoof Detection using Machine Learning with Colour FeaturesIRJET-  	  Face Spoof Detection using Machine Learning with Colour Features
IRJET- Face Spoof Detection using Machine Learning with Colour Features
 
Optimization of Facial Landmark for Sentiment Analysis on Images with Human F...
Optimization of Facial Landmark for Sentiment Analysis on Images with Human F...Optimization of Facial Landmark for Sentiment Analysis on Images with Human F...
Optimization of Facial Landmark for Sentiment Analysis on Images with Human F...
 
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
 
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
 
Poster ions
Poster ionsPoster ions
Poster ions
 
Innovative Analytic and Holistic Combined Face Recognition and Verification M...
Innovative Analytic and Holistic Combined Face Recognition and Verification M...Innovative Analytic and Holistic Combined Face Recognition and Verification M...
Innovative Analytic and Holistic Combined Face Recognition and Verification M...
 
Hl2413221328
Hl2413221328Hl2413221328
Hl2413221328
 
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
 
A Robust & Fast Face Detection System
A Robust & Fast Face Detection SystemA Robust & Fast Face Detection System
A Robust & Fast Face Detection System
 
International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)
 
Facial expression recongnition Techniques, Database and Classifiers
Facial expression recongnition Techniques, Database and Classifiers Facial expression recongnition Techniques, Database and Classifiers
Facial expression recongnition Techniques, Database and Classifiers
 
G1802033543
G1802033543G1802033543
G1802033543
 
IRJET - Emotion Recognising System-Crowd Behavior Analysis
IRJET -  	  Emotion Recognising System-Crowd Behavior AnalysisIRJET -  	  Emotion Recognising System-Crowd Behavior Analysis
IRJET - Emotion Recognising System-Crowd Behavior Analysis
 
Face Recognition Using Simplified Fuzzy Artmap
Face Recognition Using Simplified Fuzzy ArtmapFace Recognition Using Simplified Fuzzy Artmap
Face Recognition Using Simplified Fuzzy Artmap
 
Welcome to International Journal of Engineering Research and Development (IJERD)
Welcome to International Journal of Engineering Research and Development (IJERD)Welcome to International Journal of Engineering Research and Development (IJERD)
Welcome to International Journal of Engineering Research and Development (IJERD)
 
LEARNING BASES OF ACTICITY
LEARNING BASES OF ACTICITYLEARNING BASES OF ACTICITY
LEARNING BASES OF ACTICITY
 
Face Recognition System Using Local Ternary Pattern and Signed Number Multipl...
Face Recognition System Using Local Ternary Pattern and Signed Number Multipl...Face Recognition System Using Local Ternary Pattern and Signed Number Multipl...
Face Recognition System Using Local Ternary Pattern and Signed Number Multipl...
 
IRJET- An Overview on Automated Emotion Recognition System
IRJET-  	  An Overview on Automated Emotion Recognition SystemIRJET-  	  An Overview on Automated Emotion Recognition System
IRJET- An Overview on Automated Emotion Recognition System
 

KĂŒrzlich hochgeladen

Crayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon ACrayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon AUnboundStockton
 
Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)eniolaolutunde
 
Alper Gobel In Media Res Media Component
Alper Gobel In Media Res Media ComponentAlper Gobel In Media Res Media Component
Alper Gobel In Media Res Media ComponentInMediaRes1
 
ECONOMIC CONTEXT - LONG FORM TV DRAMA - PPT
ECONOMIC CONTEXT - LONG FORM TV DRAMA - PPTECONOMIC CONTEXT - LONG FORM TV DRAMA - PPT
ECONOMIC CONTEXT - LONG FORM TV DRAMA - PPTiammrhaywood
 
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...EduSkills OECD
 
Hybridoma Technology ( Production , Purification , and Application )
Hybridoma Technology  ( Production , Purification , and Application  ) Hybridoma Technology  ( Production , Purification , and Application  )
Hybridoma Technology ( Production , Purification , and Application ) Sakshi Ghasle
 
Employee wellbeing at the workplace.pptx
Employee wellbeing at the workplace.pptxEmployee wellbeing at the workplace.pptx
Employee wellbeing at the workplace.pptxNirmalaLoungPoorunde1
 
Concept of Vouching. B.Com(Hons) /B.Compdf
Concept of Vouching. B.Com(Hons) /B.CompdfConcept of Vouching. B.Com(Hons) /B.Compdf
Concept of Vouching. B.Com(Hons) /B.CompdfUmakantAnnand
 
How to Configure Email Server in Odoo 17
How to Configure Email Server in Odoo 17How to Configure Email Server in Odoo 17
How to Configure Email Server in Odoo 17Celine George
 
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...Marc Dusseiller Dusjagr
 
Accessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impactAccessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impactdawncurless
 
How to Make a Pirate ship Primary Education.pptx
How to Make a Pirate ship Primary Education.pptxHow to Make a Pirate ship Primary Education.pptx
How to Make a Pirate ship Primary Education.pptxmanuelaromero2013
 
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxSOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxiammrhaywood
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxheathfieldcps1
 
Mastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory InspectionMastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory InspectionSafetyChain Software
 
Organic Name Reactions for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions  for the students and aspirants of Chemistry12th.pptxOrganic Name Reactions  for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions for the students and aspirants of Chemistry12th.pptxVS Mahajan Coaching Centre
 
Sanyam Choudhary Chemistry practical.pdf
Sanyam Choudhary Chemistry practical.pdfSanyam Choudhary Chemistry practical.pdf
Sanyam Choudhary Chemistry practical.pdfsanyamsingh5019
 

KĂŒrzlich hochgeladen (20)

Crayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon ACrayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon A
 
Model Call Girl in Tilak Nagar Delhi reach out to us at 🔝9953056974🔝
Model Call Girl in Tilak Nagar Delhi reach out to us at 🔝9953056974🔝Model Call Girl in Tilak Nagar Delhi reach out to us at 🔝9953056974🔝
Model Call Girl in Tilak Nagar Delhi reach out to us at 🔝9953056974🔝
 
Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)
 
Alper Gobel In Media Res Media Component
Alper Gobel In Media Res Media ComponentAlper Gobel In Media Res Media Component
Alper Gobel In Media Res Media Component
 
CĂłdigo Creativo y Arte de Software | Unidad 1
CĂłdigo Creativo y Arte de Software | Unidad 1CĂłdigo Creativo y Arte de Software | Unidad 1
CĂłdigo Creativo y Arte de Software | Unidad 1
 
TataKelola dan KamSiber Kecerdasan Buatan v022.pdf
TataKelola dan KamSiber Kecerdasan Buatan v022.pdfTataKelola dan KamSiber Kecerdasan Buatan v022.pdf
TataKelola dan KamSiber Kecerdasan Buatan v022.pdf
 
ECONOMIC CONTEXT - LONG FORM TV DRAMA - PPT
ECONOMIC CONTEXT - LONG FORM TV DRAMA - PPTECONOMIC CONTEXT - LONG FORM TV DRAMA - PPT
ECONOMIC CONTEXT - LONG FORM TV DRAMA - PPT
 
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
 
Hybridoma Technology ( Production , Purification , and Application )
Hybridoma Technology  ( Production , Purification , and Application  ) Hybridoma Technology  ( Production , Purification , and Application  )
Hybridoma Technology ( Production , Purification , and Application )
 
Employee wellbeing at the workplace.pptx
Employee wellbeing at the workplace.pptxEmployee wellbeing at the workplace.pptx
Employee wellbeing at the workplace.pptx
 
Concept of Vouching. B.Com(Hons) /B.Compdf
Concept of Vouching. B.Com(Hons) /B.CompdfConcept of Vouching. B.Com(Hons) /B.Compdf
Concept of Vouching. B.Com(Hons) /B.Compdf
 
How to Configure Email Server in Odoo 17
How to Configure Email Server in Odoo 17How to Configure Email Server in Odoo 17
How to Configure Email Server in Odoo 17
 
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
 
Accessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impactAccessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impact
 
How to Make a Pirate ship Primary Education.pptx
How to Make a Pirate ship Primary Education.pptxHow to Make a Pirate ship Primary Education.pptx
How to Make a Pirate ship Primary Education.pptx
 
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxSOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptx
 
Mastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory InspectionMastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory Inspection
 
Organic Name Reactions for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions  for the students and aspirants of Chemistry12th.pptxOrganic Name Reactions  for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions for the students and aspirants of Chemistry12th.pptx
 
Sanyam Choudhary Chemistry practical.pdf
Sanyam Choudhary Chemistry practical.pdfSanyam Choudhary Chemistry practical.pdf
Sanyam Choudhary Chemistry practical.pdf
 

Feature Extraction

  • 1. Two Feature Extraction Methods Lian, Xiaochen skylian1985@163.com Department of Computer Science Shanghai Jiao Tong University July 13, 2007 Lian, Xiaochen Two Feature Extraction Methods
  • 2. Attention Based Method Statistics Based Method Outline 1 Attention Based Method Why Attention? Model of Attention Application in Face Recognition 2 Statistics Based Method Basic Idea Feature Selection Process Lian, Xiaochen Two Feature Extraction Methods
  • 3. Why Attention? Attention Based Method Model of Attention Statistics Based Method Application in Face Recognition Outline 1 Attention Based Method Why Attention? Model of Attention Application in Face Recognition 2 Statistics Based Method Basic Idea Feature Selection Process Lian, Xiaochen Two Feature Extraction Methods
  • 4. Why Attention? Attention Based Method Model of Attention Statistics Based Method Application in Face Recognition Why Attention? When recognizing a person, we compare the face with those stored in memory. We always can not remember all the details of a face. It is the conspicuous parts that impress themselves on us. Lian, Xiaochen Two Feature Extraction Methods
  • 5. Why Attention? Attention Based Method Model of Attention Statistics Based Method Application in Face Recognition Model of Attention How do human vision system ïŹnd salient regions in a scene? Koch and Ullman[?] proposed a biologically plausible architecture. Figure: General architecture ofExtraction Methods Lian, Xiaochen Two Feature the model
  • 6. Why Attention? Attention Based Method Model of Attention Statistics Based Method Application in Face Recognition Channels The original image is decomposed into three channels. Intensity I : Consider the brightness of a pixel, which is obtained as I = (r + g + b)/3. Color: Red-Green color and Blue-Yellow opponencies. r−g RG = max(r, g, b) b − min(r, g) BY = max(r, g, b) Orientation: Four orientation channels correspond to gabor ïŹlters oriented at 0, 45, 90, and 135 degrees. This representation is able to capture the critical distinctions in orientation. Lian, Xiaochen Two Feature Extraction Methods
  • 7. Why Attention? Attention Based Method Model of Attention Statistics Based Method Application in Face Recognition Channels Figure: Channels Lian, Xiaochen Two Feature Extraction Methods
  • 8. Why Attention? Attention Based Method Model of Attention Statistics Based Method Application in Face Recognition Image Pyramid The Gaussian pyramid is created to a depth of nine levels, with level 0 having a scale of 1 : 1 (the original input image) and level 8 being 1 : 256. This is done by ïŹltering the images with gaussian ïŹlter and then resize it. We use gaussian ïŹlter to eliminate noise, and the resizing is for biological purpose. There are seven pyramids, one for intensity MI , two for color MRG and MBY , and four for orientation MΞ (Ξ ∈ {0, 45, 90, 135}). Lian, Xiaochen Two Feature Extraction Methods
  • 9. Why Attention? Attention Based Method Model of Attention Statistics Based Method Application in Face Recognition Image Pyramid Figure: Image pyramid Lian, Xiaochen Two Feature Extraction Methods
  • 10. Why Attention? Attention Based Method Model of Attention Statistics Based Method Application in Face Recognition Center Surround Difference It is a cross-scale difference between two images, denoted by “ ”: expanding the smaller image into the larger one by interpolation, then followed by pixel-pixel substraction. Figure: Center Surround Difference Lian, Xiaochen Two Feature Extraction Methods
  • 11. Why Attention? Attention Based Method Model of Attention Statistics Based Method Application in Face Recognition Normalization Figure: Normalization effect Lian, Xiaochen Two Feature Extraction Methods
  • 12. Why Attention? Attention Based Method Model of Attention Statistics Based Method Application in Face Recognition Normalization Difference-of-Gaussians ïŹlter is usually used to detect blob. c2 −(x2 +y2 )/(2σ2 ) c2 e−(x +y )/(2σinh ) 2 2 2 DoG(x, y) = ex 2 e ex − inh 2 2πσex 2πσinh Lian, Xiaochen Two Feature Extraction Methods
  • 13. Why Attention? Attention Based Method Model of Attention Statistics Based Method Application in Face Recognition Saliency Map Combine the images from all the channels linearly. Figure: Saliency Map Lian, Xiaochen Two Feature Extraction Methods
  • 14. Why Attention? Attention Based Method Model of Attention Statistics Based Method Application in Face Recognition Figure: Faces and the corresponding saliency Map(from ORL face database) Lian, Xiaochen Two Feature Extraction Methods
  • 15. Why Attention? Attention Based Method Model of Attention Statistics Based Method Application in Face Recognition Experiment Result Figure: Error rate Figure: Rank error rate Lian, Xiaochen Two Feature Extraction Methods
  • 16. Why Attention? Attention Based Method Model of Attention Statistics Based Method Application in Face Recognition Lots of Problems! How to do recognition? Different people have different sets of features. Simply applying Euclid Distance yields bad performance: the error rate is high for a 40-person database. The performance suffers pose and expression severely. Lian, Xiaochen Two Feature Extraction Methods
  • 17. Attention Based Method Basic Idea Statistics Based Method Feature Selection Process Outline 1 Attention Based Method Why Attention? Model of Attention Application in Face Recognition 2 Statistics Based Method Basic Idea Feature Selection Process Lian, Xiaochen Two Feature Extraction Methods
  • 18. Attention Based Method Basic Idea Statistics Based Method Feature Selection Process Basic Idea Suppose S = {x1 , x2 , · · · , xn } be n features for the collected data. The objective of feature selection is to ïŹnd a subset Sd = {xi1 , xi2 , · · · , xid }, which sufïŹce to represent the original data. The performance of Sd can be evaluated by the percentage of the variation in xi that can be accounted for by the elements by Sd . If that percentage is large enough, Sd can then be the ïŹnal choice; otherwise, new signiïŹcant variables need to be added into Sd . Lian, Xiaochen Two Feature Extraction Methods
  • 19. Attention Based Method Basic Idea Statistics Based Method Feature Selection Process Feature Similarity Measure The squared-correlation coefïŹcient between two random vectors x and y is (xt y)2 sc(x, y) = . (xt x)(yt y) This measure has the following properties: 0 ≀ |sc(x, y)| ≀ 1. |sc(x, y)| if and only if x and y are linearly related. The measure is invariant to scaling and translation. The measure is sensitive to rotation. Lian, Xiaochen Two Feature Extraction Methods
  • 20. Attention Based Method Basic Idea Statistics Based Method Feature Selection Process Step-By-Step Selection At the ïŹrst step, let i=1 sc(xi , xj ) n Cj,1 = , n i1 = arg max {Cj,1 }. 1≀j≀n Select xi1 as the ïŹrst signiïŹcant variable. Lian, Xiaochen Two Feature Extraction Methods
  • 21. Attention Based Method Basic Idea Statistics Based Method Feature Selection Process Step-By-Step Selection Assume the ïŹrst m − 1 most signiïŹcant variables, z1 , · · · , zm−1 , has been chosen. The m-th signiïŹcant feature zm will be chosen in such a manner: The subset Sm−1 + {zm } should be the most representative subset compared with any other subsets formed by adding a candidate feature to Sm−1 . Let αj ∈ S − Sm−1 and i=1 sc(xi , αj ) n Cj,m = , n im = arg max {Cj,m }. 1≀j≀n The m-th signiïŹcant feature can then be xim . Lian, Xiaochen Two Feature Extraction Methods
  • 22. Attention Based Method Basic Idea Statistics Based Method Feature Selection Process Lian, Xiaochen Two Feature Extraction Methods
  • 23. Attention Based Method Basic Idea Statistics Based Method Feature Selection Process Some Discussion The squared-correlation coefïŹcient is used to measure the linear correlation between variables. Need new method for nonlinear relationships. The greedy search process do not assure the optimal selection. The complexity is O(n2 N), where n is the number of features, and N is the number of samples. When n become large, the algorithm will be inefïŹcient. Lian, Xiaochen Two Feature Extraction Methods
  • 24. Attention Based Method Basic Idea Statistics Based Method Feature Selection Process C. Koch, and S. Ullman, “Shifts in Selective Visual Attention: Towards the Underlying Neural Circuitry,” Human Neurobiology, vol. 4, pp. 219-227, 1985. pp. 89-102, 1977. Laurent Itti, and Christof Koch, “A saliency-based search mechanism for overt and covert shitfs of visual attention,” Vision Research, 40(2000). Dirk Walther, and Christof Koch, “Modeling attention to salient proto-objects,” Neural Networks, 19(2006). Laurent Itti, Christof Koch, and Ernst Niebur, “A Model of Saliency-Based Visual Attention for Rapid Scene Analysis,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, No. 11, Nov. 1998. Lian, Xiaochen Two Feature Extraction Methods
  • 25. Attention Based Method Basic Idea Statistics Based Method Feature Selection Process Hua-Liang, and Stephen A. Billings, “Feature Subset Selection and Ranking for Data Dimensionality Reduction,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 29, no.1, Jan. 2007. Pabitra Mitra, C.A. Mrthy, and Sankar K. Pal “Unsupervised Feature Selection Using Feature Similarity,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, No. 3, Mar. 2002. Lian, Xiaochen Two Feature Extraction Methods