SlideShare une entreprise Scribd logo
1  sur  23
By
Imran Hossain Faruk
   Ear features have been used for many years
    in the forensic science of recognition
   Ear is a stable biometric and does not very
    with age.
   Ear has all the properties that a biometric
    trait should have, i.e. uniqueness,
    universality, permanence and collectability




                 Imran Hossain Faruk   01/28/13   2
   Ear does not have a completely random
    structure. It has standard parts as other
    biometric traits like face
   Unlike human face, ear has no expression
    changes, make-up effects and more over the
    color is constant through out the ear.




                 Imran Hossain Faruk   01/28/13   3
Fig 1: Anatomy of the Ear
Imran Hossain Faruk   01/28/13   4
Image Acquisition


Pre-Processing and Edge
       Detection



  Feature Extraction




Two-Stage Classification




 Imran Hossain Faruk   01/28/13   5
   The side face images have been acquired in
    the same lightening conditions.
   All Images taken from with a distance of 15-
    20 cms between the ear and camera
   The image should be carefully taken such
    that outer ear shape is preserved.
   The less erroneous the outer shape is the
    more accurate the results are.




                 Imran Hossain Faruk   01/28/13   6
Fig 2: A side face image acquired
        Imran Hossain Faruk   01/28/13   7
   Selecting the ROI portion of the image by
    segmentation.
   Color image is then converted to grayscale
    image




              Fig 3: Cropped Gray scale image


                   Imran Hossain Faruk   01/28/13   8
   Edge detection and binarization is done using
    the well known canny edge detector.
   If w is the width of the image in pixel and h
    is the height of the image in pixel, the canny
    edge detector takes as input an array w × h
    of gray values and sigma (standard deviation)
   Output a binary image with a value 1 for
    edge pixels, i.e., the pixel which constitute
    an edge and a value 0 for all other pixels.



                  Imran Hossain Faruk   01/28/13   9
Fig 4: Grayscale image and its corresponding edge detected binary image

                      Imran Hossain Faruk   01/28/13           10
    Using adaptive weighted median filter this
    kind of noise can be removed




        Fig 5: image with and without noise

                 Imran Hossain Faruk   01/28/13   11
   Here features extracted all are angles
   Features are divided into two vectors
   First features is found using the outer shape
    of the ear.
   Second feature vector is found using all other
    edges
   To find the angels, the terms max-line and
    normal line are used




                  Imran Hossain Faruk   01/28/13   12
   Max-line: it is the longest line that can be
    drawn with both its endpoints on the edges
    of the ear.
   The length of a line is measured in terms of
    Euclidean distance
   If there are more than one line, features
    corresponding to each max-line are to be
    extracted




                 Imran Hossain Faruk   01/28/13   13
   Normal Line: lines which are perpendicular
    to the max-line and which divide the max-
    line into (n+1) equal parts, where n is a
    positive integer.




         Fig 5: Image with max-line and normal line

                   Imran Hossain Faruk   01/28/13     14
   The max-line m, normal line l1,l2,l3,…..,ln
    named from top to bottom.
   Center of the max-line is c.
   P1,P2,P3,……,Pn are the points where the
    outer edge and the normal lines intersect.




                  Imran Hossain Faruk   01/28/13   15
   First feature vector(FV1): it can be defined
    by.
          FV1 = [θ1, θ2, θ3,…., θn]




               Fig 6: image showing the angel θ1

                  Imran Hossain Faruk   01/28/13   16
   Second feature vector(FV2): all the points
    where the edges of the ear and normal line
    intersect except the outer most edge




     Fig 7: image showing second feature vector and angel respectively
                        Imran Hossain Faruk   01/28/13           17
   Classification is the task of finding a match
    for a given query image.
   Here classification is performed in two
    stages.
   In first stage the first feature vector is used
    while in second stage second feature vector
    is used.




                  Imran Hossain Faruk   01/28/13   18
Imran Hossain Faruk   01/28/13   19
Imran Hossain Faruk   01/28/13   20
   A given query image is first tested against all the images in
    the database using first feature vector
   Only the images are matched in the first stage are
    considered for second stage of classification
   As the size of the FV1 is less, that is n (number of normal
    line) so only n comparison is needed for the first stage
    classification.
   In the second stage classification m*n comparison are
    required, assuming m points for each normal line.
   If the classification is single stage, than total comparison
    required are I*((n)+(m*n)), where I is the number of images
    in the database
   If the classification is divided into two stage the
    comparison would be I*n+I1*(m*n)
    where I1 is the number of image that are matched
    with respect to the first feature vector.
   Saved computation is (I – I1)*(m*n).
                      Imran Hossain Faruk   01/28/13    21
   Ear recognition can used for both
    identification and verification purpose.
   Since some portion of ear is kept covert by
    hair so it is very difficult to get the complete
    image of ear.
   Since its uniqueness is moderate we can not
    rely on it completely.




                  Imran Hossain Faruk   01/28/13   22
   Ping Yan, Kevin W. Bowyer, “Empirical
    Evaluation of Advanced Ear Biometrics”, IEEE
    Computer Society Conference on Computer
    Vision and Pattern Recognition , 2005
   Michal choaras, “Ear biometric based on
    geometric al feature extraction”, Electronic
    letters on computer vision and image
    analysis(Journal ELCVIA), 585-95,2005.




                 Imran Hossain Faruk   01/28/13   23

Contenu connexe

Tendances

Iris recognition system
Iris recognition systemIris recognition system
Iris recognition systemNilu Desai
 
Retina recognition biometrics drishtysharma
Retina recognition biometrics drishtysharmaRetina recognition biometrics drishtysharma
Retina recognition biometrics drishtysharmaDrishty Sharma
 
Fingerprint recognition system by sagar chand gupta
Fingerprint recognition system by sagar chand guptaFingerprint recognition system by sagar chand gupta
Fingerprint recognition system by sagar chand guptascg121433
 
Pattern recognition palm print authentication system
Pattern recognition palm print authentication systemPattern recognition palm print authentication system
Pattern recognition palm print authentication systemMazin Alwaaly
 
Automated Fingerprint Identification Systems
Automated Fingerprint Identification SystemsAutomated Fingerprint Identification Systems
Automated Fingerprint Identification SystemsRmcauley
 
A short introduction to multimedia forensics the science discovering the hist...
A short introduction to multimedia forensics the science discovering the hist...A short introduction to multimedia forensics the science discovering the hist...
A short introduction to multimedia forensics the science discovering the hist...Sebastiano Battiato
 
BRAIN FINGERPRINTING
BRAIN FINGERPRINTINGBRAIN FINGERPRINTING
BRAIN FINGERPRINTINGApoorv Pandey
 
Biometric Signature Recognization
 Biometric Signature Recognization Biometric Signature Recognization
Biometric Signature RecognizationFaimin Khan
 
Palmprint recognition presentation
Palmprint recognition presentationPalmprint recognition presentation
Palmprint recognition presentationAlexandru Dorobantu
 
Pattern recognition IRIS recognition
Pattern recognition IRIS recognitionPattern recognition IRIS recognition
Pattern recognition IRIS recognitionMazin Alwaaly
 
voice recognition
voice recognition voice recognition
voice recognition Hemant Jain
 
Audio and Video Forensics
Audio and Video ForensicsAudio and Video Forensics
Audio and Video ForensicsDipika Sengupta
 
1.4 Performance Measures.ppt
1.4 Performance Measures.ppt1.4 Performance Measures.ppt
1.4 Performance Measures.pptssuser7ec6af
 
Thesis presentation ist
Thesis presentation istThesis presentation ist
Thesis presentation istdeep sharma
 

Tendances (20)

Retinal Recognition
Retinal RecognitionRetinal Recognition
Retinal Recognition
 
Iris recognition system
Iris recognition systemIris recognition system
Iris recognition system
 
Retina recognition biometrics drishtysharma
Retina recognition biometrics drishtysharmaRetina recognition biometrics drishtysharma
Retina recognition biometrics drishtysharma
 
Fingerprint recognition system by sagar chand gupta
Fingerprint recognition system by sagar chand guptaFingerprint recognition system by sagar chand gupta
Fingerprint recognition system by sagar chand gupta
 
Forensic audio
Forensic audioForensic audio
Forensic audio
 
Face reconstruction
Face reconstructionFace reconstruction
Face reconstruction
 
Pattern recognition palm print authentication system
Pattern recognition palm print authentication systemPattern recognition palm print authentication system
Pattern recognition palm print authentication system
 
Automated Fingerprint Identification Systems
Automated Fingerprint Identification SystemsAutomated Fingerprint Identification Systems
Automated Fingerprint Identification Systems
 
A short introduction to multimedia forensics the science discovering the hist...
A short introduction to multimedia forensics the science discovering the hist...A short introduction to multimedia forensics the science discovering the hist...
A short introduction to multimedia forensics the science discovering the hist...
 
BRAIN FINGERPRINTING
BRAIN FINGERPRINTINGBRAIN FINGERPRINTING
BRAIN FINGERPRINTING
 
Iris scan.ppt 1
Iris scan.ppt 1Iris scan.ppt 1
Iris scan.ppt 1
 
Biometric Signature Recognization
 Biometric Signature Recognization Biometric Signature Recognization
Biometric Signature Recognization
 
Facial reconstruction
Facial reconstructionFacial reconstruction
Facial reconstruction
 
Palmprint recognition presentation
Palmprint recognition presentationPalmprint recognition presentation
Palmprint recognition presentation
 
Pattern recognition IRIS recognition
Pattern recognition IRIS recognitionPattern recognition IRIS recognition
Pattern recognition IRIS recognition
 
voice recognition
voice recognition voice recognition
voice recognition
 
Forensic imaging
Forensic imagingForensic imaging
Forensic imaging
 
Audio and Video Forensics
Audio and Video ForensicsAudio and Video Forensics
Audio and Video Forensics
 
1.4 Performance Measures.ppt
1.4 Performance Measures.ppt1.4 Performance Measures.ppt
1.4 Performance Measures.ppt
 
Thesis presentation ist
Thesis presentation istThesis presentation ist
Thesis presentation ist
 

En vedette

Ear Biometrics shritosh kumar
Ear Biometrics shritosh kumarEar Biometrics shritosh kumar
Ear Biometrics shritosh kumarshritosh kumar
 
Face And Ear Composite Recognition Tool
Face And Ear Composite Recognition ToolFace And Ear Composite Recognition Tool
Face And Ear Composite Recognition ToolAbhineet Bhamra
 
Gait Recognition Using Infrared
Gait Recognition Using InfraredGait Recognition Using Infrared
Gait Recognition Using InfraredBirunthaG
 
Multimodal Biometric Systems
Multimodal Biometric SystemsMultimodal Biometric Systems
Multimodal Biometric SystemsPiyush Mittal
 
Review of Detection & Recognition Techniques for 2D Ear Biometrics System
Review of Detection & Recognition Techniques for 2D Ear Biometrics SystemReview of Detection & Recognition Techniques for 2D Ear Biometrics System
Review of Detection & Recognition Techniques for 2D Ear Biometrics Systemshritosh kumar
 
Silent speech recognition
Silent speech recognitionSilent speech recognition
Silent speech recognitionJay Patel
 
Multispectral imaging in Forensics with VideometerLab 3
Multispectral imaging in Forensics with VideometerLab 3Multispectral imaging in Forensics with VideometerLab 3
Multispectral imaging in Forensics with VideometerLab 3Adrian Waltho
 
Basics of Coding Theory
Basics of Coding TheoryBasics of Coding Theory
Basics of Coding TheoryPiyush Mittal
 
PatSeer Introduction
PatSeer IntroductionPatSeer Introduction
PatSeer IntroductionGridlogics
 
Face recognition ppt
Face recognition pptFace recognition ppt
Face recognition pptSantosh Kumar
 
Deep neural networks
Deep neural networksDeep neural networks
Deep neural networksSi Haem
 
Definition and types of research
Definition and types of researchDefinition and types of research
Definition and types of researchfadifm
 

En vedette (17)

Ear Biometrics shritosh kumar
Ear Biometrics shritosh kumarEar Biometrics shritosh kumar
Ear Biometrics shritosh kumar
 
Face And Ear Composite Recognition Tool
Face And Ear Composite Recognition ToolFace And Ear Composite Recognition Tool
Face And Ear Composite Recognition Tool
 
Biometrics system
Biometrics systemBiometrics system
Biometrics system
 
Gait Recognition Using Infrared
Gait Recognition Using InfraredGait Recognition Using Infrared
Gait Recognition Using Infrared
 
Multimodal Biometric Systems
Multimodal Biometric SystemsMultimodal Biometric Systems
Multimodal Biometric Systems
 
Review of Detection & Recognition Techniques for 2D Ear Biometrics System
Review of Detection & Recognition Techniques for 2D Ear Biometrics SystemReview of Detection & Recognition Techniques for 2D Ear Biometrics System
Review of Detection & Recognition Techniques for 2D Ear Biometrics System
 
F04724954
F04724954F04724954
F04724954
 
Silent speech recognition
Silent speech recognitionSilent speech recognition
Silent speech recognition
 
Multispectral imaging in Forensics with VideometerLab 3
Multispectral imaging in Forensics with VideometerLab 3Multispectral imaging in Forensics with VideometerLab 3
Multispectral imaging in Forensics with VideometerLab 3
 
Lip recognition
Lip recognition Lip recognition
Lip recognition
 
Basics of Coding Theory
Basics of Coding TheoryBasics of Coding Theory
Basics of Coding Theory
 
gait analysis
gait analysisgait analysis
gait analysis
 
Iris ppt
Iris pptIris ppt
Iris ppt
 
PatSeer Introduction
PatSeer IntroductionPatSeer Introduction
PatSeer Introduction
 
Face recognition ppt
Face recognition pptFace recognition ppt
Face recognition ppt
 
Deep neural networks
Deep neural networksDeep neural networks
Deep neural networks
 
Definition and types of research
Definition and types of researchDefinition and types of research
Definition and types of research
 

Plus de Piyush Mittal

Plus de Piyush Mittal (20)

Power mock
Power mockPower mock
Power mock
 
Design pattern tutorial
Design pattern tutorialDesign pattern tutorial
Design pattern tutorial
 
Reflection
ReflectionReflection
Reflection
 
Gpu archi
Gpu archiGpu archi
Gpu archi
 
Cuda Architecture
Cuda ArchitectureCuda Architecture
Cuda Architecture
 
Intel open mp
Intel open mpIntel open mp
Intel open mp
 
Intro to parallel computing
Intro to parallel computingIntro to parallel computing
Intro to parallel computing
 
Cuda toolkit reference manual
Cuda toolkit reference manualCuda toolkit reference manual
Cuda toolkit reference manual
 
Matrix multiplication using CUDA
Matrix multiplication using CUDAMatrix multiplication using CUDA
Matrix multiplication using CUDA
 
Channel coding
Channel codingChannel coding
Channel coding
 
Java cheat sheet
Java cheat sheetJava cheat sheet
Java cheat sheet
 
Google app engine cheat sheet
Google app engine cheat sheetGoogle app engine cheat sheet
Google app engine cheat sheet
 
Git cheat sheet
Git cheat sheetGit cheat sheet
Git cheat sheet
 
Vi cheat sheet
Vi cheat sheetVi cheat sheet
Vi cheat sheet
 
Css cheat sheet
Css cheat sheetCss cheat sheet
Css cheat sheet
 
Cpp cheat sheet
Cpp cheat sheetCpp cheat sheet
Cpp cheat sheet
 
Ubuntu cheat sheet
Ubuntu cheat sheetUbuntu cheat sheet
Ubuntu cheat sheet
 
Php cheat sheet
Php cheat sheetPhp cheat sheet
Php cheat sheet
 
oracle 9i cheat sheet
oracle 9i cheat sheetoracle 9i cheat sheet
oracle 9i cheat sheet
 
Open ssh cheet sheat
Open ssh cheet sheatOpen ssh cheet sheat
Open ssh cheet sheat
 

Ear biometrics using feature extraction and two-stage classification

  • 2. Ear features have been used for many years in the forensic science of recognition  Ear is a stable biometric and does not very with age.  Ear has all the properties that a biometric trait should have, i.e. uniqueness, universality, permanence and collectability Imran Hossain Faruk 01/28/13 2
  • 3. Ear does not have a completely random structure. It has standard parts as other biometric traits like face  Unlike human face, ear has no expression changes, make-up effects and more over the color is constant through out the ear. Imran Hossain Faruk 01/28/13 3
  • 4. Fig 1: Anatomy of the Ear Imran Hossain Faruk 01/28/13 4
  • 5. Image Acquisition Pre-Processing and Edge Detection Feature Extraction Two-Stage Classification Imran Hossain Faruk 01/28/13 5
  • 6. The side face images have been acquired in the same lightening conditions.  All Images taken from with a distance of 15- 20 cms between the ear and camera  The image should be carefully taken such that outer ear shape is preserved.  The less erroneous the outer shape is the more accurate the results are. Imran Hossain Faruk 01/28/13 6
  • 7. Fig 2: A side face image acquired Imran Hossain Faruk 01/28/13 7
  • 8. Selecting the ROI portion of the image by segmentation.  Color image is then converted to grayscale image Fig 3: Cropped Gray scale image Imran Hossain Faruk 01/28/13 8
  • 9. Edge detection and binarization is done using the well known canny edge detector.  If w is the width of the image in pixel and h is the height of the image in pixel, the canny edge detector takes as input an array w × h of gray values and sigma (standard deviation)  Output a binary image with a value 1 for edge pixels, i.e., the pixel which constitute an edge and a value 0 for all other pixels. Imran Hossain Faruk 01/28/13 9
  • 10. Fig 4: Grayscale image and its corresponding edge detected binary image Imran Hossain Faruk 01/28/13 10
  • 11. Using adaptive weighted median filter this kind of noise can be removed Fig 5: image with and without noise Imran Hossain Faruk 01/28/13 11
  • 12. Here features extracted all are angles  Features are divided into two vectors  First features is found using the outer shape of the ear.  Second feature vector is found using all other edges  To find the angels, the terms max-line and normal line are used Imran Hossain Faruk 01/28/13 12
  • 13. Max-line: it is the longest line that can be drawn with both its endpoints on the edges of the ear.  The length of a line is measured in terms of Euclidean distance  If there are more than one line, features corresponding to each max-line are to be extracted Imran Hossain Faruk 01/28/13 13
  • 14. Normal Line: lines which are perpendicular to the max-line and which divide the max- line into (n+1) equal parts, where n is a positive integer. Fig 5: Image with max-line and normal line Imran Hossain Faruk 01/28/13 14
  • 15. The max-line m, normal line l1,l2,l3,…..,ln named from top to bottom.  Center of the max-line is c.  P1,P2,P3,……,Pn are the points where the outer edge and the normal lines intersect. Imran Hossain Faruk 01/28/13 15
  • 16. First feature vector(FV1): it can be defined by. FV1 = [θ1, θ2, θ3,…., θn] Fig 6: image showing the angel θ1 Imran Hossain Faruk 01/28/13 16
  • 17. Second feature vector(FV2): all the points where the edges of the ear and normal line intersect except the outer most edge Fig 7: image showing second feature vector and angel respectively Imran Hossain Faruk 01/28/13 17
  • 18. Classification is the task of finding a match for a given query image.  Here classification is performed in two stages.  In first stage the first feature vector is used while in second stage second feature vector is used. Imran Hossain Faruk 01/28/13 18
  • 19. Imran Hossain Faruk 01/28/13 19
  • 20. Imran Hossain Faruk 01/28/13 20
  • 21. A given query image is first tested against all the images in the database using first feature vector  Only the images are matched in the first stage are considered for second stage of classification  As the size of the FV1 is less, that is n (number of normal line) so only n comparison is needed for the first stage classification.  In the second stage classification m*n comparison are required, assuming m points for each normal line.  If the classification is single stage, than total comparison required are I*((n)+(m*n)), where I is the number of images in the database  If the classification is divided into two stage the comparison would be I*n+I1*(m*n) where I1 is the number of image that are matched with respect to the first feature vector.  Saved computation is (I – I1)*(m*n). Imran Hossain Faruk 01/28/13 21
  • 22. Ear recognition can used for both identification and verification purpose.  Since some portion of ear is kept covert by hair so it is very difficult to get the complete image of ear.  Since its uniqueness is moderate we can not rely on it completely. Imran Hossain Faruk 01/28/13 22
  • 23. Ping Yan, Kevin W. Bowyer, “Empirical Evaluation of Advanced Ear Biometrics”, IEEE Computer Society Conference on Computer Vision and Pattern Recognition , 2005  Michal choaras, “Ear biometric based on geometric al feature extraction”, Electronic letters on computer vision and image analysis(Journal ELCVIA), 585-95,2005. Imran Hossain Faruk 01/28/13 23

Notes de l'éditeur

  1. 01/28/13