Скачать презентацию Biometrics Faces and Identity Verification in a Networked Скачать презентацию Biometrics Faces and Identity Verification in a Networked

a7a791f55965c777a58d2a42e3a112a2.ppt

  • Количество слайдов: 24

Biometrics: Faces and Identity Verification in a Networked World CSI 7163/ELG 5121 Donald Chow Biometrics: Faces and Identity Verification in a Networked World CSI 7163/ELG 5121 Donald Chow dchow [email protected] ca Mathew Samuel [email protected] uottawa. ca

Agenda • Identification • Biometrics • Facial Recognition – PCA – 3 D Expression Agenda • Identification • Biometrics • Facial Recognition – PCA – 3 D Expression Invariant Recognition – 3 D Morphable Model • Biometric Communication – XML implementation of CBEFF • Conclusion • Questions

Three Basic Identification Methods Possession (“something I have”) • Keys • Passport • Smart Three Basic Identification Methods Possession (“something I have”) • Keys • Passport • Smart Card q. Universal q. Unique q. Permanent q. Collectable ü q. Acceptance ü Biometrics (“something I am”) • Face • Fingerprint • Iris q. Universal ü q. Unique ü q. Permanent ü q. Collectable ü q. Acceptance ? Knowledge (“something I know”) • Password • PIN “Sidova” “ 750426 ” q. Universal q. Unique q. Permanent q. Collectable ü q. Acceptance ü

Biometrics • Refer to a broad range of technologies • Automate the identification or Biometrics • Refer to a broad range of technologies • Automate the identification or verification of an individual • Based on human characteristics – Physiological: Face, fingerprint, iris – Behavioural: Hand-written signature, gait, voice Characteristics Templates 0110010101… 011010100100110… 001100010010010. . .

Typical Biometric Authentication Workflow Enroll: Enrollment subsystem Template Feature Extractor Biometric reader 1010010… Authenticate: Typical Biometric Authentication Workflow Enroll: Enrollment subsystem Template Feature Extractor Biometric reader 1010010… Authenticate: Authentication subsystem Match or No Match Template Biometric Matcher Database 1010010… Biometric reader Feature Extractor

Identification vs. Verification Identification (1: N) Biometric reader Biometric Matcher Database This person is Identification vs. Verification Identification (1: N) Biometric reader Biometric Matcher Database This person is Emily Dawson I am Emily Dawson Verification (1: 1) ID Biometric reader Biometric Matcher Match Database

Faces • Faces are integral to human interaction • Manual facial recognition is already Faces • Faces are integral to human interaction • Manual facial recognition is already used in everyday authentication applications – ID Card systems (passports, health card, and driver’s license) – Booking stations – Surveillance operations

Facial Recognition • Facial recognition requires 2 steps: – Facial Detection (will not present Facial Recognition • Facial recognition requires 2 steps: – Facial Detection (will not present today) – Facial Recognition • Typical Facial Recognition technology automates the recognition of faces using one of two 2 modeling approaches: – Face appearance • 2 D Eigen faces • 3 D Morphable Model – Face geometry • 3 D Expression Invariant Recognition

Facial Recognition Algorithms • 2 D Eigenface – Principle Component Analysis (PCA) • 3 Facial Recognition Algorithms • 2 D Eigenface – Principle Component Analysis (PCA) • 3 D Face Recognition – 3 D Expression Invariant Recognition – 3 D Morphable Model

Facial Recognition: Eigenface • Decompose face images into a small set of characteristic feature Facial Recognition: Eigenface • Decompose face images into a small set of characteristic feature images. • A new face is compared to these stored images. • A match is found if the new faces is close to one of these images.

Facial Recognition: PCA - Overview • Create training set of faces and calculate the Facial Recognition: PCA - Overview • Create training set of faces and calculate the eigenfaces • Project the new image onto the eigenfaces. • Check if image is close to “face space”. • Check closeness to one of the known faces. • Add unknown faces to the training set and re-calculate

Facial Recognition: PCA – Training Set Facial Recognition: PCA – Training Set

Facial Recognition: PCA Training • Find average of training images. • Subtract average face Facial Recognition: PCA Training • Find average of training images. • Subtract average face from each image. • Create covariance matrix • Generate eigenfaces • Each original image can be expressed as a linear combination of the eigenfaces – face space

Facial Recognition: PCA Recognition • A new image is project into the “facespace”. • Facial Recognition: PCA Recognition • A new image is project into the “facespace”. • Create a vector of weights that describes this image. • The distance from the original image to this eigenface is compared. • If within certain thresholds then it is a recognized face.

Facial Recognition: 3 D Expression Invariant Recognition • Treats face as a deformable object. Facial Recognition: 3 D Expression Invariant Recognition • Treats face as a deformable object. • 3 D system maps a face. • Captures facial geometry in canonical form. • Can be compared to other canonical forms.

Facial Recognition: 3 D Morphable Model • Create a 3 D face model from Facial Recognition: 3 D Morphable Model • Create a 3 D face model from 2 D images. • Synthetic facial images are created to add to training set. • PCA can then be done using these images

Pros and Cons • 2 D face recognition methods are sensitive to lighting, head Pros and Cons • 2 D face recognition methods are sensitive to lighting, head orientations, facial expressions and makeup. • 2 D images contain limited information • 3 D Representation of face is less susceptible to isometric deformations (expression changes). • 3 D approach overcomes problem of large facial orientation changes

Communication • Common Biometric Exchange Formats Framework (CBEFF) • XML implementation of CBEFF • Communication • Common Biometric Exchange Formats Framework (CBEFF) • XML implementation of CBEFF • CBEFF Data Elements – Standard Biometric Header – Biometric Specific Memory Block – Signature or MAC

Conclusion • Facial scan has unique advantages over other biometrics • Core technologies are Conclusion • Facial scan has unique advantages over other biometrics • Core technologies are highly researched • Automated facial detection and facial recognition algorithm are not yet mature

References • • • Antonini, G. et al. (2003) “Independent Component Analysis and Support References • • • Antonini, G. et al. (2003) “Independent Component Analysis and Support Vector Machine for Face Feature Extraction”, Signal Processing Institute, Swiss Federal Institute of Technology Lausanne, Switzerland: 1 -8 Bolle, R. M. et al. (2004) Guide to Biometrics, New York: Springer-Verlag: 1 -5 Bronstein, A. M. et al. (2003) “Expression-Invariant 3 D Face Recognition” AVBPA, LNCS (2688): 62 -70, Springer-Verlag Berlin Heidelbert Huang, J et al. (2003) “Component-based Face Recognition with 3 D Morphable Models” Center for Biological and Computational Learning, MIT Jeng, SH. Et al. (1998) “Facial Feature Detection Using Geometrical Face Model: An Efficient Approach” Pattern Recognition, vol 31(3): 273 -282 Nanavati, S. et al. (2002) Biometrics: Identity Verification in a Networked World, New York: John Wiley & Sons, Inc: 1 -5 Storring, M. (2004) “Computer Vision and Human Skin Colour” Computer Vision and Media Technology Laboratory, PHD Dissertation, Aalborg University Turk, M. (1991) “Eigenfaces for Recognition” Journal of Cognitive Neuroscience, The Media Laboratory: Vision and Modeling Group, MIT, vol(3): 1 Vezhevets, V. et al. (2002) “A Survey on Pixel-Based Skin Color Detection Techniques” Graphics Medial Laboratory, Faculty fo Computational Mathematics and Cybernetics, Moscow State University

Questions Questions

Facial Detection: Colour Algorithms: • Pixel-based • Region-based Approaches: • Explicitly defined region within Facial Detection: Colour Algorithms: • Pixel-based • Region-based Approaches: • Explicitly defined region within a specific colour space • Dynamic skin distribution model

Facial Detection: Geometry • Faces decompose into 4 main organs – – Eyebrows Eyes Facial Detection: Geometry • Faces decompose into 4 main organs – – Eyebrows Eyes Nose Mouth • Algorithm – Preprocessing – Matching

Facial Detection: Demo (Torch 3 Vision) Facial Detection: Demo (Torch 3 Vision)