FACE RECOGNITION AUTHOR: Łukasz Przywarty - 171018.

Slides:



Advertisements
Similar presentations
Face Recognition Sumitha Balasuriya.
Advertisements

Dr. Marc Valliant, VP & CTO
Face Recognition. Introduction Why we are interested in face recognition? Why we are interested in face recognition? Passport control at terminals in.
Face Recognition CPSC UTC/CSE.
Face Description with Local Binary Patterns:
Face Recognition Method of OpenCV
Amir Hosein Omidvarnia Spring 2007 Principles of 3D Face Recognition.
By: W. Zhao, R. Chellappa, P.J. Phillips, and A. Rosenfeld Presented By: Diego Velasquez.
Facial feature localization Presented by: Harvest Jang Spring 2002.
Face Recognition and Biometric Systems
As applied to face recognition.  Detection vs. Recognition.
Face Recognition & Biometric Systems, 2005/2006 Face recognition process.
Computer Vision Spring ,-685 Instructor: S. Narasimhan Wean 5403 T-R 3:00pm – 4:20pm Lecture #20.
Face Recognition Under Varying Illumination Erald VUÇINI Vienna University of Technology Muhittin GÖKMEN Istanbul Technical University Eduard GRÖLLER Vienna.
A Study of Approaches for Object Recognition
UPM, Faculty of Computer Science & IT, A robust automated attendance system using face recognition techniques PhD proposal; May 2009 Gawed Nagi.
Face Detection: a Survey Speaker: Mine-Quan Jing National Chiao Tung University.
Eigenfaces As we discussed last time, we can reduce the computation by dimension reduction using PCA –Suppose we have a set of N images and there are c.
FACE RECOGNITION BY: TEAM 1 BILL BAKER NADINE BROWN RICK HENNINGS SHOBHANA MISRA SAURABH PETHE.
Face Recognition: A Comparison of Appearance-Based Approaches
EECE 279: Real-Time Systems Design Vanderbilt University Ames Brown & Jason Cherry MATCH! Real-Time Facial Recognition.
Smart Traveller with Visual Translator for OCR and Face Recognition LYU0203 FYP.
Face Recognition: An Introduction
Three-Dimensional Face Recognition Using Surface Space Combinations Thomas Heseltine, Nick Pears, Jim Austin Advanced Computer Architecture Group Department.
A PCA-based feature extraction method for face recognition — Adaptively weighted sub-pattern PCA (Aw-SpPCA) Group members: Keren Tan Weiming Chen Rong.
A Brief Survey on Face Recognition Systems Amir Omidvarnia March 2007.
PhD Thesis. Biometrics Science studying measurements and statistics of biological data Most relevant application: id. recognition 2.
TEAM-1 JACKIE ABBAZIO SASHA PEREZ DENISE SILVA ROBERT TESORIERO Face Recognition Systems.
Face Recognition CPSC 601 Biometric Course.
Facial Recognition CSE 391 Kris Lord.
Vision-Based Biometric Authentication System by Padraic o hIarnain Final Year Project Presentation.
A survey of image-based biometric identification methods: Face, finger print, iris, and others Presented by: David Lin ECE738 Presentation of Project Survey.
Computer vision.
Recognition Part II Ali Farhadi CSE 455.
Introduction Detecting Faces in a Single Image –Knowledge-Based Methods –Feature-Based Methods –Template Matching –Appearance-Based Methods Face Image.
February 27, Face Recognition BIOM 426 Instructor: Natalia A. Schmid Imaging Modalities Processing Methods.
BACKGROUND LEARNING AND LETTER DETECTION USING TEXTURE WITH PRINCIPAL COMPONENT ANALYSIS (PCA) CIS 601 PROJECT SUMIT BASU FALL 2004.
Face Recognition System By Arthur. Introduction  A facial recognition system is a computer application for automatically identifying or verifying a person.
Access Control Via Face Recognition Progress Review.
1 Recognition by Appearance Appearance-based recognition is a competing paradigm to features and alignment. No features are extracted! Images are represented.
Access Control Via Face Recognition. Group Members  Thilanka Priyankara  Vimalaharan Paskarasundaram  Manosha Silva  Dinusha Perera.
A Seminar Report On Face Recognition Technology A Seminar Report On Face Recognition Technology 123seminarsonly.com.
Face Recognition: An Introduction
(Team 1)Jackie Abbazio, Sasha Perez, Denise Silva and Robert Tesoriero (Team 2) Faune Hughes, Daniel Lichter, Richard Oswald and Michael Whitfield Clients:
3D Face Recognition Using Range Images
Facial Recognition Justin Kwong Megan Thompson Raymundo Vazquez-lugo.
Face Image-Based Gender Recognition Using Complex-Valued Neural Network Instructor :Dr. Dong-Chul Kim Indrani Gorripati.
Timo Ahonen, Abdenour Hadid, and Matti Pietikainen
Facial Recognition Systems By Derek Ciocca. 1.Parts of the system 2.Improving Accuracy 3.Current and future uses.
3D Face Recognition Using Range Images Literature Survey Joonsoo Lee 3/10/05.
Facial Recognition By Lisa Tomko.
Face Recognition Technology By Catherine jenni christy.M.sc.
A facial recognition system is a computer application for automatically identifying or verifying a person from a digital image or a video frame from.
ZAGAZIG UNIVERSITY-BENHA BRANCH SHOUBRA FACULTY OF ENGINEERING ELECTRICAL ENGINGEERING DEPT. COMPUTER SYSTEM DIVISION GRAUDATION PROJECT 2003.
Face Detection & Recognition
Face Detection 蔡宇軒.
RAJAT GOEL E.C.-09. The information age is quickly revolutionizing the way transactions are completed. Using the proper PIN gains access, but the user.
Submitted by: Siddharth Jain (08EJCIT075) Shirin Saluja (08EJCIT071) Shweta Sharma (08EJCIT074) VIII Semester, I.T Department Submitted to: Mr. Abhay Kumar.
By: Suvigya Tripathi (09BEC094) Ankit V. Gupta (09BEC106) Guided By: Prof. Bhupendra Fataniya Dept. of Electronics and Communication Engineering, Nirma.
FACE RECOGNITION. A facial recognition system is a computer application for automatically identifying or verifying a person from a digital image or a.
Presented By Bhargav (08BQ1A0435).  Images play an important role in todays information because A single image represents a thousand words.  Google's.
Face Recognition 1.
PRESENTED BY Yang Jiao Timo Ahonen, Matti Pietikainen
Fast Preprocessing for Robust Face Sketch Synthesis
Recognition: Face Recognition
Final Year Project Presentation --- Magic Paint Face
Outline Peter N. Belhumeur, Joao P. Hespanha, and David J. Kriegman, “Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection,”
Facial Recognition in Biometrics
Faculty of Science IT Department Lecturer: Raz Dara MA.
Presentation transcript:

FACE RECOGNITION AUTHOR: Łukasz Przywarty - 171018

Table of contents Introduction Recognition process Face detection Feature extraction Face recognition Application example Summary Literature Face recognition – 2/18

Introduction Why? Face recognition – 3/18 Areas Applications Information Security Access security (OS, data bases) Data privacy (e.g. medical records) User authentication (trading, on line banking) Access management Secure access authentication (restricted facilities) Permission based systems Access log or audit trails Biometrics Person identification (national IDs, Passports, voter registrations, driver licenses) Automated identity verification (border controls) Law Enforcement Video surveillance Suspect identification Suspect tracking (investigation) Simulated aging Forensic Reconstruction of faces from remains Personal security Home video surveillance systems Expression interpretation (driver monitoring system) Entertainment - Leisure Home video game systems Photo camera applications Face recognition – 3/18

Introduction Since when? 1960’s – semi-automated system: required the administrator to locate face coordinates; computer used this for recognition 1970’s – Goldstein, Harmon, Lesk: vector containing 21 features e.g eyebrow weight, nose length as the basis to recognize faces (pattern classification) 1986 – Kirby, Sirovich: methods based on PCA (Principal Component Analysis); goal: represent image in lower dimension without losing much information; dominant approach in following years Face recognition – 4/18

Introduction Problems? Pose variations Observation conditions (angle, light, shadows, reflections etc.) Ageing Facial expression Facial occulsion: make-up, hair style, accesories Face recognition – 5/18

Identification or verification Recognition process How to do it? How to detect face? Detection depending on scenario: Controlled environment – simple edge detection techniques Color images – skin colors can be used to find faces Images in motion – e.g blink detection Input Face detection Feature extraction Face recognition Identification or verification Face recognition – 6/18

Recognition process How to detect face? Detection methods: Knowledge –based methods : they try to capture our knowledge of faces and translate them into set of rules (face has two symmetric eyes, the eye area is darker than the cheeks etc), facial features could be the distance between eyes or color intensity difference. Feature-invariant methods: algorithms that try to find invariant features of a face despite it’s angle or position Face recognition – 7/18

Recognition process How to detect face? for example: algorithms that detect face-like textures or the color of human skin. Template matching try to define face as a function and find a standard template of all the faces, template colud be: face contour, relation between face regions in terms of brightness and darkness, limited to faces that are frontal. Appearance-based methods statistical analysis. Face recognition – 8/18

Recognition process How to standarize image? Histogram modification Image filtration Geometrical transformation Rotate Scale Move Resize Desaturation or color modification Face recognition – 9/18

Division of face recognition systems Feature-based approach First, most intuitive idea First step: localization of points on face images: eyes centre points nose start-end points etc. Next step: measuring: face, nose width, height etc. distances between eyes centres, nose and eyes etc. Problems Accurate points localization Face recognition – 10/18

Division of face recognition systems Feature-based approach Used methods: Geometric Matching Bunch Graph Matching Hidden Markov Model Techniques Face recognition – 11/18

Division of face recognition systems Holistic approach Whole face analysis Methods based on: Correlation: simple method operating on input image pixels, direct comparision to a pattern in database, works if images were taken in almost the same conditions PCA (Principal Component Analysis ) and eigenfaces concept: feature dimension reduction (converts two dimensional vectors into one dimensional vector) extracts the features of face which vary the most, Face recognition – 12/18

Division of face recognition systems Holistic approach problem: image must be the same size and normalized; pose and illumination variation in not acceptable, rate od recognition: 95% LDA (Linear Discriminate Analysis) and Fisherface concept Face recognition – 13/18

Division of face recognition systems Hybrid approach Both local feature and whole face Methods based on: AAM (Active Appearance Model) integrated statistical model which combines a model of shape variation and apperance with new image, built during a training phase, compares both whole face shape and pixels brightness around feature. Face recognition – 14/18

Application example Picasa 3.5 Static images Luxand FaceSDK 66 feature points -30-30 degrees head rotation support 49 700 faces per second Verilook 5.1 Multiface processing Live face detection Tolerance to face posture (near 360 degrees) 44 000 faces per second Multiple samples of same face Face recognition – 15/18

Final word Summary? Despite of 40 years development still unreliable 12% of biometric technologies (2nd place, after print) Low effectiveness in pilot projects (UK: Newham, USA: Tampa) Failed trial in airports Face recognition – 16/18

Literature E. Bagherian, R. Wirza O.K. Rahmat. „Facial feature extraction for face recognition: a review” C. Iancu, P. Corcoran, G. Costache . „A review of face recognition techniques for in-camera applications” M. Smiatacz, W. Malina. „Automatic face recognition – methods, problems and applications” K. Ślot. „Rozpoznawanie biometryczne” K. Ślot. „Wybrane zagadnienia biometrii” Face recognition – 17/18

FACE RECOGNITION Thank you for your attention!