Page 1 The CSU Face Identification Evaluation System, ICVS 2003 Talk The CSU Face Identification Evaluation System: Its Purpose, Features and Structure.

Slides:



Advertisements
Similar presentations
Real-Time Detection, Alignment and Recognition of Human Faces
Advertisements

Active Appearance Models
QR Code Recognition Based On Image Processing
Zhimin CaoThe Chinese University of Hong Kong Qi YinITCS, Tsinghua University Xiaoou TangShenzhen Institutes of Advanced Technology Chinese Academy of.
Face Recognition and Biometric Systems Eigenfaces (2)
Face Recognition. Introduction Why we are interested in face recognition? Why we are interested in face recognition? Passport control at terminals in.
Face Recognition Ying Wu Electrical and Computer Engineering Northwestern University, Evanston, IL
Face Recognition CPSC UTC/CSE.
Face Description with Local Binary Patterns:
Face Recognition Method of OpenCV
Automatic Feature Extraction for Multi-view 3D Face Recognition
Performance Evaluation Measures for Face Detection Algorithms Prag Sharma, Richard B. Reilly DSP Research Group, Department of Electronic and Electrical.
Face Recognition and Biometric Systems
Computer Vision Spring ,-685 Instructor: S. Narasimhan Wean 5403 T-R 3:00pm – 4:20pm Lecture #20.
Face Verification across Age Progression Narayanan Ramanathan Dr. Rama Chellappa.
CS 790Q Biometrics Face Recognition Using Dimensionality Reduction PCA and LDA M. Turk, A. Pentland, "Eigenfaces for Recognition", Journal of Cognitive.
UPM, Faculty of Computer Science & IT, A robust automated attendance system using face recognition techniques PhD proposal; May 2009 Gawed Nagi.
吳家宇 吳明翰 Face Detection Based on Template Matching and 2DPCA Algorithm 2009/01/14.
Face detection and recognition Many slides adapted from K. Grauman and D. Lowe.
Face Recognition Jeremy Wyatt.
Evaluation of Image Pre-processing Techniques for Eigenface Based Face Recognition Thomas Heseltine york.ac.uk/~tomh
Subspace Representation for Face Recognition Presenters: Jian Li and Shaohua Zhou.
FACE RECOGNITION, EXPERIMENTS WITH RANDOM PROJECTION
Performance Evaluation in Computer Vision Kyungnam Kim Computer Vision Lab, University of Maryland, College Park.
EECE 279: Real-Time Systems Design Vanderbilt University Ames Brown & Jason Cherry MATCH! Real-Time Facial Recognition.
Comparison and Combination of Ear and Face Images in Appearance-Based Biometrics IEEE Trans on PAMI, VOL. 25, NO.9, 2003 Kyong Chang, Kevin W. Bowyer,
Page 1 CVPR Workshop: Statistical Analysis in Computer Vision A Statistical Assessment of Subject Factors in the PCA Recognition of Human Subjects Geof.
Chapter 11: Inference for Distributions
Face Recognition: An Introduction
A PCA-based feature extraction method for face recognition — Adaptively weighted sub-pattern PCA (Aw-SpPCA) Group members: Keren Tan Weiming Chen Rong.
CS 485/685 Computer Vision Face Recognition Using Principal Components Analysis (PCA) M. Turk, A. Pentland, "Eigenfaces for Recognition", Journal of Cognitive.
Vision-Based Biometric Authentication System by Padraic o hIarnain Final Year Project Presentation.
Face Recognition Using Neural Networks Presented By: Hadis Mohseni Leila Taghavi Atefeh Mirsafian.
Wang, Z., et al. Presented by: Kayla Henneman October 27, 2014 WHO IS HERE: LOCATION AWARE FACE RECOGNITION.
Gender and 3D Facial Symmetry: What’s the Relationship ? Xia BAIQIANG (University Lille1/LIFL) Boulbaba Ben Amor (TELECOM Lille1/LIFL) Hassen Drira (TELECOM.
Face Alignment Using Cascaded Boosted Regression Active Shape Models
PCA & LDA for Face Recognition
Dimensionality Reduction: Principal Components Analysis Optional Reading: Smith, A Tutorial on Principal Components Analysis (linked to class webpage)
BPS - 3rd Ed. Chapter 211 Inference for Regression.
Topics: Statistics & Experimental Design The Human Visual System Color Science Light Sources: Radiometry/Photometry Geometric Optics Tone-transfer Function.
Using Support Vector Machines to Enhance the Performance of Bayesian Face Recognition IEEE Transaction on Information Forensics and Security Zhifeng Li,
Classification Course web page: vision.cis.udel.edu/~cv May 12, 2003  Lecture 33.
A Two-level Pose Estimation Framework Using Majority Voting of Gabor Wavelets and Bunch Graph Analysis J. Wu, J. M. Pedersen, D. Putthividhya, D. Norgaard,
Face Recognition: An Introduction
CSE 185 Introduction to Computer Vision Face Recognition.
Real-Time Detection, Alignment and Recognition of Human Faces Rogerio Schmidt Feris Changbo Hu Matthew Turk Pattern Recognition Project June 12, 2003.
Principal Manifolds and Probabilistic Subspaces for Visual Recognition Baback Moghaddam TPAMI, June John Galeotti Advanced Perception February 12,
28. Multiple regression The Practice of Statistics in the Life Sciences Second Edition.
Analyzing Expression Data: Clustering and Stats Chapter 16.
Face Image-Based Gender Recognition Using Complex-Valued Neural Network Instructor :Dr. Dong-Chul Kim Indrani Gorripati.
Chapter 20 Classification and Estimation Classification – Feature selection Good feature have four characteristics: –Discrimination. Features.
GENDER AND AGE RECOGNITION FOR VIDEO ANALYTICS SOLUTION PRESENTED BY: SUBHASH REDDY JOLAPURAM.
Timo Ahonen, Abdenour Hadid, and Matti Pietikainen
University of South Florida, Tampa1 Gait Recognition and Inverse Biometrics Sudeep Sarkar (Zongyi Liu, Pranab Mohanty) Computer Science and Engineering.
Learning Photographic Global Tonal Adjustment with a Database of Input / Output Image Pairs.
Notes on HW 1 grading I gave full credit as long as you gave a description, confusion matrix, and working code Many people’s descriptions were quite short.
Intelligent Database Systems Lab 國立雲林科技大學 National Yunlin University of Science and Technology 1 Recognizing Partially Occluded, Expression Variant Faces.
3D Face Recognition Using Range Images Literature Survey Joonsoo Lee 3/10/05.
BPS - 5th Ed. Chapter 231 Inference for Regression.
Class Six Turn In: Chapter 15: 30, 32, 38, 44, 48, 50 Chapter 17: 28, 38, 44 For Class Seven: Chapter 18: 32, 34, 36 Chapter 19: 26, 34, 44 Quiz 3 Read.
University of Ioannina
Recognition with Expression Variations
PRESENTED BY Yang Jiao Timo Ahonen, Matti Pietikainen
Lecture 8:Eigenfaces and Shared Features
Face Recognition and Feature Subspaces
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,”
Face Recognition and Detection Using Eigenfaces
Learning Gender with Support Faces
Basic Practice of Statistics - 3rd Edition Inference for Regression
Presentation transcript:

Page 1 The CSU Face Identification Evaluation System, ICVS 2003 Talk The CSU Face Identification Evaluation System: Its Purpose, Features and Structure David S. Bolme, J. Ross Beveridge, Marcio Teixeira and Bruce A. Draper Computer Science, Colorado State University 3rd International Conference on Computer Vision Systems - ICVS 2003

Page 2 The CSU Face Identification Evaluation System, ICVS 2003 Talk Goals of the CSU Face Recognition Evaluation Work Baseline/control Face Recognition algorithms. –Four algorithms selected from FERET 96/97 study. PCA, Eigenfaces (Turk and Pentland, MIT) PCA+LDA, (Zhao et. al., Maryland) Bayesian Image diff. Classifier, (Moghaddam et. al., MIT) Elastic Bunch Graph(Okada, et. al., USC) –Reference implementations in ANSI C. CSU Face Identification Evaluation System Statistical methodology for studying algorithms. –Parametric and Nonparametric methods –Standardized protocols and associated scripts. Determine critical factors that influence performance.

Page 3 The CSU Face Identification Evaluation System, ICVS 2003 Talk Obtaining the CSU Face Identification Evaluation System The Evaluation of Face Recognition Algorithms Website. First release of code on March 1, 2001 Current code release, –Version 4.0, –October 31, 2002 Over 1,500 downloads of Version 4.0 through March 2003 Users Guide is included and also available separately.

Page 4 The CSU Face Identification Evaluation System, ICVS 2003 Talk This ICVS 2003 Paper overlaps parts of the User’s Guide CSU Face Identification Evaluation System: Users Guide Installation Testing the system –Scripts,scrapshots System Overview –Image Formats –Distance Files Image Preprocessing Algorithms –PCA, –PCA+LDA, –BIC Analysis –Cumulative Match Curves –Error bars & distributions

Page 5 The CSU Face Identification Evaluation System, ICVS 2003 Talk System Overview Subspace Training Subspace Project Rank Curve Testing Permutation Testing Preprocessing Training Testing Analysis Standard Cumulative Match Curves Probability Distribution for Recognition Rate Normalization Bayesian Training Bayesian Project

Page 6 The CSU Face Identification Evaluation System, ICVS 2003 Talk Refinement of NIST preprocessing used in FERET. Image Preprocessing Integer to float conversion –Converts 256 gray levels to single-floats Geometric Normalization –Aligns human chosen eye coordinates Masking –Crop with elliptical mask leaving only face visible. Histogram Equalization –Histogram equalizes unmasked pixels: 256 levels. Pixel normalization –Shift and scale pixel values so mean pixel value is zero and standard deviation over all pixels is one.

Page 7 The CSU Face Identification Evaluation System, ICVS 2003 Talk The csuSubspace module: PCA and PCA+LDA … PCA+LDA space projection Distance Matrix Training images Eigenspace Combined space (PCA+LDA) Training Testing …

Page 8 The CSU Face Identification Evaluation System, ICVS 2003 Talk Bayesian Image difference Classifier: Take Difference of Images  Classify difference image as either: Intrapersonal from same subject Extrapersonal from different subjects Intrapersonal Example Extrapersonal Example - - = =

Page 9 The CSU Face Identification Evaluation System, ICVS 2003 Talk Bayesian Image difference Classifier: Training Uses csuSubspace Module csuMakeDiffs csuSubspaceTrain... Extrapersonal... Intrapersonal All Training Images Extrapersonal PCA Subspace Intrapersonal PCA Subspace

Page 10 The CSU Face Identification Evaluation System, ICVS 2003 Talk Bayesian Image difference Classifier: Testing uses csuBayesianProject Extrapersonal PCA Subspace Intrapersonal PCA Subspace CsuBayesianProject Probe & Gallery Images Distance Matrix

Page 11 The CSU Face Identification Evaluation System, ICVS 2003 Talk Evaluation Methodology and Tools Two Distinct Questions 1.Is an observed difference in performance significant? Monte Carlo Inference. Generalized Linear Models. 2.What covariates, and combinations of covariates, most influence performance? And how much? McNemar’s Test. Monte Carlo Inference. McNemar’sTest Tally when one algorithm succeeds and the other fails. Monte Carlo Inference Example: Sample Recognition Rate Probability Distribution created by perturbing probe gallery choice. Generalized Linear Model Example: Mixed Effects Logistic Regression with Repeated Measures on People. Power WeakStrong Complexity Simple Involved Covariates covers both features of algorithms and of people Version 4.0

Page 12 The CSU Face Identification Evaluation System, ICVS 2003 Talk Training, Probes, Galleries, What Varies? Training Gallery Probes F F F F FV F VF F VV F F F V V F VV V V V V Essentially FERET 1996/97 Micheals & Boult CVPR 2001 CSU PCA vs. PCA+LDA Analysis CSU PCA+LDA Configuration Analysis F V Fixed Throughout Study Varied, i.e. randomly sampled

Page 13 The CSU Face Identification Evaluation System, ICVS 2003 Talk Producing Cumulative Match Curves

Page 14 The CSU Face Identification Evaluation System, ICVS 2003 Talk Producing Sample Distributions TrainingTesting - Galleries and Probes Day 1Day 2 1 Subject Subject Id PG 67PG 53PG 145PG 6GP 154GP 71GP 98GP … 99GP Balanced Sampling Compare PCA and PCA+LDA. Distance Measures: L1, L2, Mah. Angle (PCA), Soft L2 (PCA+LDA). Methodology: Monte Carlo Sampling of Probe/Gallery. CVPR 2001 citation.

Page 15 The CSU Face Identification Evaluation System, ICVS 2003 Talk PCA vs. PCA+LDA Confidence Intervals Sample Probability Distribution for PCA at rank 1 using Mahalanobis Distance Probability

Page 16 The CSU Face Identification Evaluation System, ICVS 2003 Talk Tabular Output from csuPermute

Page 17 The CSU Face Identification Evaluation System, ICVS 2003 Talk PCA vs. PCA+LDA Comparing Distance Measures Distance Measure Matters PCA favors Mahalanobis Angle PCA+LDA, Soft and Angle Similar Cumulative Match with Error Bars Distance choice more important than subspace.

Page 18 The CSU Face Identification Evaluation System, ICVS 2003 Talk Current Research FERET Subject Covariates Covariates for 2,974 Images, 1,209 Subjects

Page 19 The CSU Face Identification Evaluation System, ICVS 2003 Talk FERET Covariates Results (Preliminary!) Glasses Off Age Young Eyes Open Expression Neutral Race White No Facial Hair No Makeup Mouth Closed No Bangs Skin Clear Male Glasses Off/On Eyes Open/Closed Expression Changes Facial Hair Changes Always Makeup Makeup Changes Mouth Always Open Mouth Changes Bangs Change Skin Not Clear Glasses Always On Age Old Eyes Always Closed Always Non-neutral Race Asian Race African-Amer. Race Other Always Facial Hair Always Bangs Female -50%-40%-30%-20%-10%0% 10%20%30%40%50% Change in Similarity Measure Harder to Recognize Easier to Recognize

Page 20 The CSU Face Identification Evaluation System, ICVS 2003 Talk Conclusion Release 4.0 Contains –Three algorithms: PCA, PCA+LDA, BIC. –Cumulative match curve and probe gallery permutation tools. –Scripts for common experiments, including standard FERET. Supported platforms include –Code is ANSI C: Unix, Windows, … –Turn-key scripts and code tested on Linux, Solaris, Darwin. Over 1,500 downloads since October 31, Related papers on web site. Near Future - Release: 5.0 –Elastic Bunch Graph Matching (USC FERET). –Data Preparation for Generalized Linear Models. PCA+LDA Configuration and FERET Subject Covariate Study.

Page 21 The CSU Face Identification Evaluation System, ICVS 2003 Talk The End

Page 22 The CSU Face Identification Evaluation System, ICVS 2003 Talk Help for csuPreprocesNormalize

Page 23 The CSU Face Identification Evaluation System, ICVS 2003 Talk Help for SubspaceTrain

Page 24 The CSU Face Identification Evaluation System, ICVS 2003 Talk Help for csuSubspaceProject

Page 25 The CSU Face Identification Evaluation System, ICVS 2003 Talk Help for csuMakeDiffs First step in Bayesian Algorithm

Page 26 The CSU Face Identification Evaluation System, ICVS 2003 Talk Help for csuBayesianProject

Page 27 The CSU Face Identification Evaluation System, ICVS 2003 Talk Help for csuAnalysis Tools