H OW TO C ONTROL A CCEPTANCE T HRESHOLD FOR B IOMETRIC S IGNATURES WITH D IFFERENT C ONFIDENCE V ALUES ? Yasushi Makihara( 槇原靖 ), Md. Altab Hossain, Yasushi.

Slides:

Advertisements

Similar presentations

Dept of Bioenvironmental Systems Engineering National Taiwan University Lab for Remote Sensing Hydrology and Spatial Modeling STATISTICS Hypotheses Test.

Advertisements

One Sample T-tests One sample t-tests are used in the following two situations The size of a sample is less than 25 The population standard deviation is.

Hypothesis testing Another judgment method of sampling data.

Evaluating Classifiers

Happiness comes not from material wealth but less desire. 1.

Iris Recognition Under Various Degradation Models Hans Christian Sagbakken.

© Tan,Steinbach, Kumar Introduction to Data Mining 4/18/ Other Classification Techniques 1.Nearest Neighbor Classifiers 2.Support Vector Machines.

From the homework: Distribution of DNA fragments generated by Micrococcal nuclease digestion mean(nucs) = bp median(nucs) = 110 bp sd(nucs+ = 17.3.

Biometrics & Security Tutorial 7. 1 (a) Please compare two different kinds of biometrics technologies: Retina and Iris. (P8:2-3)

Topic 6: Introduction to Hypothesis Testing

D IVERSITY - BASED, MODEL - GUIDED CONSTRUCTION OF SYNTHETIC GENE NETWORKS WITH PREDICTED FUNCTIONS Tom Ellis, Xiao Wang & James J Collins 1 VC Lab, Dept.

T IME WARPING OF EVOLUTIONARY DISTANT TEMPORAL GENE EXPRESSION DATA BASED ON NOISE SUPPRESSION Yury Goltsev and Dmitri Papatsenko *Department of Molecular.

Assessing and Comparing Classification Algorithms Introduction Resampling and Cross Validation Measuring Error Interval Estimation and Hypothesis Testing.

Classification and risk prediction

Keystroke Biometric : ROC Experiments Team Abhishek Kanchan Priyanka Ranadive Sagar Desai Pooja Malhotra Ning Wang.

Radial Basis Functions

Estimation from Samples Find a likely range of values for a population parameter (e.g. average, %) Find a likely range of values for a population parameter.

10 Hypothesis Testing. 10 Hypothesis Testing Statistical hypothesis testing The expression level of a gene in a given condition is measured several.

© sebastian thrun, CMU, The KDD Lab Intro: Outcome Analysis Sebastian Thrun Carnegie Mellon University

Dynamic Face Recognition Committee Machine Presented by Sunny Tang.

Learning From Data Chichang Jou Tamkang University.

Darlene Goldstein 29 January 2003 Receiver Operating Characteristic Methodology.

Chapter 11 Integration Information Instructor: Prof. G. Bebis Represented by Reza Fall 2005.

4-1 Statistical Inference The field of statistical inference consists of those methods used to make decisions or draw conclusions about a population.

Ch 15 - Chi-square Nonparametric Methods: Chi-Square Applications

Chapter 5 Basic System Errors (Alireza Tavakkoli).

Inference about a Mean Part II

Robert S. Zack, Charles C. Tappert, and Sung-Hyuk Cha Pace University, New York Performance of a Long-Text-Input Keystroke Biometric Authentication System.

Biometric ROC Curves Methods of Deriving Biometric Receiver Operating Characteristic Curves from the Nearest Neighbor Classifier Robert Zack dissertation.

ROC Curve and Classification Matrix for Binary Choice Professor Thomas B. Fomby Department of Economics SMU Dallas, TX February, 2015.

05/06/2005CSIS © M. Gibbons On Evaluating Open Biometric Identification Systems Spring 2005 Michael Gibbons School of Computer Science & Information Systems.

Population Proportion The fraction of values in a population which have a specific attribute p = Population proportion X = Number of items having the attribute.

Chapter 12 Inferring from the Data. Inferring from Data Estimation and Significance testing.

Chapter 5 DESCRIBING DATA WITH Z-SCORES AND THE NORMAL CURVE.

Choosing Statistical Procedures

KinWrite: Handwriting-Based Authentication Using Kinect Proceedings of the 20th Annual Network & Distributed System Security Symposium, NDSS 2013 Jing.

Probability Distributions and Test of Hypothesis Ka-Lok Ng Dept. of Bioinformatics Asia University.

Digital Camera and Computer Vision Laboratory Department of Computer Science and Information Engineering National Taiwan University, Taipei, Taiwan, R.O.C.

Digital Camera and Computer Vision Laboratory Department of Computer Science and Information Engineering National Taiwan University, Taipei, Taiwan, R.O.C.

1 Biometrics and the Department of Defense February 17, 2003.

Operating Characteristic Curve

Normal Distributions Z Transformations Central Limit Theorem Standard Normal Distribution Z Distribution Table Confidence Intervals Levels of Significance.

Maximum Likelihood Estimator of Proportion Let {s 1,s 2,…,s n } be a set of independent outcomes from a Bernoulli experiment with unknown probability.

Computational Intelligence: Methods and Applications Lecture 12 Bayesian decisions: foundation of learning Włodzisław Duch Dept. of Informatics, UMK Google:

CpSc 810: Machine Learning Evaluation of Classifier.

Lecture notes for Stat 231: Pattern Recognition and Machine Learning 3. Bayes Decision Theory: Part II. Prof. A.L. Yuille Stat 231. Fall 2004.

A ROBUST B AYESIAN TWO - SAMPLE TEST FOR DETECTING INTERVALS OF DIFFERENTIAL GENE EXPRESSION IN MICROARRAY TIME SERIES Oliver Stegle, Katherine Denby,

Designing multiple biometric systems: Measure of ensemble effectiveness Allen Tang NTUIM.

ECE 471/571 – Lecture 6 Dimensionality Reduction – Fisher’s Linear Discriminant 09/08/15.

Twenty Second Conference on Artificial Intelligence AAAI 2007 Improved State Estimation in Multiagent Settings with Continuous or Large Discrete State.

Biometric for Network Security. Finger Biometrics.

Introducing Communication Research 2e © 2014 SAGE Publications Chapter Seven Generalizing From Research Results: Inferential Statistics.

Classification Course web page: vision.cis.udel.edu/~cv May 14, 2003  Lecture 34.

G. Cowan Computing and Statistical Data Analysis / Stat 9 1 Computing and Statistical Data Analysis Stat 9: Parameter Estimation, Limits London Postgraduate.

Cameron Rowe.  Introduction  Purpose  Implementation  Simple Example Problem  Extended Kalman Filters  Conclusion  Real World Examples.

Chapter 7: The Distribution of Sample Means

S PIKE LATENCY AND JITTER OF NEURONAL MEMBRANE PATCHES WITH STOCHASTIC H ODGKIN –H UXLEY CHANNELS Mahmut Ozer, MuhammetUzuntarla, Matjaž Perc, Lyle J.Graham.

Bor-Sen Chen, Chia-Hung Chang, Yung-Jen Chuang

Inference for the Mean of a Population

Module 22: Proportions: One Sample

Inferring Population Parameters

When we free ourselves of desire,

ФОРЕНЗИКА У КРИМИНАЛИСТИЦИ

Chapter 9 Hypothesis Testing

Statistical inference

4-1 Statistical Inference

ROC Curves Receiver Operating Characteristic (ROC) curves are used to determine the appropriate operating point of a system, the tradeoff between False.

Numerical Computation and Optimization

Statistical inference

Presentation transcript:

H OW TO C ONTROL A CCEPTANCE T HRESHOLD FOR B IOMETRIC S IGNATURES WITH D IFFERENT C ONFIDENCE V ALUES ? Yasushi Makihara( 槇原靖 ), Md. Altab Hossain, Yasushi Yagi( 八木康史 ) 大阪大学 ICPR VC Lab, Dept. of Computer Science, NTHU, Taiwan

I NTRODUCTION Biometrics-based verification Quality measure False Acceptance Rate(FAR) False Rejection Rate(FRR) Receiver Operating Characteristics (ROC) curve 2 VC Lab, Dept. of Computer Science, NTHU, Taiwan

A DAPTIVE ACCEPTANCE THRESHOLD CONTROL Receiver Operating Characteristics (ROC) curve 3 VC Lab, Dept. of Computer Science, NTHU, Taiwan

A DAPTIVE ACCEPTANCE THRESHOLD CONTROL ROC curve 4 VC Lab, Dept. of Computer Science, NTHU, Taiwan

A DAPTIVE ACCEPTANCE THRESHOLD CONTROL ROC curve 5 VC Lab, Dept. of Computer Science, NTHU, Taiwan

A DAPTIVE ACCEPTANCE THRESHOLD CONTROL Simplified example High confidence (right side) Low confidence(left side) 6 VC Lab, Dept. of Computer Science, NTHU, Taiwan

A DAPTIVE ACCEPTANCE THRESHOLD CONTROL Simplified example High confidence (right side) Low confidence(left side) 7 VC Lab, Dept. of Computer Science, NTHU, Taiwan

A DAPTIVE ACCEPTANCE THRESHOLD CONTROL FAR FRR Error rate Acceptance rate 8 VC Lab, Dept. of Computer Science, NTHU, Taiwan

A DAPTIVE ACCEPTANCE THRESHOLD CONTROL Gradient Lower error gradient accepted samples are positive samples Higher error gradient accepted samples are negative samples Middle error gradient positive and negative samples in the accepted samples are balanced 9 VC Lab, Dept. of Computer Science, NTHU, Taiwan

A DAPTIVE ACCEPTANCE THRESHOLD CONTROL Implementation (distance, quality measure) Weight ( i th positive sample for k th quality measure control point) 10 VC Lab, Dept. of Computer Science, NTHU, Taiwan

A DAPTIVE ACCEPTANCE THRESHOLD CONTROL Implementation Gaussian kernel-based non-parametric PDF estimation Optimal approximation coef. of regularization term 11 VC Lab, Dept. of Computer Science, NTHU, Taiwan

E XPERIMENTS Test data VC Lab, Dept. of Computer Science, NTHU, Taiwan 12

E XPERIMENTS Simulation data VC Lab, Dept. of Computer Science, NTHU, Taiwan 13

C ONCLUSION & D ISCUSSION Outperforms the previous methods in terms of the ROC curve, particularly under a lower FAR or FRR tolerance condition With the assumption that distributions of distance and quality measures are consistent in the training and test sets, the optimality is not guaranteed in case where the distributions are in consistent. 14 VC Lab, Dept. of Computer Science, NTHU, Taiwan