Visual-based ID Verification by Signature Tracking



Similar documents
Biometric Authentication using Online Signatures

ECE 533 Project Report Ashish Dhawan Aditi R. Ganesan

Identity authentication using improved online signature verification method

Efficient on-line Signature Verification System

Biometric Authentication using Online Signature

Keywords image processing, signature verification, false acceptance rate, false rejection rate, forgeries, feature vectors, support vector machines.

SIGNATURE VERIFICATION

STATIC SIGNATURE RECOGNITION SYSTEM FOR USER AUTHENTICATION BASED TWO LEVEL COG, HOUGH TRANSFORM AND NEURAL NETWORK

Handwritten Signature Verification using Neural Network

FACE RECOGNITION BASED ATTENDANCE MARKING SYSTEM

Biometrics is the use of physiological and/or behavioral characteristics to recognize or verify the identity of individuals through automated means.

Establishing the Uniqueness of the Human Voice for Security Applications

Introduction to Pattern Recognition

DESIGN OF DIGITAL SIGNATURE VERIFICATION ALGORITHM USING RELATIVE SLOPE METHOD

LOCAL SURFACE PATCH BASED TIME ATTENDANCE SYSTEM USING FACE.

A colour Code Algorithm for Signature Recognition

Comparison of Elastic Matching Algorithms for Online Tamil Handwritten Character Recognition

3)Skilled Forgery: It is represented by suitable imitation of genuine signature mode.it is also called Well-Versed Forgery[4].

Securing Electronic Medical Records Using Biometric Authentication

Object Recognition and Template Matching

Support Vector Machines for Dynamic Biometric Handwriting Classification

Multimedia Document Authentication using On-line Signatures as Watermarks

Securing Electronic Medical Records using Biometric Authentication

Novelty Detection in image recognition using IRF Neural Networks properties

Document Image Retrieval using Signatures as Queries

MACHINE VISION MNEMONICS, INC. 102 Gaither Drive, Suite 4 Mount Laurel, NJ USA

A PHOTOGRAMMETRIC APPRAOCH FOR AUTOMATIC TRAFFIC ASSESSMENT USING CONVENTIONAL CCTV CAMERA

Open-Set Face Recognition-based Visitor Interface System

International Journal of Advanced Information in Arts, Science & Management Vol.2, No.2, December 2014

Assignment 1 Biometric authentication

T-REDSPEED White paper

USER AUTHENTICATION USING ON-LINE SIGNATURE AND SPEECH

Method of Combining the Degrees of Similarity in Handwritten Signature Authentication Using Neural Networks

Signature Verification Why xyzmo offers the leading solution.

Signature verification using Kolmogorov-Smirnov. statistic

TIETS34 Seminar: Data Mining on Biometric identification

Palmprint Recognition. By Sree Rama Murthy kora Praveen Verma Yashwant Kashyap

International Year of Light 2015 Tech-Talks BREGENZ: Mehmet Arik Well-Being in Office Applications Light Measurement & Quality Parameters

A Prototype For Eye-Gaze Corrected

Computer Graphics. Geometric Modeling. Page 1. Copyright Gotsman, Elber, Barequet, Karni, Sheffer Computer Science - Technion. An Example.

Building an Advanced Invariant Real-Time Human Tracking System

HAND GESTURE BASEDOPERATINGSYSTEM CONTROL

AUTOMATED ATTENDANCE CAPTURE AND TRACKING SYSTEM

High-Performance Signature Recognition Method using SVM

National Performance Evaluation Facility for LADARs

CS231M Project Report - Automated Real-Time Face Tracking and Blending

The Scientific Data Mining Process

CS 534: Computer Vision 3D Model-based recognition

AN IMPROVED DOUBLE CODING LOCAL BINARY PATTERN ALGORITHM FOR FACE RECOGNITION

A secure face tracking system

Template-based Eye and Mouth Detection for 3D Video Conferencing

VEHICLE TRACKING USING ACOUSTIC AND VIDEO SENSORS

Multimodal Biometric Recognition Security System

Anomaly Detection and Predictive Maintenance

Part-Based Recognition

The Role of Size Normalization on the Recognition Rate of Handwritten Numerals

Using Four-Quadrant Charts for Two Technology Forecasting Indicators: Technology Readiness Levels and R&D Momentum

Tracking of Small Unmanned Aerial Vehicles

(I) s(t) = s 0 v 0 (t t 0 ) a (t t 0) 2 (II). t 2 = t v 0. At the time. E kin = 1 2 m v2 = 1 2 m (a (t t 0) v 0 ) 2

HANDS-FREE PC CONTROL CONTROLLING OF MOUSE CURSOR USING EYE MOVEMENT

Effects of Time Normalization on the Accuracy of Dynamic Time Warping

Determining optimal window size for texture feature extraction methods

NFC & Biometrics. Christophe Rosenberger

COEFFICIENT OF KINETIC FRICTION

Signature-based Biometric Authentication

Tracking Groups of Pedestrians in Video Sequences

The Development of a Pressure-based Typing Biometrics User Authentication System

VEHICLE LOCALISATION AND CLASSIFICATION IN URBAN CCTV STREAMS

How To Fix Out Of Focus And Blur Images With A Dynamic Template Matching Algorithm

Error Log Processing for Accurate Failure Prediction. Humboldt-Universität zu Berlin

Article. Electronic Signature Forensics. Copyright Topaz Systems Inc. All rights reserved.

NAVIGATING SCIENTIFIC LITERATURE A HOLISTIC PERSPECTIVE. Venu Govindaraju

Palmprint Recognition with PCA and ICA

Automatic Extraction of Signatures from Bank Cheques and other Documents

DYNAMIC FUZZY PATTERN RECOGNITION WITH APPLICATIONS TO FINANCE AND ENGINEERING LARISA ANGSTENBERGER

Automatic Labeling of Lane Markings for Autonomous Vehicles

BEHAVIOR BASED CREDIT CARD FRAUD DETECTION USING SUPPORT VECTOR MACHINES

Cryptographic key generation using handwritten signature

Tracking in flussi video 3D. Ing. Samuele Salti

Chapter 5 Input. Chapter 5 Objectives. What Is Input? What Is Input? The Keyboard. The Keyboard

RESEARCH ON SPOKEN LANGUAGE PROCESSING Progress Report No. 29 (2008) Indiana University

TexPoint fonts used in EMF. Read the TexPoint manual before you delete this box.: AAAAA

Intrusion Log Sharing University of Wisconsin-Madison

Capacity of an RCE-based Hamming Associative Memory for Human Face Recognition

Tutorial for proteome data analysis using the Perseus software platform

Statistical Analysis of Signature Features with Respect to Applicability in Off-line Signature Verification

Alternative Biometric as Method of Information Security of Healthcare Systems

Voice Authentication for ATM Security

Signature Region of Interest using Auto cropping

Machine Learning for Medical Image Analysis. A. Criminisi & the InnerEye MSRC

Taking Inverse Graphics Seriously

Approximate Object Location and Spam Filtering on Peer-to-Peer Systems

Transcription:

Visual-based ID Verification by Signature Tracking Mario E. Munich and Pietro Perona California Institute of Technology www.vision.caltech.edu/mariomu

Outline Biometric ID Visual Signature Acquisition Description of the system Tracking results Signature Verification Dynamic Time Warping Experimental Results Conclusions and further work AVBPA99 - March 3rd, 999

Biometric ID Identification based on measurements of human biological characteristics Vision-based: Face Recognition [Taylor et. al.,turk & Pentland, Wiskott et.al.] Fingerprint Recognition [Jain et. al.] Other: Voice Recognition Signature Verification Iris Scanning [Daugman] Retina Scanning... AVBPA99 - March 3rd, 999 3

Why visual signature acquisition? Current I/O computer interfaces have limitations for decreasing their size. tablet digitizer screen keyboard Cell phone + PDA Future new I/O computer interfaces will involve Audio and Visual techniques. PDA camera mouse microphone Advantages: smaller size implementing them in VLSI. more natural way for people to communicate with computers. AVBPA99 - March 3rd, 999 4

Visual signature acquisition AVBPA99 - March 3rd, 999 5

Visual signature acquisition Preprocessing Pen Tip Tracker Ballpoint Detector Filter Signature Verification True! AVBPA99 - March 3rd, 999 6

Preprocessing Get the template of the pen tip Mouse-clicking (manual) Pen familiar to the system Unknown pen (size = 5x5 pixels) Get the portion of image where the pen tracker looks for the pen tip (size = 3x3 pixels) AVBPA99 - March 3rd, 999 7

Pen tip tracker Portion of the image extracted in order to compute correlation Predicted position of the pen tip Pen tip template Location of maximum correlation Predicted position of the pen tip The most likely position of the pen tip is given by the location of maximum correlation AVBPA99 - March 3rd, 999 8

Filter Predicts the position of the pen tip in the following image Speeds up computations Smoothes out the trajectory Estimates the position of the pen tip for missing frames Model of pen tip s dynamics dx dt dv dt da dt y(t) = = = = v(t) a(t) n a (t) x(t) + n y (t) where: x(t): D pen tip s position v(t): D pen tip s velocity a(t): D pen tip s acceleration y(t): location of max. correlation AVBPA99 - March 3rd, 999 9

Real Time Implementation Camera Pentium 30 Frame grabber PCI Bus The frame grabber is a PXC00 from Imagination. The system runs at 60 Hz with a total processing time of 5ms per frame. No calibration needed. AVBPA99 - March 3rd, 999 0

Acquired signatures Example signature Prototype Forgery AVBPA99 - March 3rd, 999

Signature Verification Off-line Signature Verification Works on a static image of the signature, i.e., the result of the act of signing. On-line Signature Verification Works on the dynamic process of generation of the signature, i.e., the action of signing itself. ( Automatic signature verification and writer identification, the state of the art, by M.Parizeau and R. Plamondon is a good survey paper) AVBPA99 - March 3rd, 999

Signature Verification New signature Comparison True signature or forgery? Prototype Training set AVBPA99 - March 3rd, 999 3

Signature Verification Previous work on Signature Verification using Dynamical Time Warping: Sato and Kogure, 98 Parizeau and Plamondon, 990 Huang and Yang, 995 Wirtz, 995 Nalwa, 997 Munich and Perona 98, 99... AVBPA99 - March 3rd, 999 4

Signature Verification P (φ (t-)) v(t-) Signature (C ) Comparison of two signatures P (φ (t)) P (φ (t-)) Signature (C ) v(t) P (φ (t)) Similarity measure ( distance between C and C ) C = ( P D( C, C (),..., P ) d(( P = = Elementary distance of matching P (φ (t-)) with P (φ (t-)) and P (φ (t)) with P (φ (t)). P ( φ ( t)) T t= ( φ ( t )), ( φ ( t )) ),( ( φ ( t)), ( φ ( t)) )) ( T ) P ), C ( φ P ( φ ( t)) ( t)) P [ ] φ ( t) AVBPA99 - March 3rd, 999 5 P = P ( P ( φ P () ( t)) P ( φ ( t )),..., P ( φ ( T ) P ( φ ( t )) ), φ ( t )) P P Matching function = ( φ φ ( t) ( t )) =

Dynamical Time Warping(DTW) Given C = (P (),,P (T )), C = (P (),,P (T )) and the distance function D(C,C ), DTW finds a warping function φ = [φ, φ ] T that minimizes the dissimilarity between C and C : φ = arg min D(C,C) φ with the following recursion [Bellman et.al.,957, Sakoe & Shiba,978]: D(t) = min {D(t ) + d((p( φ (t )),P ( φ (t )) ),(P ( φ (t)),p ( φ (t))))} φ(t ), φ (t ) Cumulated distance up to step t Cumulated distance up to step (t-) Elementary distance added by matching P (φ (t-)) with P (φ (t-)) and P (φ (t)) with P (φ (t)). AVBPA99 - March 3rd, 999 6

Dynamical Time Warping φ φ (t) = j Recursion (for the discrete case): D(t) = D(i,j) = d((p ( φ (t )),P min φ(t ), φ (t ) ( φ (t )) ),(P {D(t ) + (i),p (j) ))} φ (t) = i Warping plane φ φ (t) = j φ (t) = i Local slope constraints D(i,j) = D(i,j) min D(i,j ) D(i,j ) + + + d((i,j),(i,j)) d((i,j ),(i,j)) d((i,j ),(i,j)) AVBPA99 - March 3rd, 999 7

Dynamical Time Warping φ Maximum deviation from linear warping constraint Dynamical Time Warping solution φ (t) Global slope constraint φ (t) φ The algorithm is O(N) both in time and spatial complexity. Constraints could be used in order to reduce the complexity since they will reduce the number of nodes to be explored. AVBPA99 - March 3rd, 999 8

Dynamical Time Warping x(t) y(t) examples from s05 x(t) after DTW y(t) after DTW Alignment path AVBPA99 - March 3rd, 999 9

Dynamical Time Warping x(t) y(t) examples from s030 x(t) after DTW y(t) after DTW Correspondence AVBPA99 - March 3rd, 999 0

Signature alignment Main inertia axis of the signature In order to obtain some degree of invariance w.r.t. rotations, align the main inertia axis of the signature with the horizontal axis before performing DTW. AVBPA99 - March 3rd, 999

Evaluation of the SV system There are two types of errors to evaluate in order to asses the performance of the system: FAR (False Acceptance Rate): percentage of false signatures classified as true. FRR (False Rejection Rate): percentage of real signatures classified as false. AVBPA99 - March 3rd, 999

Evaluation of the SV system Error rate FRR FAR FRR Equal error rate (Indicator of the perf. of the system) Classif. Thres. Error trade-off curve FAR Ideal case: FAR = FRR = 0% AVBPA99 - March 3rd, 999 3

Experiments Collected a database of signatures 56 subjects 5-30 sample signatures per subject 0 signatures were collected per session, and each session took place on a different day 0 forgeries per subject each signature acquired with the real-time pen tracking system AVBPA99 - March 3rd, 999 4

Experiments The algorithm was tested as follows: Training set: 0 signatures per subject. Test set (true): remaining 5 signatures per subject. Test set (false): all 375 signatures from all other subjects ( random forgeries ). Test set (false): 0 intentional forgeries. AVBPA99 - March 3rd, 999 5

Experiments examples references False rejects False accepts AVBPA99 - March 3rd, 999 6

Results FRR FRR FAR FAR AVBPA99 - March 3rd, 999 7

Conclusions Presented the performance of a vision-based technique for personal identification. Demonstrated the feasibility of having such a system working in real-time with high performance in verification. AVBPA99 - March 3rd, 999 8

Future Work Evaluate different representations of the signature and different similarity measures in order to improve performance and achieve scale invariance. Overcome the lack of examples in order to extract more meaningful estimates of the generalization error. AVBPA99 - March 3rd, 999 9

Future Work Match all examples in a way such that the prototype would be a more robust representative of its class. Once we have the matching function, devise other similarity measures that improve performance. Collect a new, clean and bigger database of examples. AVBPA99 - March 3rd, 999 30