[PPT] - Robotic Arm Motion for Verifying Signatures Moises Diaz 1 Miguel A. PowerPoint Presentation

SLIDE 1

Introduction VSA Robotic features Results Conclusions

Robotic Arm Motion for Verifying Signatures

Moises Diaz1 Miguel A. Ferrer2 Jose J. Quintana2

1Universidad del Atlantico Medio, Spain 2Instituto para el Desarrollo Tecnológico y la Innovación en Comunicaciones

Universidad de Las Palmas de Gran Canaria, Spain

16th ICFHR, Niagara Fall, August 8th, 2018

Diaz, Ferrer, Quintana (UNIDAM, ULPGC) 1 / 25

SLIDE 2

Introduction VSA Robotic features Results Conclusions

Outline

1

Introduction

2

Virtual Skeletal Arm model

3

Robotic/Anthropomorphic Feature Extraction

4

Results

5

Conclusions

Diaz, Ferrer, Quintana (UNIDAM, ULPGC) 2 / 25

SLIDE 3

Introduction VSA Robotic features Results Conclusions

Automatic Signature Verification

Diaz, Ferrer, Quintana (UNIDAM, ULPGC) 3 / 25

SLIDE 4

Introduction VSA Robotic features Results Conclusions

On-line: Local features The signature is analyzed locally The signature is represented through timing sequences or functions in diverse domains Basic functions: obtained directly from the digital tablet

Position: xn, yn Pressure: pn Pen-tip angles from the writing area: φn, ψn

Extended functions

Tan angle: θn = tan−1( ˙ yn/ ˙ xn) velocity (module): vn = ˙ x2

n + ˙

y2

n

log-radius curvature: ρn = log(1/kn) = log(vn/ ˙ θn) acceleration (module): an =

t2

n + c2 n =

˙ vn + v2

n θ2 n

Time derivatives of the above functions ...

Diaz, Ferrer, Quintana (UNIDAM, ULPGC) 4 / 25

SLIDE 5

Introduction VSA Robotic features Results Conclusions

Our proposal A novel feature space for on-line signature verification

Diaz, Ferrer, Quintana (UNIDAM, ULPGC) 5 / 25

SLIDE 6

Introduction VSA Robotic features Results Conclusions

Main characteristics Based on the arm posture when signing: joint angles and positions Physical meaning, simple, fast and verifiable solution Designing of a Virtual Skeletal Arm (VSA) model Mathematical fundamentals from forward and direct kinematic in robotics

Diaz, Ferrer, Quintana (UNIDAM, ULPGC) 6 / 25

SLIDE 7

Introduction VSA Robotic features Results Conclusions

Outline

1

Introduction

2

Virtual Skeletal Arm model

3

Robotic/Anthropomorphic Feature Extraction

4

Results

5

Conclusions

Diaz, Ferrer, Quintana (UNIDAM, ULPGC) 7 / 25

SLIDE 8

Introduction VSA Robotic features Results Conclusions

Virtual Skeletal Arm (VSA) model Similarities with the theoretical model

Diaz, Ferrer, Quintana (UNIDAM, ULPGC) 8 / 25

SLIDE 9

Introduction VSA Robotic features Results Conclusions

Virtual Skeletal Arm (VSA) model Proposal Architecture based on an anthropomorphic robot We got two sets of timing functions: joint angle movements and joint position

Diaz, Ferrer, Quintana (UNIDAM, ULPGC) 9 / 25

SLIDE 10

Introduction VSA Robotic features Results Conclusions

Outline

1

Introduction

2

Virtual Skeletal Arm model

3

Robotic/Anthropomorphic Feature Extraction

4

Results

5

Conclusions

Diaz, Ferrer, Quintana (UNIDAM, ULPGC) 10 / 25

SLIDE 11

Introduction VSA Robotic features Results Conclusions

Coordinate Frames in the VSA Relationship among them by homogeneous transformation matrices. E.g.:

0Ti 6 =

    ni

x

i

x

ai

x

pi

x

ni

y

i

y

ai

y

pi

y

ni

z

i

z

ai

z

pi

z

1    

Diaz, Ferrer, Quintana (UNIDAM, ULPGC) 11 / 25

SLIDE 12

Introduction VSA Robotic features Results Conclusions

Forward Kinematics Goal: To calculate the pose of the coordinate frames (CFs) relating to the VSA model, as a function of its joints angles Q(qi

k).

Strategy: Denavit-Hartenberg (DH) algorithm is widely used.

Table: DH parameters, DHi

k

Joint k δi

k

dk ak αk 1 qi

1

L1 − π

2

2 qi

2 − π 2

L2 3 qi

3

L3 − π

2

4 qi

4

L4

π 2

5 qi

5

− π

2

6 qi

6

L5

Diaz, Ferrer, Quintana (UNIDAM, ULPGC) 12 / 25

SLIDE 13

Introduction VSA Robotic features Results Conclusions

Forward Kinematics

k−1Ti k =

    c

δi

k

−c (αk) s
δi

k

s (αk) s
δi

k

akc
δi

k

s
δi

k

c (αk) c
δi

k

−s (αk) c
δi

k

aks
δi

k

−s (αk)

c (αk) dk 1     (1)

0Ti 6 = 0Ti 1· 1Ti 2· 2Ti 3· 3Ti 4· 4Ti 5· 5Ti 6

(2)

Diaz, Ferrer, Quintana (UNIDAM, ULPGC) 13 / 25

SLIDE 14

Introduction VSA Robotic features Results Conclusions

Inverse Kinematics Goal: To deduce the joint angle-based features, Q(qi

k), based on

the pose of the pen attached to the end of the model. Strategy: kinematic decoupling. Firstly qi

1, qi 2, qi 3, secondly,

qi

4, qi 5, qi 6

Diaz, Ferrer, Quintana (UNIDAM, ULPGC) 14 / 25

SLIDE 15

Introduction VSA Robotic features Results Conclusions

Kinematics Validation

Diaz, Ferrer, Quintana (UNIDAM, ULPGC) 15 / 25

SLIDE 16

Introduction VSA Robotic features Results Conclusions

The function will be availble soon For researching purposes, we share our anthropomorphic feature extractor Developed in Matlab language angles = pos2ang(x,y,z)

Diaz, Ferrer, Quintana (UNIDAM, ULPGC) 16 / 25

SLIDE 17

Introduction VSA Robotic features Results Conclusions

Outline

1

Introduction

2

Virtual Skeletal Arm model

3

Robotic/Anthropomorphic Feature Extraction

4

Results

5

Conclusions

Diaz, Ferrer, Quintana (UNIDAM, ULPGC) 17 / 25

SLIDE 18

Introduction VSA Robotic features Results Conclusions

Experimental protocol Database: MCYT-100: 25 genuine, 25 forgeries, 100 users Train: first T enrolled signature Test:

FAR: remaining genuine signatures: (25 − T) × 100 scores FRR: Random Forgery (RF): 1st testing genuine signature from the

ther users: 99 × 100 = 9900 scores

FRR: Skilled Forgery (SF): all available: 25 × 100 = 2500 scores

Features: Q(qi

k), ∀k ∈ 1, . . . 6

ևOUR CONTRIBUTION ASV: Dynamic Time Warping Performance: EER and DET curve

Diaz, Ferrer, Quintana (UNIDAM, ULPGC) 18 / 25

SLIDE 19

Introduction VSA Robotic features Results Conclusions

Pen-tip angles for orientating the CF {S6} Raw angles (θi

r, φi r), and the

corresponding joint angles Smoothed angles (θi

s, φi s), and the

corresponding joint angles Estimated angles (θi

e, φi e), and the

corresponding joint angles Fixed angles (θi

f, φi f), and the

corresponding joint angles

Diaz, Ferrer, Quintana (UNIDAM, ULPGC) 19 / 25

SLIDE 20

Introduction VSA Robotic features Results Conclusions

Performance results for different number of signatures to train MCYT-100, only angle-based features and a DTW verifier

Diaz, Ferrer, Quintana (UNIDAM, ULPGC) 20 / 25

SLIDE 21

Introduction VSA Robotic features Results Conclusions

Comparison with on-line ASV, using five signatures to train and the MCYT-100. Performance in ERR (%).

Diaz, Ferrer, Quintana (UNIDAM, ULPGC) 21 / 25

SLIDE 22

Introduction VSA Robotic features Results Conclusions

Outline

1

Introduction

2

Virtual Skeletal Arm model

3

Robotic/Anthropomorphic Feature Extraction

4

Results

5

Conclusions

Diaz, Ferrer, Quintana (UNIDAM, ULPGC) 22 / 25

SLIDE 23

Introduction VSA Robotic features Results Conclusions

Conclusions Framework to transform the on-line signature samples into a new feature space Mathematical basis for the designing Virtual Skeletal Arm (VSA) models Using robotic concepts to deduce the 3D movement from the pen-tip Features with physical meaning, simple, fast and with a verifiable solution Good results with angle-based features for on-line ASV

Diaz, Ferrer, Quintana (UNIDAM, ULPGC) 23 / 25

SLIDE 24

Introduction VSA Robotic features Results Conclusions

Future works Combination of position-based and angle-based robotic/anthropomorphic features Use more signature database and verifiers Modeling the anatomy of the hand: the finger movement supported by the wrist can be also relevant Adapting robotic features for off-line ASV

Diaz, Ferrer, Quintana (UNIDAM, ULPGC) 24 / 25

SLIDE 25

Introduction VSA Robotic features Results Conclusions

Robotic Arm Motion for Verifying Signatures

Moises Diaz1 Miguel A. Ferrer2 Jose J. Quintana2

1Universidad del Atlantico Medio, Spain 2Instituto para el Desarrollo Tecnológico y la Innovación en Comunicaciones

Universidad de Las Palmas de Gran Canaria, Spain

16th ICFHR, Niagara Fall, August 8th, 2018

Diaz, Ferrer, Quintana (UNIDAM, ULPGC) 25 / 25