Multiple Biometrics for Personal Verification/Identification

Chaur-Chin ChenDepartment of Computer Science

Institute of Information Systems & ApplicationsNational Tsing Hua University

Hsinchu 30013, TaiwanE-mail: cchen@cs.nthu.edu.tw

Outline

• What is Biometrics?• Motivation by Evidence Iris Image Pattern Analysis Handwriting/Handprinting Verification Personal Signature Verification Hand Geometry Verification Voice (Speech) Pattern Recognition Face Image Recognition Fingerprint Image Verification/Identification Palmprint, Ear shape, Gesture, …• Fingerprint Classification and Verification• Face Image Recognition• Opportunities and Challenges

What and Why is Biometrics?

• What is Biometrics?

Biometrics is the science and technology of interactively measuring and statistically analyzing biological data, in particular, taken from live people.

• Why Biometrics?

(1) The banking industry reports that false acceptance rate (FAR) at ATMs are as high as 30%, which results in financial fraud of US$2.98 billion a year.

(2) In U.S., nearly half of all escapees from prisons leave through the front door, posing as someone else.

(3) Roughly 4000 immigration inspectors at US ports-of-entry intercepted and denied admission to almost 800,000 people. There is no estimate of those who may have gotton through illegally.

(4) Personal verification/identification becomes a more serious job after the WTC attack on September 11, in the year 2001.

The evidence indicates that neither a PIN number nor a password is reliable.

Some Biometric Images

美國啟用出入境指紋及影像辨識系統• 美國國土安全部基於安全考慮，自 (2004)元月五日起，啟用數位化出入境身分辨識系統 (US-VISIT)，大部分來美的 14歲至 7

9歲旅客，包括來自台灣、大陸、香港的留學生，於進入美國國際機場及港口時，都要接受拍照及留下指紋掃描紀錄以便辨識查核。 (27個免簽證國公民之入境待遇略有不同，短期來美者，將受豁免。 )，亦將需接受指紋掃描查核。  

US-VISIT

• US-VISIT currently applies to all visitors (with limited exemptions) holding non-immigrant visas, regardless of country of origin.

• 2004 – US$ 330 million• 2005 – US$ 340 million • 2006 – US$ 340 million• 2007 – US$ 362 million

入境按指紋 日本11月將實施• 日本入境排隊長 指紋掃瞄會更長！  (2007年 9月 27日 )

• 入境日本將按指紋 日官員赴台宣導新措施  (2007年 9月 27日 )

• 日11月20日實施外國人入境須按指紋臉部照片 (2007年 9月 25日 )

• 入境按指紋 日本11月將實施  (2007年 9月 2日 )

Implementation of An Automatic Fingerprint Identification System

Peihao Huang, Chia-Yung Chang, Chaur-Chin ChenDepartment of Computer Science

National Tsing Hua UniversityHsinchu 30013, Taiwan

E-mail: cchen@cs.nthu.edu.tw Presented on May 19, 2007 in IEEE Int’l Conference on EIT

A Typical Fingerprint Image

Outline

• A Flowchart of Fingerprint Identification ♪ Type Classification ♪ Minutia Points Detection ♪ Minutiae Pattern Extraction ♪ Pattern Matching♦ Databases: Rindex28, Lindex101♦ Experimental Results

Flowchart of An AFIS

Image Enhancement

• Support that A(i, j) is image gray level at pixel (i, j), μ and s2 are the mean and variance of gray levels of input image, and α=150, γ=95, γ must satisfy γ>s.

The enhanced image B( i , j ) is obtained by a contrast stretching given below

• B( i , j ) α + γ ＊  ([A ( i , j ) – μ]／ s)

Result of Image Enhancement

Orientation Computation (1/4) • First we apply a 5 by 5 median filter on the image to

avoid false gradient vectors generated by noise.• Then compute the gradient (Gx,Gy) at each pixel by a

Sobel operator.

mask Sobel Operation

)2()2()2()2(

741963

321987

zzzzzzGzzzzzzG

y

x

z1 z2 z3

z4 z5 z6

z7 z8 z9

Orientation Computation (2/4)

sincos

y

x

GG

xy

yx

GG

GG1

22

tan

0 Gx X

Y

Gy

ρ

θ

The relationship between [Gx, Gy]T and [ρ,θ]T 

Orientation Computation (3/4)• Because of opposite gradient vectors might offset each o

ther, we double the angles of the gradient vectors before averaging each block, and let the length of the gradient vectors be squared [5][6][10][11]

• Let be represented by

• The average gradient in each block R (w×w) is

Tyx ,

yx

yx

y

x

GG

GG

2cossin2

sincos

2sin

2cos 22

2

222

2

2

Tyx ~,~

yx

yxR

y

xR

y

x

GG

GG

2w1

w1

~~ 22

22

Orientation Computation (4/4)• The block gradient direction ψ is defined as

where (a block direction) is defined as

for

yx ~,~21

),( yx

xy

xy

xy

yx

/tan

/tan

/tan

,1

1

1

0 00 0

0

yxyx

x

Results of Block Orientations

Block orientated images

Singular Points Detection (1/2)

• Because of noisy directions, we have to smooth the direction before computing the Poincaré index.

• We regard the direction as a vector, double the angles and use a 3 by 3 averaging filter to smooth the direction.

• The average direction of the block is

ciiBBB

BBb

BBa

yixii

i ycyi

i xcxi

or 70 ,,

2

2

,,

7

0 ,,

7

0 ,,B3 B2 B1

B4 Bc B0

B5 B6 B7

1 1 1

1 2 1

1 1 1

abarctan

21

Singular Points Detection (2/2)• We compute Poincaré index by summing up the differen

ce in the direction surrounding the block P. For each block Pj, we compute the angle difference from 8 neighboring blocks along the counter-clockwise directions.

P1 P8 P7

P2 P P6

P3 P4 P5

P1 → P2 → P3 → P4 → P5 → P6 → P7 → P8 → P1

Core if the sum of difference is 180°Delta if the sum of difference is -180°

Example of An Ideal Core

/

\

| • |

| | |

Detected Singular Points (Blocks)

Singular points of Fingerprint Images

Criteria for Type Classification

Type Arch(tented arch)

Left loop

Right loop

Whorl(twins loop)

Others

# of cores

0 or 1 1 1 2 0 or >2

# of deltas

0 or 1(middle)

1(right) 1(left) 0~2 0 or >2

4+1 Fingerprint Type Classification

Arch Left Loop Right Loop Whorl miscellaneous

Fingerprint Database (1)

• Rindex28 Rindex28, is obtained from PRIP Lab at NTHU. It contains

112 images of size 300 by 300 contributed by 28 different individuals. Each contributed 4 times with the same right index finger scanned by a Veridicom FPS110 live scanner with the resolution 500 dpi

Fingerprint Database (2)

• Lindex101 Lindex101, is obtained from PRIP Lab at NTHU. It contains

404 images of size 300 by 300 contributed by 101 different individuals. Each contributed 4 times with the same left index finger scanned by a Veridicom FPS110 live scanner with the resolution 500 dpi

Results of Classification

• Experiment on Rindex28: 4x28 right index fingerprint images collected from 28 students– No classification error

• Experiment on Lindex101: 4x101 left index fingerprint images are collected from 101 students– 17 classification errors

Due to inappropriately pressing, too complex structure?, or poor quality.

Inappropriately Pressing

Right Loop Arch ?

Inappropriately Pressing

Whorl ? Left Loop ?

Too Complex Structure ?

Left Loop or Whorl ? Left Loop or Arch ?

Fingerprint Images of Poor Quality

? X ? X

Outline

• A Flowchart of Fingerprint Identification ♪ Type Classification ♪ Minutia Points Detection ♪ Minutiae Pattern Extraction ♪ Pattern Matching♦ Databases: Rindex28, Lindex101♦ Experimental Results

Flowchart of An AFIS

Image Binarization (1/2)• We have to distinguish valley from ridge of a fingerprint i

mage before smoothing and thinning. So the gray value of pixels in the enhanced fingerprint image will be binarized to 0 or 255.

• First we compute the gray value of P25 and P50 from the enhanced image, where Pk is the kth percentile of enhanced fingerprint image histogram.

• Then we partition an enhanced fingerprint image into w by w blocks and compute the mean of each blocks. We define that Mj is the mean of the j-th block.

Image Binarization (2/2)• If the gray value of pixel Si is less than P25, we assign 0 t

o Si . If the gray value of pixel Si greater than P50, we assign 255 to Si . Otherwise, the pixel value is defined by the following rule:

otherwise 0

81 if 255

8

0j

ixx

x

i

MSS

Post-Processing (Smoothing)• After binarization, we find that there is still much noise on rid

ge region. In order to make the result of thinning better, we have to smooth the fingerprint image first. A smooth stage uses neighboring pixels to remove noise.

• First a 5 by 5 filter is used. The pixel pi is assigned by: pi = { 255 if Σ5x5Nw 18≧ 0 if Σ5x5Nb 18 ≧ pi otherwise• Then a 3 by 3 filter is further proceed by: pi = { 255 if Σ3x3Nw 5≧ 0 if Σ3x3Nb 5 ≧ pi otherwise

(a) Original image (b) Enhanced image

(c) Binarization image (d) Smoothed image

Thinning [9]• The purpose of thinning stage is to gain the skeleton

structure of a fingerprint image.• It reduces a binary image consisting of ridges and valleys

into a ridge map of unit width.

(d) Smoothed image (e) Thinned image

Minutiae Definition♫ From a thinned image, we can classify each ridge pixel in

to the following categories according to its 8-connected neighbors.

♫ A ridge pixel is called :an isolated point if it does not contain any 8-connected n

eighbor.an ending if it contains exactly one 8-connected neighbor.an edgepoint if it has two 8-connected neighbors.a bifurcation if it has three 8-connected neighbors.a crossing if it has four 8-connected neighbors.

Example of Minutiae Extraction

Spurious Minutiae Deletion• Spurious minutia pixels include: (a) endings that lie on the margins of the region of interest. (b) two “close” endings with the same ridge orientation. (c) an ending and a bifurcation that are connected and close enough. (d) two bifurcations that are too close.

Spurious Minutiae Elimination

Due to broken ridges, fur effects, and ridge endings near the margins of an image, we have to remove the spurious minutiae as described below.

(1) Two endings are too close (within 8 pixels) (2) An ending and a bifurcation are too close (< 8 pixels) (3) Two bifurcations are too close (< 8 pixels) (4) Minutiae are near the margins (< 8 pixels)

Region of Interest Detection (1/2)

• To avoid obtaining false singular points or minutiae, we use mean and standard deviation in each block to determine if the block is “good” (not a marginal block) or not.

where , and is the ratio of

distance to the center of the fingerprint image. μ and σ are normalized to be in [0,1].

• If v > 0.8, the block is what we want.

210 ww)1(w v2w5.0w 0 5.0w1

Region of Interest Detection (2/2)

Enhanced image Region of interest

Example of Minutiae Extraction

Example of Minutiae Extraction

Example of Minutiae Extraction

Minutiae Pattern Matching

Minutiae Pattern Matching

Minutiae Pattern Representation

• Fingerprint Template Data

 

The information format of fingerprint template data. 

The information format of singular points, core or delta. 

The information format of a minutia.

Type #of cores

Core* # of deltas Delta* # of minutiae

Minutiae*

4 bits 2 bits 24 bits 2 bits 24 bits

7 bits 26 bits

X Coordinate Y Coordinate Direction

10 bits 10 bits 4 bits

Kind of Minutiae X Coordinate Y Coordinate Direction

2 bits 10 bits 10 bits 4 bits

Fingerprint Matching Score

The matching score of these two fingerprints is calculated by

where M is the number of potential type-matching minutiae within a disk of a certain user-specified radius, R (12 pixels). r measures the distance between a pair of potentially matched minutiae points.

j

M

j Rr

MS

1

)1(1100

Fingerprint Database (1)

• Rindex28 Rindex28, is obtained from PRIP Lab at NTHU. It contains

112 images of size 300 by 300 contributed by 28 different individuals. Each contributed 4 times with the same right index finger scanned by a Veridicom FPS110 live scanner with 500 dpi

Fingerprint Database (2)

• Lindex101 Lindex101, is obtained from PRIP Lab at NTHU. It contains

404 images of size 300 by 300 contributed by 101 different individuals. Each contributed 4 times with the same left index finger scanned by a Veridicom FPS110 live scanner with 500 dpi

FVC2000 Fingerprint Database (3)

• FVC2000Sensor Type Image Size Resolution

DB1 Low-cost Optical Sensor 300x300 500 dpi

DB2 Low-cost Capacitive Sensor

256x364 500 dpi

DB3 Optical Sensor 448x478 500 dpi

DB4 Synthetic Generator 240x320 about500 dpi

Fingerprint Images from FVC2000

Examples of fingerprint images from each database of FVC2000

Experimental Results  Rindex28 Lindex101 DB1 DB2 DB3 DB4

Recognitionrate 99.11%

111/11282.67%334/404

92.50%74/80

90.00%72/80

87.50%70/80

92.50%74/80

Enrolling timefor each fingerprint image

 0.25 sec

 0.25 sec

 0.25 sec

 0.25 sec

 0.45 sec

 0.17 sec

Matchingtime 0.359 sec 3.14 sec 0.25 sec 0.218 sec 0.234 sec 0.156 sec

The experimental results of 6 databases

Mismatched Fingerprint Images

Conclusion

€ We reveal three problems, which affect the results of an AFIS which merit further studies.

(1) Noise produces the poor binarization results(2) Broken ridges result in the false orientation, which causes the misclassification of a fingerprint type(3) The shifted fingerprint image is difficult to match the minutiae pattern well, for example, the type misclassification due to the missing cores or deltas

Are They From the Same Person?

SVD-Based Projection for Face RecognitionChou-Hao Hsu and Chaur-Chin Chen

Department of Computer ScienceInstitute of Information Systems & Applications

National Tsing Hua University, Hsinchu,Taiwan 30013E-mail: cchen@cs.nthu.edu.tw

Training Face Images

• Let Fi(j) be the ith face image of m by n fro

m the jth subject, 1 i N≦≦ j and 1 j K,≦≦ N1+N2+….+Nk=N be the training face imag

es. Define the mean image S as 1 1

1 jNKj

ij i

S FN

Singular Value Decomposition S=UDVt

• Do S=UDVt where U and V are orthogonal.• Select r,c with r m, c n such that ≦ ≦ d11+d22+…+dhh 85% of trace(D), where h≧

=min{r,c}• Let Ur =[u1,u2,...,ur], Vc =[v1,v2,…,vc]• Where U is an m by m orthogonal matrix• V is an n by n orthogonal matrix

Convert a face image into features

• For each training image Ak, we represent this Ak as xk =(Ur)tAVc , an r by c feature image

• For each test image T, we represent T by y=(Ur)tTVc , an r by c feature image

Distance between training feature images and a test feature image

• Compute d(y,xk) by Fröbenius norm• The smaller Fröbenius norm, the closer• Rank the norms in an ascending order• Determine the recognition rates from ranks

1, 2, 3, ...,8 and plot the curve

Part of 5*40 Training Face Images

Missed Face Images and Their Wrongly-Best Matched Images

A Comparison of Difference Projection Methods

Challenges and Opportunities

• A perfect biometric recognition system did not exist and will never exists

• An application based on biometrics usually requests a perfect verification/identification

• A collection of biometric data is usually time consuming and more or less intrudes personal privacy

• The mechanism of achieving the trade-off between privacy and security merits studies.

CC1017