7/31/2019 BK2 Chapters 1 2

1/53

1

Handbook of Fingerprint

Recognition

Chapters 1 & 2

Presentation by

Konda Jayashree

7/31/2019 BK2 Chapters 1 2

2/53

2

History of fingerprints

Human fingerprints have been discovered on a large number ofarchaeological artifacts and historical items

In 1684, the English plant morphologist, Nehemiah Grew, published the firstscientific paper reporting his systematic study on the ridge, furrow, and pore

structure

In 1788, a detailed description of the anatomical formations of fingerprintswas made by Mayer.

In 1823, Purkinji proposed the first fingerprint classification, which classified

into nine categories

Sir Francis Galton introduced the minutae features for fingerprint matchingin late 19th century

7/31/2019 BK2 Chapters 1 2

3/53

3

History of fingerprints

7/31/2019 BK2 Chapters 1 2

4/53

4

Formation of fingerprints

Fingerprints are fully formed at about seven months of fetus

development

General characteristics of the fingerprint emerge as the skin on

the fingertip begins to differentiate.

flow of amniotic fluids around the fetus and its position in the

uterus change during the differentiation process

Thus the cells on the fingertip grow in a microenvironment that is

slightly different from hand to hand and finger to finger

7/31/2019 BK2 Chapters 1 2

5/53

5

Fingerprint sensing

Based on the mode of acquisition, a fingerprint image is classified

as

Off line image

Live-scan image

7/31/2019 BK2 Chapters 1 2

6/53

6

There are a number of live-scan sensing mechanisms thatcan detect the ridges and valleys present in the fingertip

Examples are

Optical FTIR

Capacitive

Pressure-based

Ultrasound

7/31/2019 BK2 Chapters 1 2

7/53

7

7/31/2019 BK2 Chapters 1 2

8/53

8

Fingerprint Representation

Fingerprint representation should have following two

properties

Saliency

Suitability

7/31/2019 BK2 Chapters 1 2

9/53

9

Fingerprint feature extraction

Fingerprint pattern, when analyzed at different

scales, exhibits different types of features

global level - delineates a ridge line flow pattern

local level minute details can be identified

Very fine level intra-ridge details can be detected

7/31/2019 BK2 Chapters 1 2

10/53

10

7/31/2019 BK2 Chapters 1 2

11/53

11

7/31/2019 BK2 Chapters 1 2

12/53

12

Difficulty in fingerprint matching

Fingerprint matching is a difficult problem due to large variability in differentimpressions of the same finger Main factors responsible for intra-class variations are: displacement, rotation,

partial overlap, non-linear distortion, variable pressure, skin condition, noiseand feature extraction errors

7/31/2019 BK2 Chapters 1 2

13/53

13

Fingerprint Matching

A three class categorization of fingerprint

matching approaches is: Correlation based matching

Minutae based matching

Ridge feature based matching

7/31/2019 BK2 Chapters 1 2

14/53

14

Fingerprint classification and Indexing

To reduce the search time and computational complexity

technique used to assign a fingerprint to one of the several pre-specified types

Only a limited number of categories have been identified, and there

are many ambiguous fingerprints

7/31/2019 BK2 Chapters 1 2

15/53

15

Synthetic fingerprints

Performance evaluation of fingerprint recognition

systems is very data dependent

To obtain tight confidence intervals at very lowerror rates, large databases of images are

required and its expensive

To solve this problem synthetic fingerprint

images are introduced

7/31/2019 BK2 Chapters 1 2

16/53

16

Designing Fingerprint recognition systems

The major issues in designing the fingerprint

recognition system includes

Defining the system working mode

Choosing the hardware and software components Dealing with exceptions

Dealing with poor quality fingerprint images

Defining effective administration and optimization

policy

7/31/2019 BK2 Chapters 1 2

17/53

17

Designing Fingerprint recognition systems

The system designer should take into account several

factors Proven technology

System interoperability and standards

Cost/performance trade off

7/31/2019 BK2 Chapters 1 2

18/53

18

Securing fingerprint recognition systems

Maintaining the fingerprint recognition

system is critical and requires resolving

the frauds like Repudiation

Coercion

Circumvention

Contamination Denial of service attacks

7/31/2019 BK2 Chapters 1 2

19/53

19

Applications

7/31/2019 BK2 Chapters 1 2

20/53

20

Fingerprint Sensing

Acquisition of fingerprint Images was

performed by two techniques

Off-line sensing

Live-scan sensing

7/31/2019 BK2 Chapters 1 2

21/53

21

The general structure of fingerprint

scanner is shown in figure

7/31/2019 BK2 Chapters 1 2

22/53

22

The main parameters characterizing a fingerprint image are

Resolution

Area

Number of pixels

Dynamic RangeGeometric Accuracy

Image Quality

7/31/2019 BK2 Chapters 1 2

23/53

23

Off-line fingerprint Acquisition

Although the first fingerprint scanners were introduced more than 30 years

ago, still ink-technique is used in some applications

Why & What are the advantages?

Because it has the possibility of producing

Rolled impressions

Latent impressions

7/31/2019 BK2 Chapters 1 2

24/53

24

Rolled fingerprint Impressions

7/31/2019 BK2 Chapters 1 2

25/53

25

Latent fingerprint images

7/31/2019 BK2 Chapters 1 2

26/53

26

Live scan fingerprint sensing

The most important part of a fingerprint

scanner is the sensor.

All the existing scanners belong to one of

the 3 families

Optical sensors

Solid state sensorsUltrasound sensors

7/31/2019 BK2 Chapters 1 2

27/53

27

Optical sensors

FTIR (Frustrated Total Internal Reflection)

7/31/2019 BK2 Chapters 1 2

28/53

28

FTIR with sheet prism

In this, sheet prism is used instead of glass prism

Only Advantage is

Mechanical Assembly is reduced to some extent

7/31/2019 BK2 Chapters 1 2

29/53

29

Optical Fibers

In Optical Fibers, a significant reduction of thepackagiing size can be achieved by substituting prismand lens with a fiber optic platen

7/31/2019 BK2 Chapters 1 2

30/53

30

Electro Optical

7/31/2019 BK2 Chapters 1 2

31/53

31

Solid state sensors

These are designed to overcome the size and cost problems

Silicon based sensors are used in this

Neither optical components nor external CCD/CMOS image sensors are

needed

Four main effects have been produced to convert the physical information

into electrical signals

Capacitive

Thermal

Electric field

Piezo Electric

7/31/2019 BK2 Chapters 1 2

32/53

32

Capacitive

7/31/2019 BK2 Chapters 1 2

33/53

33

Thermal sensors

Works based on temperature differentials

Sensors are made of pyro electric material

Temperature differential produces an image, but

this image soon disappears because the thermal equilibrium is quickly reached

and pixel temperature is stabilized

Solution is sweeping method

Advantages Not sensitive to ESD

Can accept thick protective coating

7/31/2019 BK2 Chapters 1 2

34/53

34

Electric field

Sensor consists of drive ring

This generates a sinusoidal signal and amatrix of active antennas

To image a fingerprint, the analogueresponse of each element in the sensor

matrix is amplified, integrated and digitized

7/31/2019 BK2 Chapters 1 2

35/53

35

Piezo- Electric

Pressure sensitive sensors

Produce an electrical signal when mechanical stress isapplied to them

Sensor surface is made up of a non-conducting dielectricmaterial

Ridges and valleys are present at different distances fromthe surface , they result in different amounts of current

7/31/2019 BK2 Chapters 1 2

36/53

36

Ultrasound sensors

Principle is Echography

7/31/2019 BK2 Chapters 1 2

37/53

37

Ultrasound sensors

Advantages of Ultrasound sensors

Good Quality images

Disadvantages

Scanner is large

Mechanical parts are quite expensive

7/31/2019 BK2 Chapters 1 2

38/53

38

Touch Vs Sweep

Drawbacks of Touch method

Sensor can become dirty

Visible latent fingerprints remains on the

sensor

Rotation of the fingerprint may be a problem

Strict trade-off between the cost and the size

of the sensing area

7/31/2019 BK2 Chapters 1 2

39/53

39

Sweeping Method

7/31/2019 BK2 Chapters 1 2

40/53

40

Advantages of Sweeping Method

Equilibrium is continuously broken when

sweeping, as ridges and valleys touch the

pixels alternately, introducing a continuous

temperature change

Sensors always look clean

No latent fingerprints remain

No rotation

7/31/2019 BK2 Chapters 1 2

41/53

41

Drawbacks

Novice user may encounter difficulties

Interface must be able to capture asufficient number of fingerprint slices

Reconstruction of the image from theslices is time consuming

7/31/2019 BK2 Chapters 1 2

42/53

42

Image Reconstruction from the slices

Main stages are Slice quality computation

Slice pair registration

Relaxation Mosaicking

7/31/2019 BK2 Chapters 1 2

43/53

43

Algorithm for fingerprint recognition from the slices

7/31/2019 BK2 Chapters 1 2

44/53

44

Fingerprint scanners and their features

Interface

Frames per second

Automatic finger detection

Encryption Supported operating systems

7/31/2019 BK2 Chapters 1 2

45/53

45

7/31/2019 BK2 Chapters 1 2

46/53

46

7/31/2019 BK2 Chapters 1 2

47/53

47

7/31/2019 BK2 Chapters 1 2

48/53

48

7/31/2019 BK2 Chapters 1 2

49/53

49

Sensing area Vs Accuracy

Recognizing fingerprints acquired through small areasensors is difficult

7/31/2019 BK2 Chapters 1 2

50/53

50

An interesting alternative to deal with small

sensing areas is fingerprint Mosaicking

7/31/2019 BK2 Chapters 1 2

51/53

51

Storing and Compressing fingerprint images

Each fingerprint impression produces an image

of 768 x 768 ( when digitized at 500 dpi)

In AFIS applications, this needs more amount of

memory space to store these images Neither lossless methods or JPEG compression

techniques are satisfactory

A new compression technique called Wavelet

Scalar Quantization (WSQ) is introduced to

compress the images

7/31/2019 BK2 Chapters 1 2

52/53

52

WSQ

Based on Adaptive scalar quantization

Performs following steps

Fingerprint image is decomposed into a number of spatial frequencysub-bands using a Discrete wavelet transform

the resulting DWT coefficients are quantized into discrete values the quantized sub-bands are concatenated into several blocks and

compressed using an adaptive Huffman-run length encoding

A compressed image can be decoded into the original image by applyingsteps in reverse order

WSQ compress a fingerprint image by a factor of 10 to 25

7/31/2019 BK2 Chapters 1 2

53/53

53