fingerprint recognition using minutiae based feature

Fingerprint Recognition Using Minutiae-Based Features

1. Abstract

Nowadays, conventional identification methods such as driver's license, passport, ATM cards

and PIN codes do not meet the demands of this wide scale connectivity. Automated biometrics in

general, and automated fingerprint authentication in particular, provide efficient solutions to

these modern identification problems. Fingerprints have been used for many centuries as a means

of identifying people. The fingerprints of individual are unique and are stay unchanged during

the life time. Fingerprint matching techniques can be placed into two categories, minutiae-based

and correlation based. Minutiae-based techniques first find minutiae points and then map their

relative placement on the finger. However, there are some difficulties when using this approach.

It is difficult to extract the minutiae points accurately when the fingerprint is of low quality the

correlation-based method is able to overcome some of the difficulties of the minutiae-based

approach. However, it has some of its own shortcomings. Correlation-based techniques require

the precise location of a registration point and are affected by image translation and rotation.


2. Introduction

Biometric recognition refers to the use of distinctive physiological (e.g. fingerprint, palm print,

iris, face) and behavioral (eg. gait, signature) characteristics, called biometric identifiers for

recognizing individuals.

Fingerprint recognition is one of the oldest and most reliable biometric used for personal

identification. Fingerprint recognition has been used for over 100 years now and has come a long

way from tedious manual fingerprint matching. The ancient procedure of matching fingerprints

manually was extremely cumbersome and time-consuming and required skilled personnel.

Finger skin is made up of friction ridges and sweat pores all along these ridges. Friction ridges

are created during fetal life and only the general shape is genetically defined. The distinguishing

nature of physical characteristics of a person is due to both the inherent individual genetic

diversity within the human population as well as the random processes affecting the development

of the embryo. Friction ridges remain the same throughout one’s adult life. They can reconstruct

themselves even in case of an injury as long as the injury is not too serious.

Fingerprints are one of the most mature biometric technologies and are considered legitimate

proofs of evidence in courts of law all over the world. In recent times, more and more civilian

and commercial applications are either using or actively considering using fingerprint-based

identification because of the availability of inexpensive and compact solid state scanners as well

as its superior and proven matching performance over other biometric technologies.

Some important terms related to fingerprint identification systems are explained below:

Fingerprint Acquisition: How to acquire fingerprint images and how tore present them in

a proper machine-readable format.

Fingerprint Verification: To determine whether two fingerprints are from the same finger.

Fingerprint Identification: To search for a query fingerprint in a database.

Fingerprint Classification: To assign a given fingerprint to one of the prespecified

categories according to its geometric characteristics.


In case of both fingerprint identification and fingerprint verification systems, our tasks will be

broken up into 2 stages:

1. Off-line phase: Several fingerprint images of the fingerprint of a person to be verified are

first captured and processed by a feature extraction module; the extracted features are

stored as templates in a database for later use.

2. On-line phase: The individual to be verified gives his/her identity (in case of a

verification system) and places his/her finger on the inkless fingerprint scanner, minutia

points are extracted from the captured fingerprint image. These minutiae are then fed to a

matching module, which matches them against his/her own templates in the database (in

case of a verification system) or against all the users in the database (in case of an

identification system).

2.1 What is a fingerprint?

Fingerprints are the most important part in biometric for human identification. They are unique

and permanent from birth to death. So, fingerprints have been used for the forensic application

and personal identification.

A fingerprint is collection of many ridges and furrows (Valleys). The continuous dark pattern

flow in fingerprint is called ridges and the light area between ridges is called furrows. Fingerprint

has some unique points on the ridge which is known as minutiae point. Here we can consider two

main types of minutiae points which are termination point and bifurcation point as shown in

Fig.1.Termination: where a ridge ends and Bifurcation: where ridges split into two parts.

Figure 1 Minutiae Points (Termination, Bifurcation)


2.2 Fingerprint Recognition

The fingerprint recognition problem can be grouped into two sub-domains: one is fingerprint

verification and the other is fingerprint identification. In addition, different from the manual

approach for fingerprint recognition by experts, the fingerprint recognition here is referred as

AFRS (Automatic Fingerprint Recognition System. Fingerprint verification is to verify the

authenticity of one person by his fingerprint. The user provides his fingerprint together with his

identity information like his ID number. The fingerprint verification system retrieves the

fingerprint template according to the ID number and matches the template with the real-time

acquired fingerprint from the user. Usually it is the underlying design principle of AFAS

(Automatic Fingerprint Authentication System).

Figure 2. General architecture of a fingerprint verification system

Fingerprint identification is to specify one person's identity by his fingerprint(s). Without

knowledge of the person's identity, the fingerprint identification system tries to match his

fingerprint(s) with those in the whole fingerprint database. It is especially useful for criminal

investigation cases. And it is the design principle of AFIS (Automatic Fingerprint Identification

System).However, all fingerprint recognition problems, either verification or identification, are

ultimately based on a well-defined representation of a fingerprint. As long as the representation

of fingerprints remains the uniqueness and keeps simple, the fingerprint matching, either for the

1-to-I verification case or 1-to-m identification case, is straightforward and easy.


2.3 Techniques for Fingerprint Recognition

1) Minutiae Extraction based Techniques: Mostly accepted finger scan technology is based on

Minutiae. Minutiae based techniques produce the fingerprint by its local features, like

termination and bifurcation. When minutiae points match between two fingerprints so fingerprint

are match. This approach has been genuinely studied, and it is the backbone of the current

available fingerprint recognition products.

2) Pattern Matching or Ridge Feature based Techniques: Feature extraction are established on

series of ridges as averse to different points which design the basis of pattern matching

techniques over Minutiae Extraction. Minutiae points can be change by wear and tear and the

main drawback are that these are acute to proper adjustment of finger and need large storage .

3) Correlation based Techniques: Correlation based technique is used to match two fingerprints,

the fingerprint are adjusted and computed the correlation for each corresponding pixel. They can

match ridge shapes, breaks, etc. Main disadvantages of this method are its computational

complication and less tolerance to non-linear distortion and contrast variation.

4) Image based Techniques: This technique attempt to do matching which based on the global

features of an all fingerprint images. It is an advance and newly develops method for fingerprint

recognition


3. Literature Survey


4. Fingerprint matching

The matching of fingerprint is achieved by some image processing steps. These step can easily

be understand by the algorithm below:

Input: Two Gray-scale Fingerprint image.

Output: Verify the fingerprint image using minutiae matching.

Step 1: Enhancement of Input Image i.e. fingerprint image using Histogram equalization.

Step 2: Binarized the enhanced fingerprint image.

Step 3: Selection of ROI (Region of Interest) in binarized image.

Step 4: Thinning of the Region of Interest as the part of fingerprint image.

Step 5: Minutiae points are extracted from image.

Step 6: Comparison and matching of one fingerprint to another fingerprint.

Step 7: Match the minutiae points of two images are computed. If Minutiae points are matched

in both images so fingerprint matching score are 1 and if it is not matched then

matching score are 0 they are mismatched.

Figure 3. Fingerprint Matching block diagram

The overall implementation of algorithm may also express by using block diagram, as shown

above. This block diagram is sub divided as pre-processing stage, minutiae extraction stage and

post-processing stage


5. Pre-processing stage

5.1 Image Acquisition

The first stage of any vision system whether for identification or verification is the image

acquisition stage. Nowadays, the automated fingerprint verification systems use live-scan digital

images of fingerprints acquired from a fingerprint sensor. These sensors are based on optical,

capacitance, ultrasonic, thermal and other imaging technologies.

1. Optical Sensors: These are the oldest and most widely used technology. In most devices, a

charged coupled device (CCD) converts the image of the fingerprint, with dark ridges and

light valleys, into a digital signal. They are fairly inexpensive and can provide resolutions up

to 500 dpi. Most sensors are based on FTIR (Frustrated Total Internal Reflection) technique

to acquire the image. In this scheme, a source illuminates the fingerprint through one side

Figure 4 :(a) General schematic for an FTIR based optical sensor (b) Schematic of a capacitive

sensor

of the prism as shown (Figure 4).Due to internal reflection phenomenon, most of the light is

reflected back to the other side where it is recorded by a CCD camera. However, in regions

where the fingerprint surface comes in contact with the prism, the light is diffused in all

directions and therefore does not reach the sensor resulting in dark regions. The quality of the

image depends on whether the fingerprint is dry or wet. Another problem faced by optical

sensors is the residual patterns left by the previous fingers. Furthermore it has been shown that

fake fingers are able to fool most commercial sensors. Optical sensors are also among the

bulkiest sensor due to the optics involved.


2. Capacitive Sensors: The silicon sensor acts as one plate of a capacitor, and the finger as

another other. The capacitance between the sensing plate and the finger depends inversely as the

distance between them. Since the ridges are closer, they correspond to increased

capacitance and the valleys correspond to smaller capacitance. This variation is converted into an

8-bit gray scale digital image. Most of the electronic devices featuring fingerprint authentication

use this form of solid state sensors due to its compactness. However, sensors that are smaller than

0.5”x0.5” are not useful since it reduces the accuracy recognition.

3. Ultra-sound Sensors: Ultrasound technology is perhaps the most accurate of the fingerprint

sensing technologies. It uses ultrasound waves and measures the distance based on the impedance

of the finger, the plate, and air. These sensors are capable of very high resolution. Sensors with

1000dpi or more are already available (www.ultra-scan.com). However, these sensors tend to be

very bulky and contain moving parts making them suitable only for law enforcement and access

control applications.

4. Thermal Sensors: These sensors are made up of pyro-electric materials whose properties

change with temperature. These are usually manufactured in the form of strips .As the

fingerprints is swiped across the sensor, there is differential conduction of heat between the

ridges and valleys(since skin conducts heat better than the air in the valleys) that is measured by

the sensor. Full size thermal sensors are not practical since skin reaches thermal equilibrium very

quickly once placed on the sensor leading to loss of signal. This would require us to constantly

keep the sensor at a higher or lower temperature making it very energy inefficient. The sweeping

action prevents the finger from reaching thermal equilibrium leading to good contrast images.

However, since the sensor can acquire only small strips at a time, a sophisticated image

registration and reconstruction scheme is required to construct the whole image from the strips.

One of the most essential characteristics of a digital fingerprint image is its resolution which

indicates the number of dots or pixels per inch (ppi). The minimum resolution that allows the

feature extraction algorithms to locate minutiae is 250 to 300 ppi.


5.2 Image Enhancement

Fingerprint image enhancement is to make the image clearer for easy further operations.

The performance of minutiae extraction algorithms and other fingerprint recognition techniques

relies heavily on the quality of the input fingerprint images. A fingerprint image is firstly

enhanced before the features contained in it could be detected or extracted. A well enhanced

image will provide a clear separation between the valid and spurious features. Since the

fingerprint images acquired from sensors or other media are not assured with perfect quality.

However the fingerprint images obtained are usually poor due to elements that corrode the clarity

of the ridge elements. This leads to problems in minutiae extraction. Spurious features are those

minutiae points that are created due to noise or artifacts and they are not actually part of the

fingerprint.

In an ideal fingerprint image, ridges and valleys alternate and flow in a locally constant

direction. Thus, image enhancement techniques are employed to reduce the noise and enhance

the definition of ridges against valleys. In order to ensure good performance of the ridge and

minutiae extraction algorithms in poor quality fingerprint images, an enhancement algorithm to

improve the clarity of the ridge structure is necessary. Enhancement methods, for increasing the

contrast between ridges and furrows and for connecting the false broken points of ridges due to

insufficient amount of ink are very useful to keep a higher accuracy to fingerprint recognition.

Histogram Equalization

It is a method for enhance the fingerprint image. Fingerprint image enhancement is to create

clearer for easy other operations. Histogram equalization is to extend the pixel value of an image

so as to increase the perceptional information. The histogram of a original fingerprint image has

the bimodal type the histogram after the histogram equalization occupies all the range from 0 to

255 and the visualization effect is enhanced.

In MATLAB histogram equalization is done by using MATLAB function.

histeq (image_file_name);


Below, the figure shows the original image histogram and histogram after equalization

operation.


5.3 Binarization

A Fingerprint-Image-Binarization transforms an 8-bit gray image to a 1-bit binarized image.

Most minutiae extraction algorithms operate on binary images where there are only two levels of

interest: 0-value holds for ridges and 1-value for furrows. And after the binarization operation

ridges are highlighted with black color and furrows are highlighted with white color.

An adaptive binarization method is achieved to binarize the fingerprint image. In this method

image is split into blocks of 16 x 16 pixels. A pixel value is set 1 if its value is greater than the

mean intensity value of the accepted block to which the pixel belongs.


5.4 Image segmentation

This is a segmentation technique. The main motive of the segmentation is to make the image

simpler which can be representing very easily and to make image meaningful that will be easy to

analyze. Generally ROI (Region of Interest) is very useful for analyze a fingerprint image. It is a

subset of an image or a dataset analyze for a particular purpose. When the image area has

ineffective ridges and furrows so firstly it made wider and larger in all directions.

There are two regions that describe any fingerprint image; namely the foreground region and the

background region. The foreground regions are the regions containing the ridges and valleys. The

ridges are the raised and dark regions of a fingerprint image while the valleys are the low and

white regions between the ridges. The foreground regions often referred to as the Region of

Interest (ROI). The background regions are mostly the outside regions where the noises

introduced into the image during enrolment are mostly found

Region of Interest (ROI)

To extraction of the ROI is performed in two steps: First, block direction estimation and direction

variety check; second, used some Morphological methods.

Two types of morphological methods are available i.e. OPEN and CLOSE. The OPEN operation

can enlarge the images and eliminate background noise. And CLOSE operation can shrink

images and eliminate small cavities.

bwmorph (x, 'close'); bwmorph (y, 'open');


6. Minutiae extraction stage

After the enhancement of the fingerprint image, the image is ready for minutiae extraction. For

proper extraction, however, a thinning algorithm is applied to the enhanced image. It produces a

skeletonized representation of the image.

6.1 Thinning

Thinning is a morphological operation that is used to remove selected foreground pixels from

binary images. It is used to eliminate the redundant pixels of ridges till the ridges are just one

pixel wide. Thinning is normally only applied to binary images, and produces another binary

image as output. It is the final step prior to minutiae extraction. All the pixels on the boundaries

of foreground regions that have at least one background neighbor are taken. Any point that has

more than one foreground neighbor is deleted as long as doing so does not locally disconnect the

region containing that pixel.

This is done by using the MATLAB thinning function that is:-

bwmorph(binaryImage,'thin',Inf)

Then the thinned image is filtered by using the following three MATLAB functions. This are

some H is breaks, isolated points and spikes.

bwmorph(binaryImage, 'hbreak',k)

bwmorph(binaryImage, 'clean',k)

bwmorph(binaryImage, 'spur',k)


The conditions for better thinning result:

a) Each ridge should be thinned to its center pixel.

b) Noise and singular pixels should be removed.

c) No further removal of pixels should be possible after accomplish of thinning process


6.2 Minutiae Marking

The method extracts the minutiae from the enhanced image. This method extracts the ridge

endings and bifurcations from the skeleton image by examining the local neighbourhood of each

ridge pixel using a 3×3 window. The method used for minutiae extraction is the crossing

number (CN) method. This method involves the use of the skeleton image where the ridge flow

pattern is eight-connected. The minutiae are extracted by scanning the local neighbourhood of

each ridge pixel in the image using a 3×3 window. CN is defined as half the sum of the

differences between the pairs of adjacent pixel.

CN=0.5 i=1Σ8 (Pi- Pi+1)

The ridge pixel can be divided into bifurcation, ridge ending and non-minutiae point based on it.

A ridge ending point has only one neighbor, a bifurcation point possesses more than two

neighbors, and a normal ridge pixel has two neighbors. A CN value of zero refers to an isolated

point, value of one to a ridge ending, two to a continuing ridge point, three to a bifurcation point

and a CN of four means a crossing point. Minutiae detection in a fingerprint skeleton is

implemented by scanning thinned fingerprint and counting the crossing number. Thus the

minutiae points can be extracted.

Cn{p} =1 Ridge Ending Cn{p} =3 Ridge Bifurcation


In the proposed method, the minutiae point’s locations and their considered direction from the 8

directions (N, S, W, E, NE, NW, SE, SW) are recorded then they used to construct the database

depending of the number of recorded minutiae point and their direction.

Suppose P is the checked point and P1-P8 are neighbourhood pixels

If CN = 3 then

If P1 and P3 and P7 = 1 then direction = W

Else if P1 and P3 and P5 = 1 then direction = S

Else if P1 and P7 and P5 = then direction = N

Else if P3 and P5 and P7 = 1 then direction = E

Else if P4 and P3 and P5 = 1 then direction = SE

Else if P3 and P2 and P1 = 1 then direction = SW

Else if P3 and P5 and P6 = 1 then direction = NE

Else if P4 and P8 and P5 = 1 then direction = NW

End if

If CN = 1 then

If P1 = 1 then direction = W

If P1 = 1 then direction = W

If P3 = 1 then direction = S

If P7 = 1 then direction = N

If P5 = 1 then direction = E

If P4 = 1 then direction = SE

If P2 = 1 then direction = SW

If P6 = 1 then direction = NE

If P8 = 1 then direction = NW


7. Post-processing stage

7.1 Minutiae Matching

When all minutiae points of two fingerprint images are extracted in selected region of interest.

Now, minutiae matching are performed for verification. Basically, minutiae

Matching is a process which completed in two steps:

1) Find Total Minutia Points: This step is used to calculate the total number of Ridge and

Bifurcation points separately. And it compares the calculated value with the original image

values.

2) Find Location of Minutiae Points: It works on the basis of Minutia Marking process. Simply,

when minutia points marked on the image it also store the location of the point. This stored

information it used to compare two different images at verification process. If both the

images belong to the same person then the location of ridge/bifurcation will match.

Otherwise matching of fingerprint images unsuccessful.

7.2 Remove False Minutiae

In fingerprint recognition, the goal is too able to detect the minutiae point and to reduce the false

minutiae in the fingerprint image. In order to remove false minutia, there are a few process that

need to be going through which are minutia marking and false minutia removal.

The procedures in removing false minutia are:

1. If the distance between one bifurcation and one termination is less than D and the

two minutiae are in the same ridge (ml case). Remove both of them. Where D is the

average inter-ridge width representing the average distance between two parallel

neighboring ridges.

2. If the distance between two bifurcations is less than D and they are in the same

ridge, remove the two bifurcations.

3. If two terminations are within a distance D and their directions are coincident with

a small angle variation. And they suffice the condition that no any other

termination is located between the two terminations. Then the two terminations are


8. Merits & Demerits

Advantages

Physical attributes are much tougher to be faked than ID cards.

Fingerprints can’t be guessed unlike passwords.

Fingerprints can’t be misplaced unlike a card.

Fingerprints can’t be forgotten unlike passwords.

Sudden enhancement in the current security level.

Less security concerns leads to increased productivity.

Disadvantages

It can be deceived by a picture or a mold of finger using Gelatin.

Fingerprints if stolen, can be a great threat to Security and intellectual property.

Requires a very large data base of fingerprints.

Some of the employees may find it uncomfortable to Have their fingerprint stored with

the employer.


9. Applications & future scope

Applications

1. Financial services (e.g. ATM )

2. Immigration & border control (e.g. points of entry declared for frequent travelers,

passport and visa cases )

3. Social services (e.g. fraud preventation in entitlement programmers)

4. Health care (e.g. security measure for privacy or medical records)

5. Physical access control (e.g. at institutional, government & residential establishment)

6. Time & attendance (e.g. replacement of time punch card)

7. Computer Security (e.g. personal computer access, network access, Internet use, e-

commerce, e-mail, encryption)

8. Telecommunications (e.g. mobile phones, call center technology, phone cards, televised

shopping)

9. Law enforcement (e.g. criminal investigation, national ID, driving license, rehabilitation

institutions/prison, home confinement, small gun)

Further works which can be carried out include following.

1. To perform statistical experiment used in this project on a larger sample size & a conduct

a full analysis of observed result.

2. An implementation of a smarter matching algorithm should be able to improve the

verification & identification process.

3. Issue need to be addressed in the systematic way in developing a fool proof fingerprint

based identification system for a wide scale development e.g. encryption security of

fingerprint template detection of force fingers, privacy concern etc.

4. Implementation of on-line fingerprint verification & Identification system using biometric

device.


10. Conclusion

This seminar has concentrated on fingerprint based biometric identification & verification

systems. The primary focus is subsequent extraction of minutiae by direct gray scale image

extraction technique .There are two important operations in pre-processing stage as Histogram

Equalization, and Selection of ROI. These two operations make this algorithm efficient. The

Histogram Equalization enhanced the quality of Input-image, which actually help to produce

accurate calculation. This research concludes that the Fingerprint Verification is possible even

the quality of the fingerprint image got affected. The ROI based approach reduces the processing

time of algorithm by working on segment not the complete image, which means it makes

fingerprint matching faster. The verification is done for selected region that authenticate the

pattern. The literature of this technique is deeply studied and experimentally executed in

MATLAB.


11. References

1. Raymond Thai, ‘Fingerprint Image Enhancement and Minutiae-Extraction,”

Thesis submitted to School of Computer Science and Software Engineering, University of

Western Australia 2. AK Jain, A. Ross, and S. Prabhakar, Fingerprint Matching Using Minutiae

and Texture Features , Proc. of International Conference on Image Processing, 2001

3. Digital Image Processing by Rafael C. Gonzalez and Richard E. Woods,Pearson Education,

2003

4. Digital Image Processing using MATLAB: Rafael C. Gonzalez, Richard E. Woods 2nd

Edition, 2009 5. Fingerprint Image Enhancement and Minutiae Extraction by Raymond Thai 2002

6. Online Fingerprint Verification by Sharat Chikkerur CUBS, University of Buffalo

fingerprint recognition using minutiae based feature

Education

fingerprint recognition

fingerprint acquisition

fingerprint images

fingerprint verification

minutiaebased techniques

minutiaebased approach

minutiaebased features

correlationbased techniques