Attendance Fingerprint Verification

7/28/2019 Attendance Fingerprint Verification

1/27

Automatic Attendance System using FingerprintVerification Technique

1. INTRODUCTION

In many institutions and organization the attendance is a very important factor

for various purposes and its one of the important criteria that is to follow for

students and organization employees. The previous approach in which manually

taking and maintains the attendance records was very inconvenient task. After

having these issues in mind we develop an automatic attendance system which

automates the whole process of taking attendance and maintaining it.

We already know about some commonly used biometric techniques are used for

objective identification and verification are like iris recognition, voice identification,

facial recognition, fingerprint identification, DNA recognition, hand geometry

recognition, signature recognition, and gait recognition. Biometrics techniques are

widely used in various areas like building security, forensic science, ATM, criminal

identification and passport control . In our proposed automatic attendance system

we uses fingerprint recognition technique for obtaining the attendance. The

fingerprint recognition is widely used for many other purposes and it is widely

popular technique . Fingerprint verification is very convenient and reliable way to

verify the persons Identity. It is believed that no two people have identical

fingerprint in this world, so the fingerprint verification and identification is most

popular way to verify the authenticity or identity of a person wherever the security

is a problematic question. The reason for popularity of fingerprint technique isuniqueness of person arises from his behavior; personal characteristics are like, for

instance uniqueness, which indicates that each and every fingerprint is unique,

different from one other. Universality, that means every person hold the individual

characteristics of fingerprint. Permanence, means that fingerprint are permanent,

are impossible to change or forgot, and can never be stolen. Collectability means


2/27

that we can measure fingerprint quantitatively .

In present scenario, the various uses of fingerprint verification are widespread

like authentication to logon machine and others but still majorly for law

enforcement applications. There are a lot of expectations that the use of fingerprint

recognition will increase which is dependent of some factor involved like small

fingerprint capturing devices, fast computing hardware, and awareness on easy to

use methods for security [3]. This paper cover the topics on fingerprint verification,

algorithm and our proposed system, the details of pre-processing of fingerprint

image including enhancement, binarization, segmentation, extracting minutiae from

image, post processing and matching, experiment and its result.

Fingerprint Recognition

The Fingerprint is the feature pattern of one finger or an impression of friction

ridges found on inner surface of finger as shown in figure 1(a). Everyone in this

world has his own fingerprint with the permanent uniqueness. A fingerprint is made

up of ridges and furrows, which shows good similarities like parallelism and average

width . However the research conducting on fingerprint verification and

identification shows that we can distinguish fingerprint with the help of minutiae,which are the some abnormal points on the ridges. There are two type of the

termination of minutiae, immediate ending of ridges or a point where ridge ends

abruptly called ending or termination and the point on the ridge from which other

branch drives or a point from where ridge splits into two or more branches is known

as bifurcation .


3/27

2. LITERATURE REVIEW

This section provides an account of published work by academic scholars and accredited

commentators on the subject of modern biometrics. The intent is to provide the reader with the

pros and cons of the knowledge and ideas established on the topic. The material selected for

research should reflect the overall goals outlined in the aims and objectives for this project.

Those overall goals are primarily intent on evaluating the current state of biometric technologies

and their potential. Therefore, with this in mind and taking into account the Ashbourne definition

of a modern biometric system, it is possible to discern the more relevant material for appraisal.

Much of this material tends to be recent, reflecting the most significant period for the

development of biometrics as a usable modern technology , ( c . 1990s to the present), with the

necessary overall historical context being provided in the main introduction. Maltoni et al , [A][1]

Bolle et al, [A][3] and Wikipedia , [B][4] are in agreement as to the list of general characteristics a

biometric must meet in order to provide high level performance, these include:

Universality , a characteristic of everyone.

Distinctiveness , any two persons should be sufficiently different.

Permanence , i.e. invariant with respect to matching, over time.

Collectabillity , biometric can be measured quantitatively.

Performance , achievable recognition accuracy, speed, robustness.

Acceptability , the extent to which people are willing to accept the system.

Circumvention , how easy it is to fool the system.

As a gauge to performance these characteristics provide the context for understanding common

biometric identifiers in relation to the key aspects mentioned above. In summary, it is hoped

that the review will reflect the overall research objective, provide insight as to the current

level/limits of knowledge and identifying controversies and areas of further research.

Moore, G, 2005 stated that the picture writing of a hand ridge patterns was discovered in Nova

Scotia. In ancient Babylon, fingerprints were used on clay tablets for business transaction and in

ancient China, thumbs prints were found on clay seals. In 14th century Persia, various official

government papers had fingerprints and one government official, a doctor, observed that no two

fingerprints were exactly alike.


4/27

Year Descriptions

1686 - Malpighi In 1686, Marcello Malpighi, a professor of anatomy at the University of

Bologna, noted in his treatise; ridges, spirals and loops in fingerprints. He made no mention of

their value as a tool for individual identification. A layer of skin was named after him; "Malpighi"

layer, which is approximately 1.8mm thick.1823 - Purkinji In 1823, John Evangelist Purkinji, a professor of anatomy at the

University of Breslau, published his thesis discussing fingerprint patterns, but he too made no

mention of the value of fingerprints for personal identification.

1856 - Hershel The English first began using fingerprints in July of 1858, when Sir

William Herschel, Chief Magistrate of the Hooghly district in Jungipoor, India, first used

fingerprints on native contracts. Sir Herschel's private conviction that all fingerprints were

unique to the individual, as well as permanent throughout that individual's life, inspired him to

expand their use.1880 - Faulds During the 1870's, Dr. Henry Faulds, the British SurgeonSuperintendent

of Tsukiji Hospital in Tokyo, Japan, took up the study of "skin-furrows" after noticing finger

marks on specimens of "prehistoric" pottery. In 1880, Dr. Faulds published an article in the

Scientific Journal, "Nature" (nature). He discussed fingerprints as a means of personal

identification, and the use of printers ink as a method for obtaining such fingerprints.

1882 - Thompson In 1882, Gilbert Thompson of the U.S. Geological Survey in New Mexico

used his own fingerprints on a document to prevent forgery. This is the first known use of

fingerprints in the United States. 1888 - Galton Sir Francis Galton, a British anthropologist anda cousin of Charles Darwin, began his observations of fingerprints as a means of identification

in the 1880's.

1891 - Vucetich Juan Vucetich, an Argentine Police Official, began the first fingerprint files

based on Galton pattern types. At first, Vucetich included the Bertillon System with the files.

1892 Vucetich & Galton Juan Vucetich made the first criminal fingerprint identification in

1892. Sir Francis Galton published his book, "Fingerprints", establishing the individuality and

permanence of fingerprints. The book included the first classification system for fingerprints.

While he soon discovered that fingerprints offered no firm clues to an individual's intelligence or genetic history, he was able to scientifically prove what Herschel and Faulds already suspected:

that fingerprints do not change over the course of an individual's lifetime, and that no two

fingerprints are exactly the same. According to his calculations, the odds of two individual

fingerprints being the same were 1 in 64 billion. Galton identified the characteristics by which


5/27

fingerprints can be identified. These same characteristics (minutia) are basically still in use

today, and are often referred to as Galton's Details.

1897 Haque & Bose On 12th June 1987, the Council of the Governor General of

India approved a committee report that fingerprints should be used for classification of criminal

records. Later that year, the Calcutta (now Kolkata) Anthropometric Bureau became the world'sfirst Fingerprint Bureau. Working in the Calcutta Anthropometric Bureau (before it became the

Fingerprint Bureau) were Azizul Haque and Hem Chandra Bose. Haque and Bose are the two

Indian fingerprint experts credited with primary development of the Henry System of fingerprint

classification (named for their supervisor, Edward Richard Henry). The Henry classification

system is still used in all English-speaking countries.

1901 Henry Introduction of fingerprints for criminal identification in England and

Wales, using Galton's observations and revised by Sir Edward Richard Henry. 1902 First

systematic use of fingerprints in the U.S. by the New York Civil Service Commission for testing.Dr. Henry P. DeForrest pioneers U.S. fingerprinting. 1903 The New York State Prison system

began the first systematic use of fingerprints in U.S. for criminals. 1904 The use of fingerprints

began in Leavenworth Federal Penitentiary in Kansas, and the St. Louis Police Department.

They were assisted by a Sergeant from Scotland Yard who had been on duty at the St. Louis

World's Fair Exposition guarding the British Display. Sometime after the St. Louis World's Fair,

the International Association of Chiefs of Police (IACP) created America's first national

fingerprint repository, called the National Bureau of Criminal Identification. 1905 U.S. Army

begins using fingerprints. U.S. Department of Justice forms the Bureau of Criminal Identificationin Washington, DC to provide a centralized reference collection of fingerprint cards. Two years

later the U.S. Navy started, and was joined the next year by the Marine Corp. During the next 25

years more and more law enforcement agencies join in the use of fingerprints as a means of

personal identification. Many of these agencies began sending copies of their fingerprint

cards to the National Bureau of Criminal Identification, which was established by the

International Association of Police Chiefs. 1907 U.S. Navy begins using fingerprints. U.S.

Department of Justice's Bureau of Criminal Identification moves to Leavenworth Federal

Penitentiary where it is staffed at least partially by inmates. 1908 U.S. Marin Corps begins usingfingerprints. 1918 Edmond Locard wrote that if 12 points (Galton's Details) were the same

between two fingerprints, it would suffice as a positive identification. Locard's 12 points seems

to have been based on an unscientific "improvement" over the eleven anthropometric

measurements (arm length, height, etc.) used to "identify" criminals before the adoption of


6/27

fingerprints. 1924 In 1924, an act of congress established the Identification Division of the FBI.

The IACP's National Bureau of Criminal Identification and the US Justice Department's

Bureau of Criminal Identification consolidated to form the nucleus of the FBI fingerprint files.

1946 By 1946, the FBI had processed 100 million fingerprint cards in manually maintained files

and by 1971, 200 million cards. With the introduction of AFIS technology, the files were split intocomputerized criminal files and manually maintained civil files. 2005 The FBIs Integrated AFIS

(IAFIS) in Clarksburg, WV has more than 49 million individual computerized fingerprint records

for known criminals. Old paper fingerprint cards for the civil files are still manually maintained in

a warehouse facility (rented shopping center space) in Fairmont, WV, though most enlisted

military service member fingerprint cards received after 1990, and all military-related fingerprint

cards received after 19 May 2000, have now been computerized and can be searched internally

by the FBI. In some future build of IAFIS, the FBI may make such civil file AFIS searches

available to other federal crime laboratories. All US states and larger cities have their own AFISdatabases, each with a subset of fingerprint records that is not stored in any other database.

Thus, law enforcement fingerprint interface standards are very important to enable sharing

records and mutual searches for identifying criminals.


7/27

3. PROJECT OVERVIEW

The main aim of this paper is to develop an accurate, fast and very efficient

automatic attendance system using fingerprint verification technique. We propose a

system in which fingerprint verification is done by using extraction of minutiae

technique and the system that automates the whole process of taking attendance,

Manually which is a laborious and troublesome work and waste a lot of time, with

its managing and maintaining the records for a period of time is also a burdensome

task. For this purpose we use fingerprint verification system using extraction of

minutiae techniques. The experimental result shows that our proposed system is

highly efficient in verification of user fingerprint.

Figure 2 shows our proposed automatic attendance system using fingerprintverification technique. A fingerprint is captured by user interface, which are likely to

be an optical, solid state or an ultrasound sensor. Generally, there are two

approaches are used for fingerprint verification system among them first one is

Minutiae based technique, in which minutiae is represented by ending or

termination and bifurcations. Other one is Image based method or matching

pattern, which take account of global feature of any fingerprint image. This method

is more useful then the first one as it solve some intractable problem of method

one, but this paper talk about the minutiae based representation of fingerprint. Thefingerprint verification can be defined as the system that confirm the authenticity of

one person by comparing his captured fingerprint templates against the stored

templates in database. One to one comparisons are conducted to identify the

person authenticity. After this if the authenticity of person is verified then system

signal true else false.


8/27

Automatic attendance system architecture representing the stages of

preprocessing, extraction of minutiae and matching of minutiae


9/27

4. FINGER PRINT RECOGNITION PROCESS

PREPROCESSING OF FINGERPRINT IMAGE

The pre-processing of a fingerprint image comprises of procedures like, first the

enhancement of image is done by histogram equalization and Fourier transform.

After this the process of binarization is done on the enhanced fingerprint image by

using locally adaptive method. This binarized fingerprint image is segmented by

using threshold or region of interest techniques.

A. Enhancement of Image

Since the fingerprint image are acquired from high quality sensors but the

perfection of image quality is questionable. So the enhancement of fingerprint

image is done to improve image quality, without even knowing the source of

degradation, with this it increase the contrast between ridges and furrows and

connect the broken points of ridges. Enhancement of image is first done by

histogram equalization, which performed on input image based on calculated

probability density function, with the help of which noise is prevented from being

amplified and visualization effects are enhanced. After this Fourier transform isapplied on image small processing blocks [8, 16] (32 by 32 pixel) according to

where u=0, 1, 2....31, v=0, 1, 2........31.

To enhance the block by its dominant frequency we multiply FFT of block by its

magnitude a set of times. The original magnitude FFT = abs(F(u, v)) = |F(u, v)|.

We can get an enhanced block, by using formula


10/27

where F-1 (F(u, v)) is calculated as:

for x = 0, 1, 2, ..., 31 and y = 0, 1, 2, ..., 31.

B. Binarization of Image

The Binarization of fingerprint image is to convert an image up to 256 gray levels

to white and black image. A locally adaptive binarization method is used in which

image binarization is done by choose mean intensity value or threshold value and

classify all pixels with or above threshold value as white and other pixels as black.

C. Segmentation of Image

Separating the fingerprint area from the background is always useful to avoid

extraction of noisy areas of fingerprint [17]. The segmentation of image is to

distinguish image object from the background. Only the region of interest is useful

for recognition, so image area without effective ridges and furrows are discarded

because it does not holds any important information and remaining effective area is

sketched out since minutiae in bound region are confusing with the initial minutiae

when image were generated. To extract region of interest we use two

methodologies, first is block direction estimation and direction variety check [9, 18]and second is extracting by morphological operations. Two morphological

operations are chosen OPEN, which remove expand image with removing of noise

and CLOSE, which shrink image with eliminating small cavities. The interest

fingerprint image area is found by subtraction of closed area from opened area.

RECOGNITION OF MINUTIAE

The recognition of minutiae is based on the extraction of minutiae in which binary

image obtained by binarization

process are submitted to fingerprint ridge thinning stage and marking of minutiae.

A. Thinning

Ridge Thinning or thinning is a process of reducing the width of the ridges in

fingerprint image to one pixel wide [10,11, 19]. Can say like this is to eliminate the


11/27

redundant pixel of ridges till the ridges point is one pixel wide and it should thinned

to its central pixel. The minutiae points, which have pixel value one is ending and

more than two is bifurcation. Thinning algorithm is classified by iterative and non-

iterative algorithms which is a faster approach [10]. The purpose of thinning is to

preserve the fingerprint minutiae shape while eliminating extra information and

performed because of morphological filtering of segmented image, removal of

unwanted branches, and smoothing up the result central path. This algorithm

follows the three simple rules are first to remove the unwanted edge points, adding

new edge points and shift edge points to the new location. The Algorithm is: The

rules [12, 20] are here according to the number of edge point neighbors which an

edge point has, and with help of this algorithm erroneous pixels are removed.

STEP 1: An edge point has zero neighbors, then remove the edge point.

STEP 2: An edge point has one neighbour, then start search for the neighbour with

maximum edge response to continue the edge, fill the gaps. (A edge can be filled

by maximum of three pixel.)

STEP 3: An edge point has two neighbours, and then there are three cases,

If point is sticking out of an otherwise straight line, then compare its edge

response to the corresponding point.

If the point is adjoining a diagonal edge then remove it. Else, the point is valid edge point.

STEP 4: An edge point has more than two neighbours, and then if point is not

having any link between multiple edges then thin the edge in logical consistent

way. The figure 3 is showing the Algorithm cases of number of

edge points neighbour.

B. Enhanced Thinning

The fingerprint ridge thinning is to eliminate the redundant pixel of ridge, till the

ridges one pixel wide, but this not always happens. There are still some locations

where skeleton has two or more pixel width, some extra or erroneous pixel. An

extra or erroneous pixel is one with more than four connected neighbour, it can

destroy the integrity of bridges and spurs, miss detect and exchange type of


12/27

minutiae points. So before extraction of minutiae we need to eliminate those extra

or erroneous pixels [4], for this purpose we use Enhanced Thinning Algorithm.

C. Marking of Minutiae

After Thinning of fingerprint image the important and next step is marking all

minutiae points. The maximum number of minutiae detected, increased the

probability of accurate results. The crossing number (CN) concept is widely use for

this purpose. Together with marking all thinned ridge and fingerprint image are

labeled with a unique ID for further process of matching and this labeling is done by

using morphological operation BWLABEL [4].

POST PROCESSING OF MINUTIAE

After the pre-processing stage on the binary and skeleton image, we extract almost

all minutiae from fingerprint skeleton using various method including Rutovitz

crossing numbers [14], due to various noises in fingerprint image it unable to heal

the image totally, like false ridge breaks, ridge cross connection and those

extraction algorithm produces a large number of spurious minutiae [11] such as

break, spur, merge, triangle, multiple break, ladder, lake, island, wrinkle, dot as

show in figure 4. So for accurate fingerprint verification post processing stage isvery necessary as it helps in differentiating spurious minutiae from genuine ones.

As we able to eliminate more unwanted or spurious minutiae chances of getting

better matching performance increase with the matching time will decreases.

For various types of false minutiae as in figure 4 shown, dot, spur, lake, island are

removed by pre processing algorithms, but bridge, triangle, ladder, wrinkle are not

which also known as H-points. If we able to remove H-points of image so we able to

eliminate most of spurious minutiae point. The process of eliminating the false

minutiae are consist of following steps first extract minutiae set, then remove short

breaks, after that removal of spurs if any, then removal of Hpoints [13] , after that

remove close minutiae and border minutiae and we get the true minutiae set. The

elimination process of false minutiae is already started by applying thinning

algorithms as shown in Figure 1 (extraction of minutiae steps), by applying the


13/27

threshold concept and various thinning algorithms we already able to remove the

short breaks and spurs. The post processing starts from the next step is removals

of H-Points, where H-Points are detected and eliminated. To recognize the H-Points

we follow some rules like, the point of intersection should lie between the two

ending or two bifurcation points, the distance between bridge midpoint and break

midpoint should be in a threshold limit and then we remove minutiae that are very

close to each other or the minutiae points which are within the certain distance

threshold from image border [14]. After preprocessing, a large percentage of extra

or spurious minutiae are deleted and we can treat rest of the minutiae points as

genuine and which can be used for fingerprint matching purpose.

MATCHING OF MINUTIAE

Matching of minutiae is that when we have two set of minutiae of fingerprint image

and using a algorithm we determines whether the give set of minutiae is from the

same finger or not. There are some matching techniques as correlation based

matching in which two fingerprint images are superimposed and finding out the

correlation between corresponding pixel, Ridge feature based matching in which

feature extracted are compared to extracted ridge pattern and the other one is

Minutia based matching technique [3] in which minutiae extracted from twofingerprint and stored as sets of point in two dimensional plane. We described this

technique here

a) The stage of Alignment : In this stage anyone minutiae is choose from each

image then calculate the similarity of the two ridges associated with the two

referenced minutiae points [9]. If the threshold value is smaller than similarity

then transform each set of minutiae to new coordinate system whose origin is at

referenced point and x-axis is coincident with the direction of referenced point.

b) The stage of Matching: After deriving the set of transformed minutiae points,

an algorithm is used for matching the pairs, assuming that minutiae have nearly

identical direction and position.


14/27

5. Tools Used

.Net Framework 3.5

C#

SQL Server 2005

.Net Framework 3.5

The main features of .Net Framework 3.5 are as below, which prompted us to

choose this platform to develop the application of this complex nature.

Interoperability

Because computer systems commonly require interaction between newer and

older applications, the .NET Framework provides means to access

functionality implemented in newer and older programs that execute outsidethe .NET environment. Access to COM components is provided in the

System.Runtime.InteropServices and System.EnterpriseServices namespaces

of the framework; access to other functionality is achieved using

the P/Invoke feature.

Common Language Runtime engine

The Common Language Runtime (CLR) serves as the execution engine of the

.NET Framework. All .NET programs execute under the supervision of the

CLR, guaranteeing certain properties and behaviors in the areas of memory

management, security, and exception handling.

Language independence

The .NET Framework introduces a Common Type System, or CTS. The

CTS specification defines all possible data types and programming constructs

supported by the CLR and how they may or may not interact with each other

conforming to the Common Language Infrastructure (CLI) specification.

Because of this feature, the .NET Framework supports the exchange of typesand object instances between libraries and applications written using any

conforming .NET language.

Base Class Library

The Base Class Library (BCL), part of the Framework Class Library (FCL), is a

library of functionality available to all languages using the .NET Framework.
http://en.wikipedia.org/wiki/Component_Object_Modelhttp://en.wikipedia.org/wiki/Component_Object_Modelhttp://en.wikipedia.org/wiki/Component_Object_Model


15/27

The BCL provides classes that encapsulate a number of common functions,

including file reading and writing, graphic

rendering, database interaction, XML document manipulation, and so on. It

consists of classes, interfaces of reusable types that integrates with

CLR(Common Language Runtime).

Simplified deployment

The .NET Framework includes design features and tools which help manage

the installation of computer software to ensure it does not interfere with

previously installed software, and it conforms to security requirements.

Security

The design addresses some of the vulnerabilities, such as buffer overflows,

which have been exploited by malicious software. Additionally, .NET providesa common security model for all applications.

Portability

While Microsoft has never implemented the full framework on any system

except Microsoft Windows, it has engineered the framework to be platform-

agnostic , [3] and cross-platform implementations are available for other

operating systems (see Silverlight and the Alternative

implementations section below). Microsoft submitted the specifications for

the Common Language Infrastructure(which includes the core class

libraries, Common Type System, and the Common Intermediate

Language), the C# language, and the C++/CLI language to both and the,

making them available as official standards. This makes it possible for third

parties to create compatible implementations of the framework and its

languages on other platforms.

C#

By design, C# is the programming language that most directly reflects the

underlying Common Language Infrastructure (CLI).Most of its intrinsic types

correspond to value-types implemented by the CLI framework. However, the

language specification does not state the code generation requirements of the
http://en.wikipedia.org/wiki/.NET_Framework#cite_note-3http://en.wikipedia.org/wiki/.NET_Framework#cite_note-3http://en.wikipedia.org/wiki/.NET_Framework#cite_note-3http://en.wikipedia.org/wiki/.NET_Framework#cite_note-3


16/27

compiler: that is, it does not state that a C# compiler must target a Common

Language Runtime, or generate Common Intermediate Language (CIL), or generate

any other specific format. Theoretically, a C# compiler could generate machine

code like traditional compilers of C++ or Fortran. Some notable features of C# that

distinguish it from C and C++ (and Java, where noted) are:

C# supports strongly typed implicit variable declarations with the keyword var ,

and implicitly typed arrays with the keyword new[] followed by a collection

initializer.

Meta programming via C# attributes is part of the language. Many of these

attributes duplicate the functionality of GCC's and VisualC++'s platform-

dependent preprocessor directives.

Like C++, and unlike Java, C# programmers must use the keyword virtual to

allow methods to be overridden by subclasses.

Extension methods in C# allow programmers to use static methods as if they

were methods from a class's method table, allowing programmers to add

methods to an object that they feel should exist on that object and its

derivatives.

The type dynamic allows for run-time method binding, allowing for JavaScript

like method calls and run-time object composition. C# has strongly typed and verbose function pointer support via the

keyword delegate .

Like the QT framework's pseudo-C++ signal and slot , C# has semantics

specifically surrounding publish-subscribe style events, though C# uses

delegates to do so.

C# offers Java like syncronized method calls, via the

attribute [ MethodImpl ( MethodImplOptions . Synchronized ) , and has support for

mutually-exclusive locks via the keyword lock .

The C# languages does not allow for global variables or functions. All methods

and members must be declared within classes. Static members of public classes

can substitute for global variables and functions.


17/27

Local variables cannot shadow variables of the enclosing block, unlike C and

C++.

A C# namespace provides the same level of code isolation as a

Java package or a C++ namespace , with very similar rules and features to

a package .

C# supports a strict Boolean data type, bool . Statements that take conditions,

such as while and if , require an expression of a type that implements

the true operator, such as the boolean type. While C++ also has a boolean

type, it can be freely converted to and from integers, and expressions such

as if ( a ) require only that a is convertible to bool, allowing a to be an int, or a

pointer. C# disallows this "integer meaning true or false" approach, on the

grounds that forcing programmers to use expressions that returnexactly bool can prevent certain types of common programming mistakes in C

or C++ such as if (a = b) (use of assignment =instead of equality ==).

In C#, memory address pointers can only be used within blocks specifically

marked as unsafe , and programs with unsafe code need appropriate

permissions to run. Most object access is done through safe object references,

which always either point to a "live" object or have the well-defined null value;

it is impossible to obtain a reference to a "dead" object (one that has been

garbage collected), or to a random block of memory. An unsafe pointer can

point to an instance of a value-type, array, string, or a block of memory

allocated on a stack. Code that is not marked as unsafe can still store and

manipulate pointers through theSystem . IntPtr type, but it cannot dereference

them.

Managed memory cannot be explicitly freed; instead, it is automatically garbage

collected. Garbage collection addresses the problem of memory leaks by freeing

the programmer of responsibility for releasing memory that is no longer needed. In addition to the try ... catch construct to handle exceptions, C# has

a try ... finally construct to guarantee execution of the code in the finally block,

whether an exception occurs or not.

Multiple inheritance is not supported, although a class can implement any

number of interfaces. This was a design decision by the language's lead


18/27

architect to avoid complication and simplify architectural requirements

throughout CLI. When implementing multiple interfaces that contain a method

with the same signature, C# allows the programmer to implement each method

depending on which interface that method is being called through, or, like Java,

allows the programmer to implement the method once and have that be the

single invocation on a call through any of the classes interfaces.

C#, unlike Java, supports operator overloading. Only the most commonly

overloaded operators in C++ may be overloaded in C#.

C# is more type safe than C++. The only implicit conversions by default are

those that are considered safe, such as widening of integers. This is enforced at

compile-time, during JIT, and, in some cases, at runtime. No implicit

conversions occur between booleans and integers, nor between enumerationmembers and integers (except for literal 0, which can be implicitly converted to

any enumerated type). Any user-defined conversion must be explicitly marked

as explicit or implicit, unlike C++ copy constructors and conversion operators,

which are both implicit by default.

C# has explicit support for covariance and contra variance, unlike Java which as

neither, and unlike C++ which has some degree of support for contra variance

simply through the semantics of return types on virtual methods.

Enumeration members are placed in their own scope.

C# provides properties as syntactic sugar for a common pattern in which a pair

of methods, accessor (getter) and mutator (setter)encapsulate operations on a

single attribute of a class. No redundant method signatures for the getter/setter

implementations need be written, and the property may be accessed using

attribute syntax rather than more verbose method calls.

Checked exceptions are not present in C# (in contrast to Java). This has been a

conscious decision based on the issues of scalability and versionability. Though primarily an imperative language, since C# 3.0 it supports functional

programming techniques through first-class function objects and lambda

expressions.

SQL Server 2005


19/27

SQL Server 2005 (formerly codenamed "Yukon") was released in October 2005. It

included native support for managing XML data, in addition to relational data. For

this purpose, it defined an xml data type that could be used either as a data type in

database columns or as literals in queries. XML columns can be associated

with XSD schemas; XML data being stored is verified against the schema. XML is

converted to an internal binary data type before being stored in the database.

Specialized indexing methods were made available for XML data. XML data is

queried using XQuery; SQL Server 2005 added some extensions to the T-

SQL language to allow embedding XQuery queries in T-SQL. In addition, it also

defines a new extension to XQuery, called XML DML, that allows query-based

modifications to XML data. SQL Server 2005 also allows a database server to be

exposed over web services using Tabular Data Stream(TDS) packets encapsulatedwithin SOAP (protocol) requests. When the data is accessed over web services,

results are returned as XML.

Common Language Runtime (CLR) integration was introduced with this version,

enabling one to write SQL code as Managed Code by the CLR. For relational data, T-

SQL has been augmented with error handling features (try/catch) and support for

recursive queries with CTEs (Common Table Expressions). SQL Server 2005 has

also been enhanced with new indexing algorithms, syntax and better error recovery

systems. Data pages are check summed for better error resiliency, and optimistic

concurrency support has been added for better performance. Permissions and

access control have been made more granular and the query processor handles

concurrent execution of queries in a more efficient way. Partitions on tables and

indexes are supported natively, so scaling out a database onto a cluster is easier.

SQL CLR was introduced with SQL Server 2005 to let it integrate with the .NET

Framework.

SQL Server 2005 introduced "MARS" (Multiple Active Results Sets), a method of allowing usage of database connections for multiple purposes.

SQL Server 2005 introduced DMVs (Dynamic Management Views), which are

specialized views and functions that return server state information that can be


20/27

used to monitor the health of a server instance, diagnose problems, and tune

performance.

Service Pack 1 (SP1) of SQL Server 2005 introduced Database Mirroring, a high

availability option that provides redundancy and failover capabilities at the database

level. Failover can be performed manually or can be configured for automatic

failover. Automatic failover requires a witness partner and an operating mode of

synchronous (also known as high-safety or full safety).


21/27

6. APPLICATIONS

The application of fingerprint identification system are :

Finance, insurance, securities: Financial safe management, important systemand department staff authorized management, fingerprint drawing money

business, credit card of fingerprint identification, the securities and exchange

the identification, insurance beneficiary identification. Information industry.

Computer application system identification upgraded like this way:

(fingerprints instead of password), internet electronic trading system

identification, smart card password exchange (fingerprints instead of

password), administrator identification for communication and network

equipment (switch, internet, etc.). Security industry: Fingerprint access

control system, fingerprint door lock, fingerprint car lock, building fingerprint

door lock, treasury and guns warehouse fingerprint access control and so

on.


22/27

7. LIMITATIONS

One of the open issues in ngerprint veri cation is the lack of robustness against

image quality degradation [80, 2]. The performance of a ngerprint recognition

system

is heavily affected by ngerprint image quality. Several factors determine the

q uality of a ngerprint image: skin conditions (e.g., dryness, wetness, dirtiness,

temporary or permanent cuts and bruises), sensor conditions (e.g., dirtiness, noise,

size),user cooperation, etc. Some of these factors cannot be avoided and some of

themvary along time. Poor quality images result in spurious and missed features,

thusdegrading the performance of the overall system. Therefore, it is very

important for a ngerprint recognition system to estimate the quality and validity of

the captured ngerprint images. We can either reject the degraded images oradjust someof the steps of the recognition system based on the estimated quality.

Several algorithms for automatic ngerprint image quality assessment have been

proposedin literature [2]. Also, the benets of incorporating automatic quality

measures in ngerprint verication have been shown in recent studies [28, 6, 32,

5].A successful approach to enhance the performance of a ngerprint verication

system is to combine the results of different recognition algorithms. A number of

simple fusion rules and complex trained fusion rules have been proposed in

literature [11, 49, 81]. Examples for combining minutia- and texture-based

approachesare to be found in [75, 61, 28]. Also, a comprehensive study of the

combination ofdifferent ngerprint recognition systems is done in [30]. However, it

has been foundthat simple fusion approaches are not always outperformed by more

complex fusionapproaches, calling for further studies of the subject.

Another recent issue in ngerprint recognition is the use of multiple sensors, either

for sensor fusion [60] or for sensor interoperability [74, 7]. Fusion of sensors offers

some important potentialities [60]: a) the overall performance can be improvedsubstantially, b) population coverage can be improved by reducing enrollment and

verication failures, and c) it may naturally resist spoong attempts against

biometric systems. Regarding sensor interoperability, most biometric systems are

designed under the assumption that the data to be compared is obtained uniquely

and the same for every sensor, thus being restricted in their ability to match or


23/27

compare biometric data originating from different sensors in practice. As a result,

changing thesensor may affect the performance of the system. Recent progress has

been madein the development of common data exchange formats to facilitate the

exchange of feature sets between vendors [19]. However, little effort has been

invested in the development of algorithms to alleviate the problem of sensor

interoperability. Someapproaches to handle this problem are given in [74], one

example of which is thenormalization of raw data and extracted features. As a

future remark, interoperability scenarios should also be included in vendor and

algorithm competitions, as donein [37].

Due to the low cost and reduced size of new ngerprint sensors, several devices

in daily use already include embedded ngerprint sensors (e.g., mobile telephones,

PC peripherals, PDAs, etc.) However, using small-area sensors implies having lessinformation available from a ngerprint and little overlap between different

acquisitions of the same nger, which has great impact on the performance of the

recognition system [59]. Some ngerprint sensors are equipped with mechan ical

guides in order to constrain the nger position. Another alternative is to perform

several acquisitions of a nger, gathering (partially) overlapping information during

the enrollment, and reconstruct a full ngerprint image. In spite of the numerous

advantages of biometric systems, they are also vulnerable to attacks [82]. Recent

studies have shown the vulnerability of ngerprint systems to fake ngerprints [35,72, 71, 63]. Surprisingly, fake biometric input to the sensor is shown to be quite

successful. Aliveness detection could be a solution and it is receiving great attention

[26, 78, 8]. It has also been shown that the matching score is a valuable piece of

information for the attacker[82, 73, 62]. Using the feedback provided by this score,

signals in the channels of the verication systemcan be modied iteratively and the

system is compromised in a number of iterations. A solution could be given by

concealing the matching score and just releasing an acceptance/rejection decision,

but this may not be suitable in certain biometric systems [82]. With the advances in

ngerprint sensing technology, new high resolution sensors are able to acquire

ridge pores and even perspiration activities of the pores [40, 21]. These features

can provide additional disc riminative information to existing ngerprint recognition


24/27

systems. In addition, acquiring perspiration activities of the pores can be used to

detect spoong attacks.


25/27

8. CONCLUSION

This paper introduces the efficient automatic attendance system, by using minutiae

based fingerprint technique. We use the methods which are simple, effective and

accurate to do the faster execution of enhancement and thinning algorithm of

fingerprint image.

In addition, we examine the experimentally determined constant K during t he

enhancement of image with using

Fourier Transform, by which we able to differentiate the enhanced quality of image

that can lead to the best verification of extracted minutiae of image. The

performance evaluation of proposed system is done by using FVC 2000 database

(500 images) [21] and the used time taken for verification was very less and

verification rate is higher and accuracy is near about 92%.


26/27

REFERENCES

[1] Fakhreddine Karray, Jamil Abou Saleh, Mo Nours Arab and Milad Alemzadeh,

Multi Modal Biometric Systems: A State of the Art Survey, Pattern Analysis and

Machine Intelligence Laboratory, University of Waterloo, Waterloo, Canada.

[2] Anil K. Jain, Arun Ross and Salil Prabhakar, An introduction to biometric

recognition, Circuits and Systems for Video Technology, IEEE Transactions on

Volume 14, Issue 1, Jan. 2004 Page(s):4 20.

[3] D. Maltoni, D. Maio, A. K. Jain, S. Prabhaker, Handbook of Fingerprint

Recognition, Springer, New York, 2003.

[4] Manvjeet Kaur, Mukhwinder Singh, Akshay Girdhar, and Parvinder S. Sandhu,

Fingerprint Verification System using Minutiae Extraction Technique, World

Academy of Science, Engineering and Technology 46 2008.

[5] H. C. Lee and R. E. Gaensslen, Advances in Fingerprint Technology, Elsevier

Science, New York, ISBN 0-444-01579-5.

[6] Guide to Fingerprint Recognition DigitalPersona, Inc. 720 Bay Road RedwoodCity, CA 94063 USA, http://www.digitalpersona.com

[7] L. OGorman, Overview of fingerprint verification technologies, Elsevier

Information Security Technical Report, Vol. 3, No. 1, 1998.

[8] B.G. Sherlock. D.M. Monro. K. Millard., Fingerprint enhancement by directional

Fourier filtering, IEE hoc. -Vis. Image Signal Processing, Vol. 141, No. 2, April

1994.

[9] Lin Hong., "Automatic Personal Identification Using Fingerprints," Ph.D. Thesis,

ISBN: 0-599-07596-1, 1998.


27/27

[10] E. Hastings, A Survey of Thinning Methodologies, Pattern analysis and

Machine Intelligence, IEEE Transactions, vol. 4, Issue 9, pp. 869885, 1992.

Attendance Fingerprint Verification

Documents