biometrics

AUTOMOBILE ENGG. DEPARTMENT Page 1
CHAPTER-1
INTRODUCTION
1.0. Background:
There are many classical ways to identify a person’s authentication such as password, identity card,etc. but
nowadays, the popular approach is Biometric which is used to authenticate a person. In this approach,we use
different identification approaches such as face recognition, voice recognition, fingerprint recognition and
retina recognition etc. So that, there is no need to carry an Identity card or too remembers password . The
most important thing is that it cannot be shared or misplaced. This approach can be used in the field of unive
rsality, acceptability, performance etc (Takita et al.,2003).The technique used in biometric system has been
broadly classified into two major areas namely behavioural and psychological biometric.
Behavioural biometric has certain parameters such as signature, speech etc.but these parameters change with
time and environment.Whereas the physiological characteristics such as palm print, face recognition, and fin
-gerprint remain unchanged throughout the individual life span. This concept is focused around the study an
implementation of a fingerprint recognition system. Fingerprint is one of the most popular biometric method
used to verify and identify a person. Formally it is defined as “The pattern of ridges and furrows on an indiv
-idual finger”. Ridges are the lines in thumb and furrow is to shallow trench of skin on an individual’s finger
.Furrow is also referred to as valley. The combination of ridges and furrows makes an individuals fingerprint
The combination of ridges and furrows that make the finger print of each person unique. The uniqueness of
a fingerprint is exclusively determined by the local ridge characteristics and their relationships (Kuglin et al.
,1975). The ridges and furrows present in the finger show good similarity in each small local windows.
Optical fingerprint imaging involves capturing a digital image of the print using visible light. This type of
sensor is, in essence, a specialized digital camera. The top layer of the sensor, where the finger is placed, is
known as the touch surface. Beneath this layer is a light-emitting phosphor layer which illuminates the surfa
-ce of the finger. The light reflected from the finger passes through the phosphor layer to an array of solidsta
-te pixels (a charge-coupled device) which captures a visual image of the fingerprint. A scratched or dirty to
uch surface can cause a bad image of the fingerprint. A disadvantage of this type of sensor is the fact that im
aging capabilities are affected by the quality of skin on the finger. For instance, a dirty or marked finger dif
ficult to image properly. Also, it is possible for an individual to erode the outer layer of skin on the fingert
ips to the point where the fingerprint is no longer visible. It can also be easily fooled by an image of afinger
print if not coupled with a "live finger" detector. However, unlike capacitive sensor, this sensor techn-ology
is not susceptible to electrostatic discharge damage.

1.1. SPECIFICATION:
It consists of optic fingerprint sensor, high performance DSP processor and Flash. It boasts of functions such
as fingerprint Login, fingerprint deletion, fingerprint verification, fingerprint upload, fingerprint download,
etc. Compared to products of similar nature, SM630 enjoys the following unique features:
 SM630 module algorithm is specially designed according to the image generation Theory of the opti-
c fingerprint collection device. It has excellent correction & tolerance to deformed and poor-quality
fingerprint.
User does not have to have professional know-how in fingerprint verification.
User can easily develop powerful fingerprint verification application systems
based on the rich collection of controlling command provided by SM630 module.
 All the commands are simple, practical and easy for development.
 Operating Voltage:
4.3V～6V
 Rating Voltage:
6.5V（exceeding this value will cause permanent damage to the module）
 Operating Current：
<80mA（Input voltage 5V）
 Fingerprint Template：
768 templates
 Search Time：
<1.5s（200 fingerprint, average value in test）
 Power-on Time：
<200ms（Time lapse between module power-on to module ready to receive
instructions）
 Tolerated Angle Offset：
±45°
 User Flash Memory：
64KByte
 Interface Protocol:
Standard serial interface （TTL level）
 Communication Baud Rate:
57600bps
 Operating Environment:
Temperature: -10℃～+40℃
Relative humidity: 40％RH～85％RH

1.1.1. CIRCUIT:
The circuit is fabricated on a silicon board of a 75mm x 27mm dimension. As shown in the fig 1.1: 1.50 mm is left on side walls
to be able to attach it to the prototype body.
FIG 1.1. circuit dimensions
1.1.2 optical sensor :
The biometric glass is optical and is used to capture the image of the
finger features. As shown in the fig 1.2:the glass dimension is 19.50mm x 32.50mm.
FIG 1.2: OPTICAL FINGER SCANNER

1.2 COMPONENTS:
1.2.1 STEP DOWN TRANSFORMER
As shown in the fig.1.3: Step down transformer is 220 volt Ac to 9-0-9 ac. We use step down transformer to
step down the voltage from 220 to 9 volt ac. This AC is further connected to the rectifier circuit for AC to
DC conversion. Transformer current rating is 750 ma .
FIG 1.3 TRANSFORMER
1.2.2 DIODE.
In this project we use IN 4007 diode as a rectifier. IN 4007 is special diode to convert the AC into DC In this
project we use two diode as a rectifier. Here we use full wave rectifier. Output of rectifier is pulsating DC.
To convert the pulsating dc into smooth dc we use Electrolytic capacitor as a main filter. From fig:1.4: it
converts AC to DC. Capacitor converts the pulsating dc into smooth dc and this DC is connected to the Regu
-lator circuit for Regulated 5 volt DC.
FIG 1.4: DIODE

1.2.3 microcontroller unit
A microcontroller is a small computer (SoC) on a single integrated circuit containing a processor core, me
mory, and programmable input/output peripherals. Program memory in the form of Ferroelectric RAM, NoR
flash or OTP ROM is also often included on chip, as well as a typically small amount of RAM. Microcontro
llers are designed for embedded applications, in contrast to the microprocessors used in personal computer
s or other general purpose applications consisting of various discrete chips. From the fig 1.5: there is the con
version power from 220V to 9V through secondary circuit.
FIG 1.5: MICROCONTROLLER CIRCUIT
1.2.3 RESET CIRCUITRY
From the fig.1.6: Pin no 9 of the controller is connected to the reset circuit. On the circuit we connect one
resistor and capacitor circuit to provide a reset option when power is on.As soon as you give the power suppl
-y the 8051 doesn't start. You need to restart for the microcontroller to start. Restarting the microcontroller is
nothing but giving a Logic 1 to the reset pin at least for the 2 clock pulses. So it is good to go for a small cir
-cuit which can provide the 2 clock pulses as soon as the microcontroller is powered. This is not a big circuit
we are just using a capacitor to charge the microcontroller and again discharging via resistor.
FIG 1.6 RESET CIRCUITRY

1.2.4 CRYSTALS
As shown in fig1.7: Pin is connected to external crystal oscillator to provide a clock to the circuit. Crystals
provide the synchronization of the internal function and to the peripherals. Whenever ever we are using cryst
als we need to put the capacitor behind it to make it free from noises. It is good to go for a 33pf capacitor.
As shown in fig:1.8 the circuit is grounded to avoid excess current.
FIG 1.7: CRYSTALS FIG 1.8: CRYSTALS CIRCUIT
We can also resonators instead of costly crystal which are low cost and external capacitor can be avoided.
But the frequency of the resonators varies a lot. And it is strictly not advised when used for communications
projects.

1.3 PROGRAMMING A BLANK CHIP
1.3.1 The 8051
The 8051 developed and launched in the early 80`s, is one of the most popular micro controller in use today.
It has a reasonably large amount of built in ROM and RAM. In addition it has the ability to access external.
The generic term `8x51` is used to define the device. The value of x defining the kind of ROM, i.e. x=0, indi
cates none, x=3, indicates mask ROM, x=7, indicates EPROM and x=9 indicates EEPROM or Flash.
Different micro controllers in market.
 PIC: One of the famous microcontrollers used in the industries. It is based on RISC Architecture
which makes the microcontroller process faster than other microcontroller.
 INTEL:These are the first to manufacture microcontrollers. These are not as sophisticated other
microcontrollers but still the easiest one to learn.
 ATMEL:Atmel's AVR microcontrollers are one of the most powerful in the embedded industry. This
is the only microcontroller having 1kb of ram even the entry stage. But it is unfortunate that in India
we are unable to find this kind of microcontroller.
1.3.2 INTEL 8051
Intel 8051 is CISC architecture which is easy to program in assembly language and also has a good support f
or High level languages.
The memory of the microcontroller can be extended up to 64k.
This microcontroller is one of the easiest microcontrollers to learn.
The 8051 microcontroller is in the field for more than 20 years. There are lots of books and study materials a
re readily available for 8051.
First of all we select and open the assembler and wrote a program code in the file. After wrote a software
we assemble the software by using internal assembler of the 8051 editor. If there is no error then assembl
er assemble the software abd 0 error is show the output window.
now assembler generate a ASM file and HEX file. This hex file is useful for us to program the blank chip.
Now we transfer the hex code into the blank chip with the help of serial programmer kit. In the programmer
we insert a blank chip 0f 89s51series.These chips are multi time programmable chip. This programming kit
is separately avilable in the market and we transfer the hex code into blank chip with the help of the serial
programmer kit.

fig1.9: first screen
fig 1.10: second screen
fig 1.11: third screen

1.4 WORKING OF ICD SCREEN
A liquid-crystal display (LCD) is a flat-panel display or other electronic visual display that uses the light-mo
dulating properties of liquid crystals. Liquid crystals do not emit light directly.In a plasma screen, each pixel
is a tiny fluorescent lamp switched on or off electronically. In an LCD screen, the pixels are switched on or
off electronically using liquid crystals to rotate polarized light. Each pins have different potential charged to
it. As the message are very limited to be displayed, we can use a 2 x 16 LCD display unit.
fig 1.12: LCD SCREEN CKT.

Description of various nodes of connections and its values :
PIN NO 1 VSS GROUND
PIN NO 2 VCC +5 V SUPPY.
PIN NO 3 VEE POWER SUPPLY TO CONTRAST CONTROL
PIN NO 4 RS RS = 0 TO SELECT
FIG 1.13: LCD SCREEN SPECIFICATIONS
from fig 1.13
Module is connected to HOST via 4PIN cable. The PIN definition is as follows:
No. PIN Definition Remarks
1 Power supply ＋ Power supply +
2 Module Tx Open circuit output, need to use pull-up
impedance in application (Typical value:
10KΩ)
3 Module Rx Wide voltage input, 7V affordable
4 Power supply Power supply －
Notes:
The PIN close to the edge of circuit board is PIN4: Power supply －.

1.5. CODING METHODS
The communication between HOST and Module must be coded as Communication
Packet.
One communication packet includes the following:
Packet Head（2 bytes）
Packet flag（1 byte）
Packet length（1 byte）
Packet Content（N bytes）
Check sum（1 byte）
Packet head：0x4D 0x58
Packet flag;
0x10：command packet
0x20：data packet
0x21：last packet
0x30：response packet
Packet length：
Length of the Content in packet
Packet content：
Content of packet
Check sum：
Low 8 bytes of the SUM from packet head to check sum.
1.5. BRIEF WORK FLOWCHART:
Module waits for command from HOST after it is powered on. Module will respond
by a Rx correct packet after receiving the correct command. Module will perform
operations according to the command and will return corresponding information after
the operation is successful. When the Module is performing operation, it will not
respond to other command given by HOST. If the check sum for the received
command is wrong, the module will send back receive error response.
Module receive correct packet:
0x4D + 0x58 + 0x30 + 0x01 + 0x01 + 0xD7
Module receive error packet:0x4D + 0x58 + 0x30 + 0x01 + 0x02 + 0xD8

FIG 1.14 FLOW CHART SHOWING LOGIC OF OPERATION

CHAPTER 2
LITERATURE REVIEW
Ravi Bhushan Tiwari & Sanjay Sharma[1]:Fingerprint identification is one of the most important
approaches for identification. Fingerprint identification has been publicized because of its consistency and
uniqueness over the period of time. Biometric identification process has gained popularity with the recent
advancement of computing capability. The uniqueness of the fingerprint and the processing power has
gained popularity in various walks of our life for the purpose of authentication and verification. This study
describes a fingerprint identification system and its implementation to establish the identity of a person. The
approach presented herein matches the fingerprint on two parameter minutia and furrows.
Anil K. Jain, Arun Ross & Salil Prabhakar[2]:A wide variety of systems requires reliable person
al recognition schemes to either confirm or determine the identity of an individual requesting their services.
The purpose of such schemes is to ensure that the rendered services are accessed only by a legitimate user an
d no one else. Examples of such applications include secure access to buildings, computer systems, laptops,
cellular phones, and ATMs. In the absence of robust personal recognition schemes, these systems are vulner
able to the wiles of an impostor. Biometric recognition or, simply, biometrics refers to the automatic recogni
tion of individuals based on their physiological and/or behavioral characteristics. By using biometrics, it is p
ossible to confirm or establish an individual’s identity based on “who she is,” rather than by “what she posse
sses” (e.g., an ID card) or “what she remembers” (e.g., a password). In this paper, we give a brief overview o
f the field of biometrics and summarize some of its advantages, disadvantages, strengths, limitations, and rel
ated privacy concerns.
Index Terms—Biometrics, identification, multimodal biometrics, recognition, verification.
M.L. Gavrilova [3]:Respect to all aspects of information access and sharing. Notable progress has been
made Over the past decade, the security research domain has witnessed tremendous growth in
in developing successful approaches to tackle the problems of user authentication, password protection,
network security, data encryption, and information privacy. In the field of security research, biometric-based
authentication firmly established itself as one of the most reliable, efficient, and versatile tools for providing
discretionary access control to a secure resource or system.While state-of-the art methods for biometric
authentication are becoming increasingly more powerful and better understood, the same unfortunately
cannot be said about the security of users populating on-line communities or Cyber worlds.
Ensuring safe and secure communication and interaction among users and, respectably, their on-line
identities presents unique challenges to academics, as well as industry and the public. Security breaches,
credit card fraud, identity theft, criminal on-line activities, and cyber bullying are just some of the
Cyberworld security issues that plague society. Despite the fact that those challenges are regularly making
headlines in the news, government reports, and in the IT security domain, there is an appalling lack of effort
to address this urgent problem. The efforts that do exist are currently limited to network security, password
protection, encryption, database security and privacy policy-making efforts. However, one of the most

crucial components for ensuring on-line security – the relationship of online communication among users,
and their identities in the real world – has been largely overlooked. A systematic study, and targeted effort to
develop effective security solutions to this crucial concern is the main focus of this paper.
Filip Orság & Martin Drahanský [4]:This paper deals with the design of a biometric security
system based upon the fingerprint and speech technology. In the first chapter there are the biometric security
systems and a concept of an integration of the both technologies introduced. Then the fingerprint technology
followed by the speech technology is shortly described. There are discussed some basic principles of each of
the technologies.
Keywords: fingerprint, speaker, recognition, biometric, security.
Emin Martinian, Sergey Yekhanin & Jonathan S. Yedidia[5]:Observing secure biometric
storage problem and develop a solution using syndrome codes. Specifically, biometrics such as fingerprints,
irises, and faces are often used for authentication, access control, and encryption instead of passwords.
While it is well known that passwords should never be stored in the clear, current systems often store
biometrics in the clear and are easily compromised. We describe the secure biometric storage problem by
discussing the insecurities in current systems, the reasons why password hashing/encryption algorithms are
unsuitable for biometrics, and propose a secure biometric storage framework based on syndrome codes and
the Slepian-Wolf theorem.
Kresimir Delac, Mislav Grgic[6]:Biometric recognition refers to an automatic recognition of
individuals based on a feature vector(s) derived from their physiological and/or behavioral characteristic.
Biometric recognition systems should provide a reliable personal recognition schemes to either confirm or
determine the identity of an individual. Applications of such a system include computer systems security,
secure electronic banking, mobile phones, credit cards, secure access to buildings, health and social services.
By using biometrics a person could be identified based on "who she/he is" rather then "what she/he has"
(card, token, key) or "what she/he knows" (password, PIN). In this paper, a brief overview of biometric
methods, both unimodal and multimodal, and their advantages and disadvantages, will be presented.
Keywords: Biometrics, Multimodal Biometrics, Recognition, Verification, Identification, Security.
Anil K. Jain, Lin Hong & Sharath Pankanti [7]:Personal recognition schemes to either confirm
or determine the identity of an individual requesting their services. The purpose of such schemes is to ensure
that the rendered services are accessed only by a legitimate user, and not anyone else. Examples of such
applications include secure access to buildings, computer systems, laptops, cellular phones and ATMs. In the
absence of robust personal recognition schemes, these systems are vulnerable to the wiles of an impostor.
Biometric recognition, or simply biometrics, refers to the automatic recognition of individuals based on their
physiological and/or behavioral characteristics. By using biometrics it is possible to confirm or establish an
individual’s identity based on “who she is”, rather than by “what she possesses” (e.g., an ID card) or “what
she remembers” (e.g., a password). In this paper, we give a brief overview of the field of biometrics and
summarize some of its advantages, disadvantages, strengths, limitations, and related privacy concerns. Index
Terms: Biometrics, Recognition, Verification, Identification, Multimodal Biometrics.

Siddhesh Angle, Reema Bhagtani & Hemali Chheda[8]:Biometrics refers to the automatic
identification of a person based on his/her physiological or behavioral characteristics. This method of
identification is preferred over traditional methods involving passwords and PIN numbers for its accuracy
and case sensitiveness. A biometric system is essentially a pattern recognition system which makes a
personal identification by determining the authenticity of a specific physiological or behavioral
characteristic possessed by the user. An important issue in designing a practical system is to determine how
an individual is identified. Depending on the context, a biometric system can be either a verification
(authentication) system or an identification system. Verification involves confirming or denying a person's
claimed identity while in identification, one has to establish a person's identity. Biometric systems are
divided on the basis of the authentication medium used. They are broadly divided as identifications of Hand
Geometry, Vein Pattern, Voice Pattern, DNA, Signature Dynamics, Finger Prints, Iris Pattern and Face
Detection. These methods are used on the basis of the scope of the testing medium, the accuracy required
and speed required. Every medium of authentication has its own advantages and shortcomings. With the
increased use of computers as vehicles of information technology, it is necessary to restrict unauthorized
access to or fraudulent use of sensitive/personal data. Biometric techniques being potentially able to
augment this restriction are enjoying a renewed interest.
Erdem Yoruk, Helin Dutagaci & Bulent Sankur[9]: The potential of hand-shape and hand-
texture based biometry is investigated and algorithms are developed. Feature extraction stage is preceded by
meticulous registration of the deformable shape of the hand. Alternative features addressing hand shape and
hand texture are investigated. Independent component analysis features prove to be the best performing in
the identification and verification tasks. It is shown that hand biometric devices can be built that perform
reliably for a population of at least half a thousand.
Keywords: Biometry. Identification and verification. Principal and independent components. Registration
for deformable shapes. Distance transform.
Julian Ashbourm[10]:The ID3D hand geometry reader, currently the most popular of the commercially
available units, installed at over 4000 locations, works by comparing the three dimensional image of the
hand with a previously enrolled sample. It is extremely easy to use and requires no technical expertise on
behalf of the user, who simply enters his number on a keypad and places his hand on the platter. Actual
verification typically takes around one second, with the whole cycle of keying in a number and placing the
hand on the platter taking around four to six seconds. This compares favourably with card based systems. In
fact a card may be used in conjunction with the hand reader, in which case the PIN is input from the card.
Entering the PIN, either from the integral keypad or from a card swipe, calls up the correct template from
the systems memory so that comparison with the presented hand can take place. The image of the hand is
captured by a CCD digital camera and subsequently analysed by software running on a buitt in HD64180
microprocessor. Identifying characteristics based on geometric measurements are compared with enrolled
templates, with a match or no match resutt dependent on previously determined case.

Syuichi Yasuoka, Yousun Karig, Ken'ichi Morooka & Hiroshi Nagahashi[11]:Texture
analysis is an important and useful area in computer vision and pattern recognition. Image texture is
constituted by various colors and luminance, so that its model can be represented as a mathematical function
with variation of pixel intensities. Many methods such as statisticid, geometrical, model based and signal
processing methods have been devised to extract the local or global features from texture images [I]. The
effectiveness of the extracted feature set depends on how well patterns from different classes can be
seperated on the feature space. Texture classification involves deciding what texture category an extracted
feature distribution belongs to. Statistical feature can be represented by a large number of feature vectors in
high diemensional feature space. Many approaches to designing a classifier are trying to solve the problems
of high dimensional feature vectors as well as a large number of classes. The choice of an efficient
discriminant function is also important to reduce the computational complcxity of enormous amount of
statistical features.
Juyang Weng and Wey-Shiuan Hwang[12]:They propose a new technique which incrementally
derive discriminating features in the input space. This technique casts both classification problems (class
labels as outputs) and regression problems (numerical values as outputs) into a unified regression problem.
The virtual labels are formed by clustering in the output space. We use these virtual labels to extract
discriminating features in the input space. This procedure is performed recursively. We organize the
resulting discriminating subspace in a coarse-to-fine fashion and store the information in a decision tree.
Such an incrementally hierarchical discriminating regression (IHDR) decision tree can be realized as a
hierarchical probability distribution model. We also introduce a sample size dependent negativelog-
likelihood (NLL) metric to deal with large-sample size cases, small-sample size cases, and unbalanced-
sample size cases. This is very essential since the number of training samples per class are different at each
internal node of the IHDR tree. We report experimental results for two types of data: face image data along
with comparison with some major appearance-based method and decision trees, hall way images with
driving directions as outputs for the automatic navigation problem – a regression application.
Michael Goh Kah Ong, Tee Connie, Andrew Teoh Beng Jin, David Ngo Chek
Ling[13]:Several contributions have shown that fusion of decisions or scores obtained from various
single-modal biometrics verification systems often enhances the overall system performance. A recent
approach of multimodal biometric systems with the use of single sensor has received significant attention
among researchers. In this paper, a combination of hand geometry and palmprint verification system is being
developed. This system uses a scanner as sole sensor to obtain the hands images. First, the hand geometry
verification system performs the feature extraction to obtain the geometrical information of the fingers and
palm. Second, the region of interest (ROI) is detected and cropped by palmprint verification system. This
ROI acts as the base for palmprint feature extraction by using Linear Discriminant Analysis (LDA). Lastly,
the matching scores of the two individual classifiers is fused by several fusion algorithms namely sum rule,
weighted sum rule and Support Vector Machine (SVM). The results of the fusion algorithms are being
compared with the outcomes of the individual palm and hand geometry classifiers. We are able to show that
fusion using SVM with Radial Basis Function (RBF) kernel has outperformed other combined and
individual classifiers.

Karthik Nandakumar and Anil K. Jain[14]:Unimodal biometric systems are often affected by
several practical problems like noisy sensor data, nonuniversality and/or lack of distinctiveness of the
biometric trait, unacceptable error rates, and spoof attacks. Multimodal biometric systems overcome some of
these problems by consolidating the evidence obtained from different sources [1]. In a multimodal biometric
system, various levels of fusion are possible: fusion at the feature extraction level, matching score level or
decision level. Integration at the matching score level is generally preferred due to the ease in accessing and
combining matching scores.
Ram Meshulam, Shulamit Reches, Aner Yarden and Sarit Kraus [15]:Security systems can
observe and hear almost anyone everywhere. However, it is impossible to employ an adequate number of
human experts to analyze the information explosion. In this paper, we present an autonomous multi-agent
framework which, as an input, obtains biometric information acquired at a set of locations. The framework
aims in real-time to point out individuals who act according to a suspicious pattern across these locations.
The system works in large-scale scenarios. We present two scenarios to demonstrate the usefulness of the
framework.
Luisa Riccardi, Bruno Peticone and Mario Savastano [16]:The increase in securig measures
due to the compler international situation is forcing the realization of several access control systems
equipped with biometric identipem. Apart from technical problems, a number of nontechnical issues,
strong& related to the user’s acceptance, may have a strong influence on the design of the application and
suggest particular choices in the selection of the biometric technique to be adopted, Starfing from the
assumption that facial recognition represents one of the most widely “accepted” biometric techniques, and
that, due to confradictory performances shown in operating conditions, this methodology is seldom
considered for high-securiq applications, the Authors have investigated the possibiliq of improving the error
figures by means of 4n original approach. The innovation consists in “enriching” the template obtained by
means of canonical facial recognition algorithms with additional information extracted from behavioral
characteristics of the user. The study, still in the early stage, is carried out in the framework of a
collaboration between the National Research Council of Italy (CNR) and the Italian Ministry of the Defense
(MoDj in the area of the strong authentication for physical access to militarry compounds. The aim of the
preseni paper is only the highlighting of the poientialify of such an approach since first experimental data
are not mature to generate consolidated error figures such as FAR and FRR. In any event, a very good
capability in distinguishing between identical huh, a very welt known problem in facial recognition, is a
promising preamble for the continuation uf the research.
Index terms - Biometrics, access control, facial recognition.
Sharath Chikkerur, Sharath Pankanti, Nalini Ratha and Ruud Bolle[17]:Minutiae
extraction is one of the critical steps in fingerprint verification algorithms. Any missing minutiae or spurious
minutiae introduced at this stage can degrade the performance of the matching algorithm. Existing structural
approaches for minutiae filtering use heuristics and adhoc rules to eliminate such false positives, where as
gray level approaches are based on using raw pixel values and a supervised classifier such as neural
networks. We propose two new techniques for minutiae verification based on non-trivial gray level features.
The proposed features intuitively represents the structual properties of the minutiae neighborhood leading to
better classification. We use directionally selective steerable wedge filters to differentiate between minutiae
and non-minutiae neighborhoods with reasonable accuracy. We also propose a second technique based on

Gabor expansion that results in even better discrimination. We present an objective evaluation of both the
algorithms. Apart from minutiae verification, the feature description can also be used for minutiae detection
and minutiae quality assessment.
Tami R. Randolph and Mark J. T. Smith[18]:In this paper, we explore a novel approach to
enhancing fingerprint images using a new binary directional filter bank (DFB). Automated fingerprint
identification systems (AFIS) are used to classify a fingerprint in a large volume of images. Many
approaches to AFIS have been suggested, most sharing in common the idea of extracting discriminate
feature representations. As part of that process, the raw fingerprints are often smoothed, converted to binary
and thinned. Conventional directional methods, which have been used successfully in the past, provide
representations that delineate the directional components in the fingerprint image enabling separation, and
enhancement. Our binary DFB receives a binary input and outputs a binary image set comprised of
directional components. Through proper weighting and manipulation of the subbands, specific features
within the fingerprint can be enhanced. We propose a new enhancement approach that remains in the binary
domain for the entire process.

CHAPTER 3
METHODOLOGY :
Three new approaches have been recently to biometric technology with implications for Cyberworld
security:
a) exploring the capabilities of multi-modal biometric fusion methods in the context of
Cyberworld user identity recognition;
b) developing a set of metrics for identifying abnormal user behaviours through recognition of their
physiological and behavioural traits; and
c) introducing the notion of biometric cancellability in the context of Cyber world authentication.
These new approaches will provide a powerful and unique methodology for enhancing user security in on-
line communities, and society as a whole. Thus we did the costing of the project and accordingly bought the
raw materials & then we learnt to read the electronic circuit and do the programming on ATMEL platform.
Then we designed the circuit with the help of pro-electronic engineer and technician.
The methodology can be further extended to relevant domains, including multimedia, text and image
categorization, multi-modal image retrieval and web based social network analysis.
Work by the researchers and collaborators of Biometric Technologies lab demonstrate the potential of using
machine intelligence and context-based biometrics in the design of new generation security systems.
The recent book “Multimodal Biometrics and Intelligent Image Processing for Security Systems” published
by IGI outlines a number of methodologies. It argues for the use of multi-modal biometric system, rather
than the traditional single biometric approach. It has been well established over the last decade that
individual biometrics have a number of deficiencies, including issues of universality, uniqueness, changes
over time, behaviour state dependence, poor sample quality, and human error. Due to the fact that
multimodal biometric system can incorporate two or more individual biometric traits, the overall system
recognition rate can increase significantly. This remains true even in the presence of erroneous, incomplete
or missing data.
The second direction will leverage the behavioural biometrics for abnormal behavior detection and
risk management in online community users. Biometrics has come close to avatar development and
intelligent robots/software authentication many times before. In 1998 M.J. Lyons et.al. published “Avatar
Creation using Automatic Face Recognition”, where authors discuss specific steps that need to be taken in
order for avatars to be created automatically from the human face. A recently published paper demonstrated
the possibility of using behavioural biometric strategies designed to recognize humans to identify artificially
created intelligent software agents used to gain an unfair advantage by some members of multiplayer online
communities. The paper lays the theoretical groundwork for research in authentication of non-biological
entities. Behavioral characteristics are even less likely to change than the avatar’s facial appearance and
clothes, as users typically invest a lot of time and money into creation of a consistent virtual image but
would not so easily change their patterns of behavior. The artificial intelligence learning methods based on
chaotic neural networks can be successfully utilized to learn normal and abnormal user behavioral patterns.

3.1. STEPS INVOLVED IN BIOMETRIC RECOGNITION USING FINGERPRINT SCANNING:
fig: 2.1 sequence of actions

CHAPTER 4
AIMS AND OBJECTIVES:
The main objective of this project and its technological implications is to increase the security measure for
the vehicle and also make it more convenient.Following are some major intricate understanding from the
projects which has lead to broaden our objectives and aim, many of which are subject to future research
works. “Big data” challenges that demand real-time performance with high recognition rates on very large
data repositories..Need for better privacy policies and their enforcement to protect user confidentiality;.
Changes in databases over time might require more sophisticated training and learning methods. Ability to
use contextual information obtained in parallel to main biometric features:-
a) Development of more advanced information fusions methods that have the ability to adapt to
biometric system changes (such as the addition of a new module or data source) while maintaining a
required level of precision.
b) Detection of normal vs. abnormal on-line user behavior through advanced pattern analysis of
appearance-based and behavioral biometrics (typing patterns, voice, text, blogs);
c) Investigating on-line social network activities as new type of biometric traits, i.e. “social biometrics”
(Twitter, Wikipedia, Facebook and LinkedIn social networks etc);
d) Emerging research into spatio-temporal biometrics for on-line communities;
e) Further development of artificial biometrics domain (Artimetrics) with new data obtained on avatars,
bots and other entities in virtual worlds;
f) Understanding mechanism that contribute to creating successful on-line communities; and
g) Studying leadership and popular personality traits in Cyber worlds
The applications of biometrics can be divided into the following three main groups:
• Commercial applications such as computer network login, electronic data security, ecommerce, Internet
access, ATM, credit card, physical access control, cellular phone, PDA,
medical records management, distance learning, etc.
• Government applications such as national ID card, correctional facility, driver’s license, social security,
welfare-disbursement, border control, passport control, etc.
• Forensic applications such as corpse identification, criminal investigation, terrorist identification,
parenthood determination, missing children, etc.
Traditionally, commercial applications have used knowledge-based systems (e.g., PINs and passwords),
government applications have used token-based systems (e.g., ID cards and badges), and forensic
applications have relied on human experts to match biometric features. Biometric systems are being
increasingly deployed in large scale civilian applications (see Figure 4). The Schiphol Privium scheme at the
Amsterdam airport, Readings, employs iris scan cards to speed up the passport and visa control procedures.
Passengers enrolled in this scheme insert their card at the gate and look into a camera; the camera acquires
the image of the traveller's eye and processes it to locate the iris, and compute the Iriscode the computed
Iriscode is compared with the data residing in the card to complete user verification. A similar scheme is
also being used to verify the identity of Schiphol airport employees working in high-security areas. Thus,
biometric systems can be used to enhance user convenience while improving security.

CHAPTER 5
RESULT AND ANALYSIS
Biometrics is a rapidly evolving technology that has been widely used in forensics, such as criminal identific
ation and prison security. Biometric identification is also under serious consideration for adoption in a broa
d range of civilian applications. E-commerce and e-banking are two of the most important application are
as due to the rapid progress in electronic transactions. These applications include electronic fund transfers, A
TM security, check cashing,
credit card security, smartcards security, and online transactions. There are currently several large biometric
security projects in these areas under development, including credit card security (MasterCard) and smart
card security (IBM and American Express). A variety of biometric technologies are now competing to de
monstrate their efficacy in these areas.The market of physical access control is currently dominated by token
-based technology. However, it
is predicted that, with the progress in biometric technology, market share will increasingly shift to bi
ometric techniques. Information system and computer-network secu-
rity, such as user authentication and access to databases via remote login is another potential application
area. It is expected that more and more information systems and computer-networks will be secured with bio
metrics with the rapid expansion of Internet and intranet. With the introduction of biometrics, government b
enefits distribution programs such as welfare disbursements will experience substantial savings in dete
rring multiple claimants. In
addition, customs and immigration initiatives such as INS Passenger Accelerated Service System(INSPA
SS), which permits faster processing of passengers at immigration checkpoints based on hand geometry, wil
l greatly increase the operational efficiency. A biometric-based national identification system provides a
unique ID to the citizens and integrates different government services. Biometrics based voter registrat
ion prevents voter fraud; and
biometrics-based driver registration enforces issuing only a single driver license to a person; and biometrics-
based time/attendance monitoring systems prevent abuses of the current token-based manual systems. H
umans have used fingerprints for personal identification for centuries and the validity of fingerprint ident
ification has been well-established [6]. A fingerprint is the pattern of ridges and furrows on the surface of a
fingertip, the formation
of which is determined during the fetal period. They are so distinct that even fingerprints of identical twi
ns are different as are the prints on each finger of the same person.
With the development of solid-state sensors, the marginal cost of incorporating a fingerprint-based COM
MUNICATIONS OF THE ACM February 2000/Vol. 43, No. 2 95biometric system may soon become aff
ordable in many applications. Consequently, fingerprints are expected to lead the biometric applications i
n the near future, with multiple fingerprints providing sufficient information to allow for large-scale reco
gnition involving millions of identities.
One problem with fingerprint technology is its lack of acceptability by a typical user, because fingerprint
s have traditionally been associated with criminal investigations and police work. Another problem is th
at automatic fingerprint identification generally requires a large amount of computational resources. Fi
nally, finger prints of a small fraction of a population may be unsuitable for automatic identification
because of genetic, aging, environmental, or occupational reasons. Hand geometry. A variety of measur
ements of the human hand, including its shape, and lengths and widths of the fingers,. The prominent local ri

dge is referred to as minutiae. This characteristic of the finger print image is used to compare an individual’s
finger image with the others stored finger images. Minutiae consist of ridge ending, ridge bifurcation, short
ridge, or independent ridge, island, ridge enclosure, spur, crossover or bridge, delta and core. Ridge ending i
s the abrupt end of a ridge; a single ridge that divides into two ridges is ridge bifurcation, ridge that commen
ces, travels a short distance and then ends is termed as short ridge, or independent ridge. Island is a single s
mall ridge inside a
short ridge, a single ridge that bifurcates and reunites shortly afterward to continue as a single ridge is called
ridge enclosure. Spur is a bifurcation with a short ridge branching off a longer ridge whereas; crossover or
bridge is a short ridge that runs between two parallel ridges. Y-shaped ridge meeting is known as a delta and
core is a U-turn in the ridge pattern. A good quality fingerprint contains 25 to 80 minutiae depending on the
sensor resolution and finger placement on the sensor. In some cases, it is difficult to extract prominent
minutia, as the
fingerprint impression is distorted due to various reasons like dry skin, injury, scars etc. This poor quality
fingerprint image leads to false minutia. False minutia is the false positive result due to insufficient ink or
due to cross connect of over-inking. A fingerprint image of an optical sensor.
Fingerprint recognition system mainly works on two stages minutiae extraction and minutiae matching (Fig.
5). In this approach, system takes two input fingerprints to be matched and it gives the percentage of
matching between two images. As we can see in figure 5, the minutiae extractor can be further classified
into three sub-modules such as image segmentation, image enhancement and final extraction. In figure 5,
minutiae matcher can also be further classified into two sub-modules such as minutiae alignment and match.
Image segmentation and image enhancement are further sub-divided in image binariztion, histogram
equalization and fast Fourier transformation (Jain et al., 1993). Further image
enhancement uses the approach of Binarization so that image can be sharp. The minutiae location and the
minutiae angles are derived after minutiae extraction. The terminations which lie at the outer boundaries are
not considered as minutiae points. Crossing number is used to locate the minutiae points in fingerprint
image. Crossing number is defined as half of the sum of differences between intensity values of two adjacent
pixels. If crossing number is 1, 2 and 3 or greater than 3 then minutiae points are classified as termination,
normal ridge and bifurcation respectively. We can see all these points in figure 8. Figure 9 shows the
original image and the extracted minutiae points. Square shape shows the position of termination and
diamond shape shows the position of bifurcation as in figure 9a and b.
ρkt = radial distance of kth minutiae
φkt = radial angle of kth minutiae
θkt = orientation angle of kth minutiae
rot = row index of reference points currently being considered
cot= column index of reference points currently being considered
rkt = row index of kth points currently being considered
ckt= column index of kth points currently being considered.

TABLE : 5(a) commands
S.NO. : NAME OF COMMAND COMMAND
CODE
1. Add Fingerprint 0X40
2. Delete Fingerprint 0X42
3. Search Fingerprint 0X44
4. Empty Fingerprint Database 0X46
5. Search Information in Fingerprint Database 0X48
6. Download Fingerprint Tempelate 0X50
7. Upload Fingerprint Tempelate 0X52
8. Read ID Number 0X60
9. Read user Flash 0X62
10. Write User Flash 0X64
11. Read Product Logo 0X80

TABLE 5(b) Response codes
S.NO. : NAME OF COMMAND COMMAND CODE
1. Receive correct 0X01
2. Receive Error 0X02
3. Operation successful 0X31
4. Finger detected 0X32
5. Time out 0X33
6. Fingerprint process failure 0X34
7. Parameter error 0X35
8. Matching id found 0X34
9. No Matching id found 0X37
10. fingerprint found 0X39
11. Fingerprint not found 0X40

5.1. PROGRAMMING SEQUENCE AND LOGIC:
1) HOST send command to search
16 fingerprints starting from 0:
0x4D + 0x58 + 0x10 + 0x05 + 0x44 + 0x00 + 0x00 + 0x00 + 0x10 + 0x0E
2) When the fingerprint is placed on the sensor window, module will respond as
operation successful:
0x4D + 0x58 + 0x30 + 0x02 + 0x44 + 0x31 + 0x4C
3) If the fingerprint is found, module will return the following:
0x4D + 0x58 + 0x30 + 0x04 + 0x44+ 0x39 + high bytes of ID for the found
fingerprint + low bytes of ID for the found fingerprint + check sum
4) If no matching fingerprint is found, module will return the following:
0x4D + 0x58 + 0x30 + 0x02 + 0x44 + 0x3A + 0x55 Readings：
1 HOST send command to search 16 fingerprints starting from 0:
0x4D + 0x58 + 0x10 + 0x05 + 0x44 + 0x00 + 0x00 + 0x00 + 0x10 + 0x0E
2 When the fingerprint is placed on the sensor window, module will respond as
operation successful:
0x4D + 0x58 + 0x30 + 0x02 + 0x44 + 0x31 + 0x4C
3 If the fingerprint is found, module will return the following:
0x4D + 0x58 + 0x30 + 0x04 + 0x44+ 0x39 + high bytes of ID for the found
fingerprint + low bytes of ID for the found fingerprint + check sum
If no matching fingerprint is found,
Remarks：
1 The number of the fingerprints that are searched starts from the ID of the first
fingerprint, Readings, the search starts from fingerprint ID 0. the number of
fingerprints searched is 0x10，then the fingerprint ID actually being searched is 0～
0x0F, altogether 0x10 fingerprints.
2 If the ID in the command is wrong, module will responds as parameter error:
0x4D + 0x58 + 0x30 + 0x02 + 0x44 + 0x35 + 0x50
3If the fingerprint quality is poor, module will respond as fingerprint processing
failure:
0x4D + 0x58 + 0x30 + 0x02 + 0x44 + 0x34 + 0x4F

4 If there is no finger placing on the sensor with 10 seconds, module will respond
as time out:
0x4D + 0x58 + 0x30 + 0x02 + 0x44 + 0x33 + 0x4E
5) Empty Fingerprint Database
Description: Empty all fingerprints in fingerprint database
Length：1 byte
Format：Command code 0x46
Readings：
1 HOST send command to empty fingerprint database:
0x4D + 0x58 + 0x10 + 0x01 + 0x46 + 0xFC
2 Module will respond as Rx correct: 0x4D + 0x58 + 0x30 + 0x01 + 0x01 +
0xD7
3 Module will respond as operation successful after executing command to empty
fingerprint database:
0x4D + 0x58 + 0x30 + 0x02 + 0x46 + 0x31 + 0x4E
6) Search Fingerprint Database Information
Description：Search and see if there is fingerprint matching the designated ID
Length：3 bytes
Format：Command code 0x4B + high byte of the to-be-searched fingerprint ID + low
byte of the to-be-searched fingerprint ID
Readings：
1 HOST send command to search fingerprint with ID 0:
0x4D + 0x58 + 0x10 + 0x03 + 0x4B + 0x00 + 0x00 + 0x03
0xD7
3 If there is fingerprint with ID 0, module will return the following:
0x4D + 0x58 + 0x30 + 0x02 + 0x4B + 0x37 + 0x59
4 If there is no fingerprint with ID 0, module will then return the following:
0x4D + 0x58 + 0x30 + 0x02 + 0x4B + 0x38 + 0x5A
Remarks：

1 If the fingerprint ID in the command is out of range, module will respond as
parameter error:
0x4D + 0x58 + 0x30 + 0x02 + 0x4B + 0x35 + 0x57
7) Download Fingerprint Template
Description：Download a fingerprint into the module
Length：3 bytes
Format：Command code 0x50 + high byte of the to-be-downloaded fingerprint ID +
low byte of the to-be-downloaded fingerprint ID
Readings：
1 HOST send a command to download a fingerprint to the position for ID 0:
0x4D + 0x58 + 0x10 + 0x03 + 0x50 + 0x00 + 0x00 + 0x08
0xD7
3 HOST send the first data packet (packet content 128):
0x4D + 0x58 + 0x20 + 0x80 + ……128 bytes of data…… + check sum
0xD7
5 HOST send the second data packet (packet content 128):
0xD7
7 Module will respond as operation successful: 0x4D + 0x58 + 0x30 + 0x02 +
0x50 + 0x31 + 0x58
Remarks：
1 If the fingerprint ID in the command is wrong, module will respond as
parameter error:
0x4D + 0x58 + 0x30 + 0x02 + 0x50 + 0x35 + 0x5C
8) Upload Fingerprint Template
Description：Upload fingerprint template with the designated ID
Length：3 bytes
Format：Command code 0x52 + high byte of the to-be-uploaded fingerprint ID + low

byte of the to-be-uploaded fingerprint ID.
Readings:
1 HOST send a command to upload a fingerprint to the position for ID 0:
0x4D + 0x58 + 0x10 + 0x03 + 0x52 + 0x00 + 0x00 + 0x0A
0xD7
3 Module send the first data packet
4 HOST will respond as Rx correct 0x4D + 0x58 + 0x30 + 0x01 + 0x01 + 0xD7
5 Module send the second data packet
Remarks：
1 If the fingerprint ID in the command is wrong, module will respond as
parameter error:0x4D + 0x58 + 0x30 + 0x02 + 0x52 + 0x35 + 0x5E
9) Read ID Number
Description：Read module ID number
Length：1 byte
Format：Command code 0x60
Example：
1 HOST send a command to read Module ID number:
0x4D + 0x58 + 0x10 + 0x01 + 0x60 + 0x16
0xD7
3 Module will respond by 24-byte ID number after executing the command:
0x4D + 0x58 + 0x30 + 0x19 + 0x60 + ……24-byte ID number…… + check sum
Remarks：
1 ID number is set by manufacturer. User can read ID number only. Each module has
its own ID number. User can tell different module by reading ID number.
10) Read User Flash
Description：Read the content of the designated address in user flash in the module
Length：4 bytes

Format：Command code 0x62 + read high bytes of the address + read low bytes of
the address + read the number
Readings：
1 HOST send command to read 10 data starting from ADD 0 in user flash:
SM630 USER MANUAL All Rights Reserved
Page 22 of 29
0x4D + 0x58 + 0x10 + 0x04 + 0x62 + 0x00 + 0x00 + 0x0A + 0x25
0xD7
3 Module will respond by the data it read:
0x4D + 0x58 + 0x30 + number of data read + 0x62 + ……data read…… + check
sum
Remarks：
1 The memory is 64K bytes in user flash (ADD 1~0xFFFF). Maximum 128Byte
data can be read at one time.
11) Write User Flash
Description：Write data in the designated address in user Flash
Length：N+4 bytes
Format：Command code 0x64 + high bytes of the address where data to be written
+ low bytes of the address where data to be written + number of data to be written
+ ……N bytes of data to be written……
Readings:
1 HOST send a command to write 2 Byte data in to the ADD 0 in user Flash
0x4D + 0x58 + 0x10 + 0x06 + 0x64 + 0x00 + 0x00 + 0x02 + 0x00 + 0x00 +
0x21
0xD7
3 Module will respond after executing the command:
0x4D + 0x58 + 0x30 + 0x02 + 0x64 + 0x31 + 0x6C
Remarks：
1 The memory is 64K bytes in user flash. Maximum 128Byte data can be written
at one time.

CHAPTER 6
CONCLUSION:
In this study, the given implementation was an effort to understand how fingerprint recognition is used as a
form of biometric to recognize identities of human beings. It includes all the stages like (image
enhancement, histogram equalization, FFT, image segmentation image binarization, block direction
estimation ROI extraction, final minutiae extraction, minutiae alignment, minutiae match) from minutiae
extraction from fingerprints to minutiae matching which generates a match values. There are many
techniques which are used in the
intermediate stages of processing. It has relatively low percentage of verification rate as compared to other
forms of biometric identification indicates that the algorithm used is not very robust and is vulnerable to
effects like scaling and elastic deformations. Various new
techniques and algorithm have been found out which give better results. Also a major challenge in
fingerprint recognition lies in the pre processing of the bad quality of fingerprint images which also add to
the low percentage of verification.
Nowadays, a PIN code or a password is being used for the purposes of an authentication, which is the
weakest point of the whole system. Biometry offers one reasonable solution. Biometry should be used
instead of passwords and PIN codes. A user will be authenticated by his/her biometric attributes and he/she
will be either confirmed or refused. The confirmation or refusal depends on the acceptance of his/her
biometric attributes.
But the PIN and password replacement is not the only benefit of biometry. More might be got. Present
biometric technology is not advanced enough to be used for the cryptographic purposes, because it is very
difficult to detect and extract always the same or nearly the same features. The features are changing with
growth and age. Hence some rough rasterization (to avoid the position change of some feature) and subsets
computation (to ensure the repeatability of some part of the features) is necessary.
Where to go on in the future? It is obvious that biometric systems will govern the security domain in future
electronic world. The identification speed and accuracy will be the crucial factors. Therefore, the algorithms
may be optimized so that they can satisfy the strict conditions they will be exposed to during the regular
service. The next possibility is to implement these algorithms under a smart card operation system and
perform the fingerprint comparison directly at the smart card. It would increase the security and due to the
impossibility of an attack of the communication among the computer, fingerprint scanner and smart card
reader.
Reliable personal recognition is critical to many business processes. Biometrics refers to automatic
recognition of an individual based on her behavioral and/or physiological characteristics. The conventional
knowledge-based and token-based methods do not really provide positive personal recognition because they
rely on surrogate representations of the person’s identity (e.g., exclusive knowledge or possession). It is,
thus, obvious that any system assuring reliable personal recognition must necessarily involve a biometric
component. This is not, however, to state that biometrics alone can deliver reliable personal recognition
component. In fact, a sound system design will often entail incorporation of many biometric and non-
biometric components (building blocks) to provide reliable personal recognition.

Biometric-based systems also have some limitations that may have adverse implications for the security of a
system. While some of the limitations of biometrics can be overcome with the evolution of biometric
technology and a careful system design, it is important to understand that foolproof personal recognition
systems simply do not exist and perhaps, never will. Security is a risk management strategy that identifies,
controls, eliminates, or minimizes uncertain events that may adversely affect system resources and
information assets. The security level of a system depends on the requirements (threat model) of an
application and the cost-benefit analysis. In our opinion, properly implemented biometric systems are
effective deterrents to perpetrators. There are a number of privacy concerns raised about the use of
biometrics. A sound trade-off between security and privacy may be necessary; collective
accountability/acceptability standards can only be enforced through common legislation. Biometrics
provides tools to enforce accountable logs of system transactions and to protect an individual’s right to
privacy.
As biometric technology matures, there will be an increasing interaction among the market,
technology, and the applications. This interaction will be influenced by the added value of the
technology, user acceptance, and the credibility of the service provider. It is too early to predict where and
how biometric technology would evolve and get embedded in which applications. But it is certain that
biometric-based recognition will have a profound influence on the way we conduct our daily business.

CHAPTER 7
REFERENCES:
[1] Ravi Bhushan Tiwari & Sanjay Sharma, "Applications on Microelectronics and Computer
Engineering" International Symposium on Signal Processing and its Applications (ISSPA)), Kuala Lumpur.
Malaysia, I3 - I6 August, 2001. Australia Vol-2, PP-280-290.
[2] Anil K. Jain, Arun Ross & Salil Prabhakar, ” Video-Based Biometrics" Appeared in IEEE
Transactions on Circuits and Systems for Video Technology, Special Issue on Image, Vol. 14, No. 1, January
2004.
[3] M.L. Gavrilova, " Human Interface",International Conf. on Multimedia and Expo (ICMA) Vol.3,
July,2003 PP-241-244.
[4] Filip Orság & Martin Drahanský,International Conf. on Pattern Recognition
(ICPR),Vol.2, September,2000, PP 937-940.
[5] Emin Martinian, Sergey Yekhanin & Jonathan S. Yedidia, International Symposium on
biometrics, Center for Unified Biometrics and Sensors (CUBS), University at Buffalo,New York,USA.,vol-5,aug 2004.
[6] Kresimir Delac, Mislav Grgic, 46th International Symposium Electronics in Marine, ELMAR-2004, 16-
18 June 2004, Zadar, Croatia,vol.2,pp 243-253.
[7] Anil K. Jain, Lin Hong & Sharath Pankanti, Communications of the ACM,Vol.43
February, 2000 pp 91-98.
[8]Siddhesh Angle, Reema Bhagtani & Hemali Chheda, Department of Biomedical
Engineering, Thadomal Shahani Engineering College, T.P.S III, Bandra, Mumbai-50,vol.1,sept 2006.
[9] Erdem Yoruk, Helin Dutagaci & Bulent Sankur, Electrical and Electronic Engineering
Department, Boğaziçi University, Bebek, İstanbul, Turkey.vol.6, January 2006.
[10] Julian Ashbourm, IEE Colloquium on Image Processing for Biometric Measurement, April,1994,
pp-5/1-5/6.
[11] Syuichi Yasuoka, Yousun Karig, Ken'ichi Morooka & Hiroshi Nagahashi, 2004 IEEE
International Conference on Systems, Man and Cybernetics,vol-1,2004.

[12] Juyang Weng and Wey-Shiuan Hwang[12], "hierarchy discrimination regression", Asian
Conference on Computer Vision (ACCV) ,Vol.3,January, 2000 , pp 426-431.
[13] Michael Goh Kah Ong, Tee Connie, Andrew Teoh Beng Jin, David Ngo Chek Ling,
"linear discriminate analysis", IEEE Trans. On Circuits and Systems for
VideoTechnology,Vol.14 ,January,2004, pp95-101.
[14] Karthik Nandakumar and Anil K. Jain, Pattern Recognition symposium,
New Delhi ,Vol.38,January2005 ,pp-2270-2285.
[15] Ram Meshulam, Shulamit Reches, Aner Yarden and Sarit Kraus, International Joint
Conference on Autonomous Agents and Multiagent Systems (AAMAS) ,Vol.8,May,2006,pp-1095-1097.
[16] Luisa Riccardi, Bruno Peticone and Mario Savastano, Proceedings of Systems, Man and
Cybernetics (SMC) Information Assurance Workshop,Vol.5,June,2005,pp-79-83.
[17] Sharath Chikkerur, Sharath Pankanti, Nalini Ratha and Ruud Bolle,
IEEE Workshops on Application of Computer Vision (WACV),Vol.,January,2005,pp:111-116.
[18] Tami R. Randolph and Mark J. T. Smith[18],International Conference on Acoustics, Speech
and Signal Processing (ICASSP),Vol.3,May,2001,pp:1561-1564.

biometrics

Empfohlen

Empfohlen

Weitere ähnliche Inhalte

Was ist angesagt?

Was ist angesagt? (20)

Andere mochten auch

Andere mochten auch (9)

Ähnlich wie biometrics

Ähnlich wie biometrics (20)

biometrics