Abstract

Biometrics is automated methods for identifying a person or verifying the identity of a person based on a physiological or behavioral characteristic has the capability to reliably distinguish between an authorized person and an imposter. Since biometric characteristics are distinctive, cannot be forgotten or lost, and the person to be authenticated needs to be physically present at the point of identification, biometrics is inherently more reliable and more capable than traditional knowledge-based and token-based techniques. Using biometrics for identifying human beings offers some unique advantages. Biometrics can be used to identify you as you. Biometrics holds the promise of fast, easy-to-use, accurate, reliable, and less expensive authentication for a variety of applications.

CHAPTER ONE

Introduction

The need for reliable user authentication techniques has increased in the wake of heightened concerns about security and rapid advancements in networking, communications and mobility. Biometrics, described as the science of recognizing an individual based on his or her legitimate method for determining an individual’s identity (Anil et al., 2005). Biometric authentication or simply biometrics refers to establishing identity based on the physiological and behavioral characteristics (also known as traits or identifiers) of an individual such as face, fingerprints, hand geometry, iris, keystroke, signature, voice, etc. Biometrics systems offer several advantages over traditional authentications schemes. They are inherently more reliable than password – based authentication as biometric traits cannot be lost or forgotten; biometric traits are difficult to copy, share and distribute; and they require the person being authenticated to be present at the time and point of authentication. Thus, a biometrics – based authentication scheme is a powerful alternative to traditional authentication schemes. A number of biometric characteristics have been in use for different applications (Anil et al., 2005).

Biometrics is the measurement and statistical analysis of people's unique physical and behavioral characteristics. The technology is mainly used for identification and access control or for identifying individuals who are under surveillance. The basic premise of biometric authentication is that every person can be accurately identified by their intrinsic physical or behavioral traits. The term biometrics is derived from the Greek words bio, meaning life, and metric, which means to measure. A biometric feature can be defined as a physiological (face, fingerprints, iris, etc.) or behavioral (gait, voice, signature, etc.) attribute of a human being that can discriminate one individual from another. Nowadays, the great interest for biometric recognition systems can be justified due to increased demand for security. The goal of a biometric based recognition system is either automatic identification or verification of identities, given input data comprising images, speech or videos. Unlike the traditional ways, such as password, biometric traits have some advantages: they cannot be stolen (although spoof attacks may exist to tamper the biometric system), lost or forget. However, to be reliable, biometric traits should be unique and over time. Some other criteria should be met such as user convenience and acceptability (mainly due to privacy reasons). Biometric recognition is usually performed by extracting a biometric template in query from the input device and compare it against some enrolled biometric templates. The comparison is processed using of the two modes: a) verification (or authentication) and b) identification (or recognition). Verification is a one-to-one process where the query face is compared against the user claiming his genuine identity to verify his claimed ID. The output is binary, either accept or reject, based on a matching procedure. We should note here that a biometric authentication technology may be used in conjunction with traditional authentication methods such as password, passports, PIN, smart cards, access tokens, etc., employed as second factor authentication. Identification is one-to-many process where the query is compared against each enrolled biometric template (multiple templates) from the database to search for the identity of the query. Identification is a bit more complex than verification as the system serves as both identifier and authenticator. A biometric based recognition system needs an enrollment procedure which allows the registration of persons in a biometric database that may be later used for identification or verification. The acquired initial data may undergo some pre-processing steps depending on the biometric modality. For instance, in the case of images, histogram equalization may help when the image suffers from illumination imbalance. For audio data, voice separation from the background may be also a pre-processing step. Biometric features are constructed by feature extraction step resulting a biometric template, further stored in the database. After a person is enrolled, the person’s biometrics are scanned and matched against the enrolled biometric templates. Matching is a complex pattern recognition problem between the enrolled samples and the test one.

Accurately identifying a person is the most critical process in biometrics-based security applications, and issued for recognizing and determining an individual identity based on his or her physical or behavioral characteristics including finger-prints and face. Biometric based identification system has been widely utilized in many security applications. Biometrics is a marvelous technology that is lower in cost, faster and more accurate. Over the last couple of decade, biometric based recognition systems have been widely investigated, a number of biometric features have been studied tested and successfully deployed in application including information security, law enforcement, surveillance, forensics, smart cards, access control, time/place control points and computer networks.

No single biometrics is expected to effectively satisfy the needs of all identification (authentication) applications. A number of biometrics have been proposed, researched, and evaluated for identification (authentication) applications. Each biometrics has its strengths and limitations; and accordingly, each biometric appeals to a particular identification (authentication) application.

CHAPTER TWO

LITERATURE REVIEW

2.0       INTRODUCTION

Research on biometric methods has gained renewed attention in recent years brought on by an increase in security concerns. The recent world attitude towards terrorism has influenced people and their governments to take action and be more proactive in security issues. This need for security also extends to the need for individuals to protect, among other things, their working environments, homes, personal possessions and assets, many biometric techniques have been developed and are being improved with the most successful being applied in everyday law enforcement and security applications.

Biometric methods include several-of-the-art techniques for almost security authentication. Advances in sensor technology and an increasing demand for biometrics are driving a burgeoning a biometric industry to develop new technologies. As commercial incentives increase many new technologies for person identification are being developed like facial biometric

2.1       BIOMETRIC SECURITY

The term “Biometrics” is derived from the Greek words, “bio” (Life) and “metrics” (to measure) Rood and Hornak, 2008. Automated biometric systems have only become available over the last few decades. Due to the significant advances in the field of computer and image processing, although biometric technology seems to belong in the twenty first century, the history of biometrics goes back thousands of years. The ancient Egyptians and the Chinese played a large role in biometric history.

Today, the focus on using biometric face recognition, recognition and identifying characteristics to stop terrorism and improve security measures.

2.2       THE EVOLUTION OF BIOMETRICS TECHNOLOGIES

The word biometrics comes from the Greeks. The combination of the words bio meaning life and metric meaning to measure marks makes biometrics. It refers to the automatic identification of a person based on his or physiological or behavioral characteristics. Various efforts and contributions from several individuals and groups resulted in the present day achievements in biometrics technology.

2.2.1    FINGERPRINT RECOGNITION

This section provides a brief history on biometric security and recognition. During 1858, the first recorded systematic capture of hand and finger imaged for identification purposes was used by Sir William Herschal, Civil service of India, who recorded a handprint on the back of a contract for each worker to distinguish employees (Komarinski, 2004). During 1870, Alphonse Bertillon developed a method of identifying individuals based on detailed records of their body measurements, physical descriptions and photographs. This method was termed as “Bertillonage” or authropometrics and the usage was aborted in 1903 when it was discovered that some people share same measurement and physical characteristics.

Sir Francis Galton, in 1892, developed a classification system for fingerprint recognition by using minutes characteristics that is being used by researchers and educationalists even today, Sir Edward Henry, during 1896, paved way to the success of fingerprint recognition by using Galton’s theory to identify prisoners by their fingerprint impressions. He devised a classification system that allowed thousands of fingerprints to be easily filed, searched and traced. He helped in the first establishment of fingerprint burea in the same year and his method gained worldwide acceptance for identification criminals

In 1880, in the October 28 issue of the British Scientific periodical Naature, Dr. Faulds was the first to publish a scientific account of the use of fingerprint as a means of identification. In addition to recognizing the importance of fingerprints, for identification, he devised a method of classification as well. Dr. Faulds is credited for the first fingerprint identification-based on alcohol bottle. The method of classification proposed by Dr. Faulds is called Henry classification system and is based on patterns such as loops and whorls, which is still used today to organize fingerprints and files. Continuing the work of Dr. Faulds, Sir. Williams Herschel and Sir. Francis Halton established the individuality and performance of fingerprints. This book, “fingerprints” from 1892, contains the first fingerprints classification system containing three basic pattern types: loop, arch, and whorl. The system was based on the distribution of the pattern types on the ten fingers. E.g. LLAWL LWWLL. The system worked, but was easier to administer, shifted from Bertillonage to fingerprinting. During the 1890’s, Sir Edward Henry, a British official in Bengal believed that a fingerprinting system was the solution to his problem of verifying the identity of criminals he studied. The works of Sir Galton and Sir Henry and proved that they could be used to produce 1,024 primary classification, which was instituted in Bengal in 1897. The system is described in his book, “Classification and uses of fingerprints”. In June 1897, Bertillonage was replaced and the Henry classification system became the official method of identifying criminals. In British India, in 1901, Sir Henry established the first fingerprint files in London subsequently, within the next 25 years, the Henry Classification system was adopted as the universally accepted method of personal identification by law enforcement agencies. Throughout the world, it is still in use, though several variants of the Henry classification system. In 1903, the Henry classification system was used to differentiate two prisoners who were identical twins. The Bertillon system was not able to make out the difference between identical twins and thus Henry Classification system was further strengthened. Juan Vucstich also worked on a classification system based on the findings of Sir Galton and years of experience in fingerprint forensics. His system was published in his book. “DactiloscopiaComparanda” (Comparative fingerprinting). In 1904, His system, “the vucstich system”, is still used in most Spanish-speaking countries. During the first 25 years of the 1900’s, more and more agencies in the U.S. started to send copies of their fingerprint cards to the National Bureau of criminal identification. These files formed the nucleus of the FBI fingerprint files when the identification Division of the FBI was established in 1924.

The first country to adopt a national computerized form of fingerprint imaging was Australia in 1956, which implemented fingerprint imaging technology into its law enforcement system. With this introduction of AFIS technology (Automated Fingerprint Identification System), the files were split into computerized criminal files and manually maintained civil files. Many files were found to be duplicated and the records actually represented somewhere between 25 and 30 million criminals and an unknown number of individuals in the civil files.

2.2.2    FINGERPRINT FEATURES

While considering the various features involved with fingerprint recognition, Galton introduced level two features by defining minutiae points as either ridge bifurcations on a local ridge. He also developed a probabilistic model using minutiae points to qualify the uniqueness of fingerprints (Galton, 1965). Although Galton discovered that sweat pores can also be observed on the ridges, no method was proposed to utilize pores for identification. In 1912, Locard introduced the sciences of poroscopy. The comparison of sweat pores for the purpose of personal identification.  In Locard stated that like the ridge characteristics, the pores are also permanent, immutable, and unique, and are useful for establishing the identity, especially when a sufficient number of ridges are not available. Locard further studied the variation of sweat pores and proposed four criteria that can be used for the pores, the form of the pores, the position of the pores on the ridges and the number of frequency of the pores. It was observed that the number of pores along a centimeter of ridge varies from 9-18 or 23-45 pores per inch and 20 to 0 pores should be sufficient to determine the identity of a person.

2.2.3    FINGERPRINT SENSING TECHNOLOGY

There are many different sensing methods to obtain the ridge-and-valley pattern of finger skin or fingerprint (Xia and O’Gorman, 2003). Historically, in Law Enforcement applications, fingerprints were mainly acquired offsine. Nowadays, most commercial and forensic applications accepts live-scan digital images acquired by directly sensing the finger surfaces with a fingerprint sensor based on optical, solid-state, ultrasonic, and other imaging technologies. The earliest known images of fingerprints were impressions in clay and later in wax, starting in the late 19th century and throughout the 20th century; the acquisition of fingerprint images was mainly performed by using the “ink-technique). This kind of process is referred to as rolled offline fingerprint sensing, which is still being used in forensic applications and background checks of applicants for sensitive jobs.

Later, “Live-scan” sensors implemented earlier had the disadvantages that they were ill-suited for wet or fry fingers and had to be cleaned regularly to prevent greases and dirt from compromising the image quality. Rows et al, 2005. The past 15 years have envisaged tremendous development in the fingerprint sensing technology.

2.2.4    FINGERPRINT ACQUISITION METHODS

This section presents the various acquisition method used to obtain fingerprints of an individual.

• Optical: (Raul, 2007) 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 surface of the finger. The light reflected from the finger passes through the phosphor layer to an array of solid state pixels (a charge-coupled device), which captures a visual image of the fingerprint.
• Ultrasonic: Majid and Sased, 2005. Ultrasonic sensors make use of the principles of medical ultrasonography in order to create visual images of the fingerprint. Unlike optical imaging, ultrasonic sensors use very high frequency sound waves to penetrate the epidermal layer of skin. The sound waves are generated using piezoelectric transducers and reflected energy is also measured using piezoelectric materials. Since the dermal skin layer exhibits the same characteristics pattern of the fingerprint, the reflected wave measurements can be used to form an image of the fingerprints.
• Capacitances: (Setlak, 2005) capacitances sensors utilize the principles associated with capacitance to form fingerprint images. In this method of imaging, the sensor array pixels each act as one plate of a parallel-plate capacitor, the dermal layer (while is electrically conductive) acts as the other plate, and the non-conductive epidermal layer acts as a dielectric.
• Passive capacitance: (Setlak, 2005) A passive capacitance sensor uses the principle outlined above to form an image of the fingerprint patterns on the derma layer of skin. Each sensor pixel is used to measure the capacitance at that point of the array. The capacitances varies between the ridges and valleys of the fingerprint due to the fact that the volume between the dermal layer and sensing element in valleys contains an air gap. The dielectric constant of the epidermis and the area of the sensing element are known values. The measured capacitance values. The measured capacitance values are then used to distinguish between fingerprint ridges and valleys.

• Active Capacitance: (Setlak, 2005). Active capacitance sensors use a charging cycle to apply a voltage to the skin before measurement takes place. The application of voltage charges the effective capacitor. The effective field between the finger and sensor follows the pattern of the ridges. In the dermal skin layer, on the discharge cycle, the voltage across the dermal layer and sensing element is compared against a reference voltage in order to calculate. The distance values are then calculated mathematically, and used to form an image if the fingerprint.

2.3       FACIAL RECOGNITION

The most familiar biometric technique is facial recognition. Human beings use facial recognition all time to identify people. As a result, in the field of biometric, facial recognition is one of the most active areas of research. Application of this rsearch ranges from the design of system that recognizes active and changing facial images against a differed background. More advanced systems can recognize a particular individual in a videotape or a movie.

Facial recognition software refers to computer aided recognition of human face with objective of verifying facial recognition of the person to be identified. The other necessity is a database of similar picture of the individual with which the image can be compared with. Each human face is made in a unique combination of facial features such as measurements of jaw lines, distance between the two eyes, shape and length of the nose. Facial recognition algorithms use these parameters to create a precise face-print. The facial recognition compares this face-print with those saved in the database.

Owing to constant technology advancement, contemporary system based on 3D model using unique somewhat never changing facial features such as measurement of the bows and that of the eye socket on receiving an image. The newer facial recognition software creates unique code, assigning distinct number to each facial feature.

Facial recognition is one of the most current and familiar biome technology in the field of biometric. Facial revongnition is among the active and accurate method of security problem solving research made.

Some advances are frequently and have been fundamentally made on the application of this research which ranges from the design of system that recognizes actively and changing facial images against a different background.

Some facial recognition software algorithms identify faces by extracting features from an image of a subjects face. Other algorithms normalize a gallery of face images and then comes the face data only saving the data in the image that can be used for facial recognition. A probe image is then compared with the face that is identified.

Facial recognition requires a software which is refers to the computer aided recognition of human face whti objective of verifying facial recognition of the person to be identified and a data base of a similar picture of the individual of the person with which the image can be compared with.

In the year 2008, Smith Kelly introduced one of the earliest successful system that is based on template matching techniques. This is applied on a set of facial features providing a sort of compressed face representation.

In the year 2008, a new emaerging trend claimed to achieve imporved accuracies is the three diemsional face recognition which was introduced by William Mark. This techniques uses 3D sensors to capture information about the shape of the face. This information is then used to identify distinctive features on the surface of a face such as the contour of the eye socket, nose and chin. One of the advantage of this development is that it is not affected by changes in highly like other techniques. It can also identify a face from a range of viewing angles.

The facial recognition system have potential being applied by so many organizations and with favorable applaud. Like a January 2001, police in Tampa Bay, Florida used facial recognition software to search for potential criminals and terrorist in attendance of the event. 19 people with minor criminals were identified.

In the 2000 Mexican Presidential election, the government employed facial recognition software to prevent fraud. Some individuals had been registering to vote under several different names in an attempt to place multiple votes by comparing new facial images to those already in the vote database, authorities were able to reduce duplication.

2.3.1    FEATURES OF FACIAL RECOGNITION SYSTEM.

There are various features involved with facial recognition system.

• Face Recognition Technology: One element of imaging analysis that is rapidly improving is that of facial recognition. The greater the ability to match a series of points on a face related to the dimension and pixel count appropriate between the eyes will result in an increasing percentage success rate in facial identification.
• Face Recognition: Humans mostly use faces to recognize individuals. Recent advances in computing technology and capability now enables similar recognition automatically. Early face recognition algorithms used simple geometric models, bur the recognition process has now matured into a science of sophisticated mathematical representations and matching processes. Major developments have propelled face recognition technology into the spotlight. Face recognition can be used for both verification (one to one), and identification (one to many) applications.
• Face template: The heart of the facial recognition system is the Local Features Analysis (LFA) algorithm. This is the mathematical technique the system uses to encode faces. The system maps the face and creates a “template” as unique numerical ID for the face. Once the system has stored a template it can compare it to the thousands or millions of templates stored in the database, each template occupies only 2 -3 of data.
• Algorithm: The right algorithm will enable fast and accurate face localization for reliable detection of multiple faces in still images as well as in live video systems. This simultaneous multiple face processing and identification can happen in a single frame. The face needs to be detected in less than 0-1 seconds and then processed in less than 0.2 seconds. This rapid detection rate allows comparison of up to 100,000 faces per seconds, through the recorded frames generating the collection of the same subject and writing it to the database. In this way the enrolled feature templates are more reliable and the face recognition quality increases considerably over time.

2.4 Voice Recognition

Voice or speaker recognition uses vocal characteristics to identify individuals using a pass-phrase. Voice recognition can be affected by such environmental factors as background noise. Additionally it is unclear whether the technologies actually recognize the voice or just the pronunciation of the pass-phrase (password) used. This technology has been the focus of considerable efforts on the part of the telecommunications industry and NSA, which continue to work on improving reliability. A telephone or microphone can serve as a sensor, which makes it a relatively cheap and easily deployable technology.

2.5 Iris Scan

Iris scanning measures the iris pattern in the colored part of the eye, although the iris color has nothing to do with the biometric. Iris patterns are formed randomly. As a result, the iris patterns in your left and right eyes are different, and so are the iris patterns of identical twins. Iris scan templates are typically around 256 bytes. Iris scanning can be used quickly for both identification and verification applications because of its large number of degrees of freedom. Current pilot programs and applications include ATMs (“Eye-TMs”), grocery stores (for checking out), and the Charlotte/Douglas International Airport (physical access). During the Winter Olympics in Nagano, Japan, an iris scanning identification system controlled access to the rifles used in the biathlon.

2.6 Retinal Scan

Retinal scans measure the blood vessel patterns in the back of the eye. Retinal scan templates are typically 40 to 96 bytes. Because users perceive the technology to be somewhat intrusive, retinal scanning has not gained popularity with end-users. The device involves a light source shined into the eye of a user who must be standing very still within inches of the device. Because the retina can change with certain medical conditions, such as pregnancy, high blood pressure, and AIDS, this biometric might have the potential to reveal more information than just an individual’s identity.

2.7 Biometric Characteristic’s Requirements

Physical and Behavioral characteristics should meet some requirements in order to be used as biometrics methods. These requirements are either theoretical or practical. There are basically seven theoretical requirements which includes

• Universality: Each person should have biometric characteristics. There are mute people, people without fingers or with injured eyes. It is really difficult to get 100% coverage.
• Uniqueness: This means that no two persons should be the same in terms of the biometric characteristics. It will indicate how differently and uniquely the biometric system will be able to recognize each user among groups of users.
• Permanence: It is required for every single characteristic or trait which is recorded in the database of the system and needs to be constant for a certain period of time period. This means that the characteristics should be invariant with time.
• Collectability: This means that the characteristics must be measured quantitatively and obtaining the characteristics should be easy.
• Performance: This refers to the achievable identification/verification accuracy and the resources and working or environmental conditions needed to achieve an acceptable accuracy.
• Acceptability: It will choose fields in which biometric technologies are acceptable.
• Circumvention: It will decide how easily each characteristic and trait provided by the user can lead to failure during the verification process.

CHAPTER THREE

3.0 APPLICATIONS OF BIOMETRIC TECHNOLOGY

Biometric Applications Biometrics are an effective personal identifier because the characteristics measured are distinct to each person. Unlike other identification methods that use something a person has, such as an identification card to gain access to a building, or something a person knows, like a password or PIN to log on to a computer system, the bio-metric characteristics are integral to something a person is, since biometrics are tightly bound to an individual, they are more reliable, cannot be forgotten, and are less likely to be lost, stolen, or otherwise compromised

3.1 Novel Applications

As biometric technology matures, there will be an increasing interaction among the (biometric) market, (biometric) technology, and the (identification) applications. The emerging interaction is expected to be influenced by the added value of the technology, the sensitivities of the population, and the credibility of the service provider. It is too early to predict where, how, and which biometric technology would evolve and be mated with which applications. Applications like automating identification for more convenient travel, for transactions via e-commerce, etc. seem to be ready for commercialization, but perhaps, biometric technology could open up a whole new genre of futuristic hi-tech applications that were not foreseen before.

Take for instance, the application of content-based search of digital libraries and in particular, video. One of the tasks in content-based search involves ascription of sound-bytes to individuals (identities) depicted in the corresponding video segment. The association of the sound to identity is essentially a closed identification problem. What makes this problem interesting is the opportunity to exploit the context and clues offered from the vision-based processing (e.g., number of people in the video and lip movements) of the video. Voice-based clues could generate plausible hypotheses about identities of visual entities. From the visual input, the hypothesis could either be accepted or rejected depending on the coherency of the sound and vision based results. Or imagine, in a hi-tech mall, the features extracted from DNA of millions of cells shredded by the body of a passing individual (and a potential customer) would be instantly matched to determine the exact identity or a possible category of population.

That individual would then be treated exclusively depending upon his spending pattern. Perhaps, there would be data mining based on the biometric characteristics! Interesting scenarios might materialize as a number of civilian applications of identification are integrated based on a single or multiple biometric technologies.

3.2 CONCLUSION AND PERSPECTIVES

Biometric is a unique identity management approach that offers the combination of user convenience cost-effective provisioning and non-repudiated compliance audit for the system operator. Biometric-based authentication clearly has advantages over these mechanism, but there are also vulnerabilities that need to be applied universally, it may be a good choice for a given application, but unfeasible in another. Fingerprint and face system provide higher level of security, non-repudiated identification for internal control and regulatory compliance and increased user convenience and productivity without the costs associated with the physical credentials. A property design and implemented fingerprint biometric system is a viable way to accomplish all the objectives.

Biometric represents a wide range of new opportunities that can make necessary personal authentication and identification both more secure and convenient. On the other hand, the rise of biometric technologies might potentially compromise the individual’s rights to privacy as well as lead to increased registration. Consequently, successful implementation of biometrics in the future must utilize the opportunities of the new technology but at the same time respect the integrity of the individual.

REFERENCES

Anil K. Jain, Arun Ross, and Sharath Pankanti, “Biometrics: A Tool for Information Security”, IEEE Transactions on Information Forensics and Security, vol. 1, no. 2, pp 21-38, June 2005.

Anil. K.Jain, Arun Ross, Salil Prabhakar, “An introduction to biometric recognition”, IEEE Transactions on circuits and systems for video technology, vol. 14, no. 1,pp 67-80, Jan 2004.

D. Cunado, M. S. Nixon, and J. N. Carter, “Using gait as a biometric, via phase-weighted magnitude spectra,” in Lecture Notes in Computer Science 1206, Proceedings of Audio and Video- Biometric Person Authentication AVBPA’97, First International Conference, Crans-Montana, Switzerland, March 12-14 (J. Bigun, G. Chollet, and G. Borgefors, eds.), pp. 95-102, Springer-Verlag, Berlin, 1997.

D. Socolinsky, L. Wolff, J. Neuheisel, C. Eveland (2001), Illumination Invariant Face Recognition Using Thermal Infrared Imagery, Proc. of 2001 IEEE Conf. on Computer Vision and Pattern Recognition, 1: 527-534.

Gelb .A. and Julia .C. (2013) Identification for development: The Biometric Revolution. The Center for Global Development.

Francis G (2000) Impact of Artificial Gummy Fingers on Finger Print System, proc of SPIE, vol 4677, pg. 275-289.

J. G. Daugman, “High confidence visual recognition of persons by a test of statistical independence,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 15, No. 11,

pp. 1148-1161, 1993.

Jain, A.K; Ross, A. Arun (2008) Introduction to Biometrics Retrieved on August 2014 from www.springer.com

K. Delac, M. Grgic (Eds.) (2007), Face Recognition, I-Tech Education and Publishing, Vienna, Austria. [3] K. Delac, M. Grgic, M. S. Bartlett (Eds.) (2008), Recent Advances in Face Recognition, IN-TECH, Vienna, Austria.

Rood D.F and Hornk G.Y (2008), Biometrics: Personal Identification in Network Society, Kluwer Academic Publishers. Washington DC.

Setlek. G.J. (2005) Multimodal Biometric Authentication Methods Proc. MMUA Workshop on Multimodal User Authentication pg. 19-106, Santa Barbara, C.A.

T. Julian, L. A. Vontver, and D. Dumesic, Review of Obstetrics & Gynecology. Stanford, CT: Appleton and Lange, 1995.

Xia. K. and O’Gorman .M. (2003), Fingerprint Sensing Technology