biometrics.doc

9
BIOINFORMATICS (BIOMATRICS IN SECURITY) Mr. ATUL.A. PADGHAN. Mr. SATISH .A. TANPURE [email protected] [email protected] Anuradha Engineering College, Chikhli Under Graduate Students (3rd Year) Electronic and Telecommunication Engineering ABSTRACT Authentication and security have been major issues right from the beginning of the computer age. The old method of using password for claiming access to a particular system is having many drawbacks such that this system merely tests that the password is correct not if the person using the password authorized to use it. Moreover the password is difficult to remember if one wants them not to be guessed easily. One of the emerging and efficient techniques for implementing security is BIOMETRICS. Using this technique one can definitely assure that he or she is the correct person. Biometrics is the science of measuring physical and behavioral characteristics that are unique to each individual. Biometrics technology verifies that an individual is knows who he or she claims to be common physical. Biometrics are fingerprints facial characteristics hand or palm geometry, retina, iris etc behavioral characteristics are signature voice keystroke etc. Out of these retinas scanning gives more accuracy for identification .An alteration solution is multi model identification system the smartcard and financial service industries are on the verge of adopting biometrics in a big way. The underlying assumption is that biometric Ids are unmatched for security –you cannot forge or presumably steal someone’s body parts. Keeping this trend in view we may soon be feeding biological information about ourselves into anever-expanding array of computerized bankingfiles credit card registries and election commission files."A biometric is a unique, measurable characteristic or trait of a human being for automatically recognizing or verifying identity." Figure: How a biometric system works

description

biometrics

Transcript of biometrics.doc

Page 1: biometrics.doc

BIOINFORMATICS (BIOMATRICS IN SECURITY)

Mr. ATUL.A. PADGHAN. Mr. SATISH .A. [email protected] [email protected]

Anuradha Engineering College, Chikhli Under Graduate Students (3rd Year) Electronic and Telecommunication Engineering

ABSTRACT

Authentication and security have been majorissues right from the beginning of the computerage. The old method of using password forclaiming access to a particular system is havingmany drawbacks such that this system merely tests that the password is correct not if the person using the password authorized to use it. Moreover the password is difficult to remember if one wants them not to be guessed easily. One of the emerging and efficient techniques for implementing security is BIOMETRICS. Using this technique one can definitely assure that he or she is the correct person. Biometrics is the science of measuring physical and behavioral characteristics that are unique to each individual. Biometrics technology verifies that an individual is knows who he or she claims to be common physical. Biometrics are fingerprints facial characteristics hand or palm geometry, retina, iris etc behavioral characteristics are signature voice keystroke etc. Out of these retinas scanning gives more accuracy for identification .An alteration solution is multi model identification system the smartcard and financial service industries are on the verge of adopting biometrics in a big way.

The underlying assumption is that biometric Ids are unmatched for security –you cannot forge orpresumably steal someone’s body parts. Keeping this trend in view we may soon be feeding biological information about ourselves into anever-expanding array of computerized bankingfiles credit card registries and election commission

files."A biometric is a unique, measurablecharacteristic or trait of a human being forautomatically recognizing or verifying identity."

Figure: How a biometric system works

DEFINITIONBiometrics can be used for identification andverification of different things about humanbeings.

Page 2: biometrics.doc

Identification a.k.a recognition is one-to-manycomparing process for a biometric sample or acode derivate from it against all of the knownbiometric reference templates on file. If theacquired sample matches a template storedwithin error marginal the identity of the enrolleeis also matched to that of the previously storedreference. The stored identity information reallyshould not reveal the physical identity of theowner of the biometric, but instead a role whichauthorizes the use of service or access.Verification is process of comparing asubmitted biometric sample against singlebiometric reference of a single enrollee whoseidentity or role is being claimed. The referencetemplate doesn't have to reside in large database but can be carried with oneself within a smart card or other security device. If the verificationprocess is well designed the biometric information is not revealed to the system, only the result: match or non-match is confirmed. All biometric identification or authentication technologies operate using the following four stage process.

BIOMETRIC

Biometric systems come in many shapes andsizes. This can range from distinct hardware,software to complete systems. All biometricsystems have the principles of capture, extractionand comparison and matching in common. Different biometrics, measures or traits of human body focus on very different features.Only thing common among them is that they areconsidered unique.

EYEBiometrics which analyze the eye are generallythought to offer the highest levels of accuracy.They can be divided in two specific technologies: examination of iris and retinapatterns. As internal parts of human eye are very well protected the sight being the most important sensor, the biometric data is also safe and immune to degradation in normal life on thecontrary to more external parts like fingertips. Inmedical science examination of the eye is usedas one indication that could reveal the certainillnesses and for example the users excessiveusage of drugs and alcohol. This is informationthe user does not necessarily want to reveal tothe operator of the scanning device. Accordingto the equipment manufacturers, they concentrate into extracting the unique pattern from the eye, and not any other information, thus ensuring the privacy of user. Still, as the analysis of the eye information is done in software new features can and could be incorporated in the software without notice.

IRIS

It has been known for seven decades that thepattern of blood vessels that emanate from theoptic nerve and disperse throughout the retinapresents an unparalleled source of biometricinformation. Since no two retinas are the same -even in identical twins - an individual can be distinguished from all others based on the vascular pattern observed.The iris is a protected internal organ of the eye,behind the cornea and the aqueous humor.

Page 3: biometrics.doc

Visually examined iris is the colored ring oftextured tissue that surrounds the pupil of theeye. Each iris is a unique structure, featuring acomplex system which is stable and unchangingthroughout life. When the information density ofiris patterns analyzed is roughly 3.4 bits persquare millimeter and complexity has about 266degrees of freedom.

The iris is closely connected to the human brainand is said to be one of the first parts of the body to decay after death. This makes recreation or use of a dead eye for fraudulent purposes very difficult. Additional tests that can be used against eye replicas can include testing the natural papillary motion and unique refractions to different infrared light sources.

Picture 2: Visualization of iris scan andextracted "IrisCode"Picture (C) IriScan, Inc.The image of iris is captured with a black andwhite video camera in a well lit environment.

The pattern is extracted after elastic deformations, such as papillary dilation andconstriction, are reversed mathematically whichis possible after localizing the inner and outerboundaries of iris. After pseudo polar coordinatemapping and using method called complexvalued 2D Gabber wavelets a bit stream,typically total 256 bytes of information, isobtained. The amount and uniqueness ofextracted information make the False Acceptprobability lowest of all known biometrics. Thescanning can be made from the distance of fewmeters so the user does not feel the processintrusive.FACEFace recognition technologies analyze the unique shape, pattern and positioning of facial features. The face is natural biometric because it is a key component in the way we humans remember and recognize each other. Face recognition is very complex technology and largely software based. Facial recognition systems are built on computer programs that analyze images of human faces for the purpose of identifying them. The programs take a facial image, measure characteristics such as the distance between the eyes, the length ofthe nose, and angle of the jaw, and create aunique file called "template." Using templates,the software then compares that image withanother image and produces a score thatmeasures how similar the images are to eachother. Typical sources of images for use in facialrecognition include video camera signals andpre-existing photos such as those in driver'slicense databases. Artificial intelligence is used

Page 4: biometrics.doc

to simulate human interpretation of faces. Theproblem with human face is that people dochange over time; wrinkles, beard, glasses andposition of the head can affect the performanceconsiderably. To increase the accuracy and adapt to these changes some kind of machine learning has to be implemented.

There are essentially two methods of capture:using video or thermal imaging. Video is morecommon as standard video cameras can be used. The precise position and angle of the head and surrounding lightning conditions may affect the system's performance. The complete facial image is usually captured and a number of points on the face can then be mapped, position of the eyes, mouth and nostrils as a example. More advanced technologies make three-dimensional map of the face which multiplies the possible measurements that can be made. Thermal imaging has better accuracy as it uses facial temperature variations caused by vein structure as the distinguishing trait. As the heat pattern is emitted from the faceitself without source of external radiation thesesystems can capture images despite the lightingconditions, even in the dark. The drawback is

cost, thermal cameras are significantly moreexpensive than standard video. [15, 16]One-to-one verification is mainly used with thismethod. Certain new systems have announcedthe possibility to one-to-many identification,even real time from live video feed. An exampleapplication of using face biometric could bestrict file access control: the video stream fromcamera attached to monitor is monitored byprogram which ensures that the legitimate user'sface is on the sight all the time when classifiedinformation is manipulated onscreen. If the userturns away or goes away from the screen thesecret files are hidden from the screen.

FINGERPRINTFingerprint scanning a.k.a finger scanning is oneof the most commercially successful biometrictechnologies today. [16] It is widely acceptedthat no fingers have identical prints, even fromthe same person or identical twins. Systematicclassification of fingerprints started in the 1800'sand is developed further trough extensive use inforensic societies. The technology has got fairlypositive user response in the enrolled pilotprojects, while drawbacks and disappointmentshave occurred trough the years. Taking onesfingerprints is often associated in the waycriminals are treated. Also the used systems have not always shown even nearly the idealperformances which have been reached in clean

Page 5: biometrics.doc

and sterile laboratory environment. Traditionalfinger scanning technique is analysis of smallunique marks of the finger image known asminutiae. Minutiae points such as finger imageridge endings or bifurcations, branches made byridges. The relative position of minutiae is usedfor comparison, and according to empiricalstudies, two individuals will not have eight ormore common minutiae. A typical live-scanfingerprint will contain 30-40 minutiae. Othersystems analyze tiny sweat pores on the fingerwhich, in the same way as minutiae, are uniquely positioned. Finger scanning is not immune to environmental disturbance. As the image is captured when the finger is touching the scanner device it is possible that dirt, condition of the skin, the pressure and alignment of the finger all affect the quality of fingerprint. This has appeared to be a problem with the introduction of the system; users had to wipe and clean their fingers each time before scanning their finger if they did not want to be falsely rejected.

Picture 3: Digitized fingerprint image withthe minute points extracted

HAND GEOMETRYWhen measuring hand geometry biometrics,three-dimensional image of the hand is taken and the shape and length of fingers and knuckles are measured. Hand geometry has been in use for many years in various applications, predominantly for access control.The technology does not achieve the highestlevels of accuracy but it is convenient and fast touse. On the capture process a user places a hand on the reader, aligning fingers with specially positioned guides. Cameras, positioned on above and on the side of hand capture images from which measurements are taken at selected points. As the hand geometry is not found to be as unique as for example fingerprints or eye scans it cannot be used as accurate identification. Because of its user-friendliness it is well suited to user id verification.

Picture 4: Hand with biometric measurementsvisualizedImage (C) Michigan State University

FINGER GEOMETRYFinger geometry biometric is very closely relatedto hand geometry. The use of just one or two fingers means more robustness, smaller devicesand even higher throughput. Two variations of capture processes are used, first being similar to hand geometry presented above. The second technique requires the user to insert a finger into a tunnel so that threedimensional measurements of the finger can be made.

PALM

Page 6: biometrics.doc

Palm biometrics is close to finger scanning and in particular AFIS technology. Ridges, valleys and other minutiae data are found on the palm as with finger images. Main interest in palm biometrics industry is law enforcement as latent images - "palm prints" - found from the crime scenes are equally useful as latent fingerprints. Certain vendors are also looking at the access control market and hope to follow the footsteps of finger scanning.

FUTURE BIOMETRICSA system that analyses the chemical make-up ofbody odor is currently in development. In thissystem sensors are capable of capturing bodyodor from non-intrusive parts of the body suchas the back of the hand. Each unique humansmell consists of different amount of volatiles.These are extracted by the system and converted into a biometric template. All testing and fastest possible analysis of the human DNA takes at least 10 minutes to complete and it needs human assistance. Thus, it cannot be considered as biometric technology in its sense of being fast and automatic. Additionally current DNA capture mechanisms, taking a blood sample or a test swab inside of the mouth, are extremely intrusive compared to other biometric systems. Apart from these problems DNA, as a concept, has a lot of potential.Ear shape biometrics research is based on lawenforcement needs to collect ear markings andshape information from crime scenes. It hassome potential in some access control applications in similar use as hand geometry.There are not excessive research activities going on with the subject.

UNDERSTANDING MULTIMODALBIOMETRIC SYSTEMS

A multimodal biometric system uses multipleapplications to capture different types ofbiometrics.

This allows the integration of two or more typesof biometric recognition and verification systemsin order to meet stringent performancerequirements. Multimodal system could be, forinstance, a combination of fingerprint verification, face recognition, voice verificationand smart-card or any other combination ofbiometrics. This enhanced structure takes advantage of the proficiency of each individual biometric and can be used to overcome some of the limitations of a single biometric. A multimodal system can combine any number of independent biometrics and overcome some of the limitations presented by using just one biometric as your verification tool.

APPLICATIONSThunder Bay Becomes First CanadianAirport to Use Facial Recognition1] Thunder Bay International Airport is the firstCanadian airport to deploy facial-recognitiontechnology.2] A second use of the technology was at the2001 Super Bowl in Tampa, where pictures weretaken of every attendee as they entered thestadium through the turnstiles and comparedagainst a database of some undisclosed kind.3] In America and Japan, the main applicationshave been entry control, ATMs, and Government

Page 7: biometrics.doc

program’s. In Britain, The Nationwide BuildingSociety introduced iris recognition within itscash dispensing machines (in lieu of PINnumbers) in 1998.

Fingerprint based recognitionThe figure to the beneath shows a door controlsystem, where the user needs to prove hisirdentity before entering the premises of thebuilding, this is done by authenticating hisfingerprints on the device shown This figure tothe above shows us what is called as smart cardwhich can be authenticated by fingerprints holding the finger on the sensor.BiosmartcardBioSmartCard - the biometric solution toSmartcard owner authentication. A Smartcardcan be used by anyone. BioSmartCard can onlybe used by authorized user Smartcards arecredit-card sized cards with processing chipsembedded into them. BioSmartCards rely on theunique characteristics of a person's fingerprint.

To register, the owner's fingerprint is digitally embedded into the card. Only your fingerprint can unlock your card. Now that's Really SMART!E-commerceApplicatinosE-commerce developers are exploring the use ofbiometrics and smart cards to more accuratelyverify a trading party’s identity. For example,many banks are interested in this combination tobetter authenticate costumers and ensure norepudiation of online banking trading, and parchasing transactions.CONCLUSIONSThe security field uses three different type ofauthentication Something you know-a password, PIN,or piece of personal information ( suchas your mother’s maiden name ); Something you have-a card key smartcard, or token (like a securID card );and/or Something you are-a biometric.Of these, a biometric is the most secure andconvenient authentication tool. It can’t beborrowed, stolen or forgotten and forgingone is practically impossible.REFERENCE[1] URL http://www.biometrics.org[2] URL http://www.ibia.org[3[ URL http://www.zdnet.com[4] URL http://www.iriscan.com