[attachment=11629]
Fingerprint identification using biometrics
Abstract
What is biometrics identification?
 It is the process by which a person can be identified by his characteristics.
 The characteristic is scanned so that the computer can compare it to the data already stored in the database.
 Biometrics identification is more secure method of identifying a person , it can not be easily shared , traded or stolen by another.
Categories
 There are mainly two categories of biometrics identification –
 Physiological characteristics :- identified by physical traits of person.
E.g. Fingerprint , retinal scans , hand print scans.
 Behavioral characteristics :- identified with the things that can change with the environment.
E.g. Voice recognition , verifying signature.
history
 Possibly the most primary known instance of biometrics in practice was a form of finger printing being used in China in 14th century as reported by explorer Joao de Barros.
 Up until the late 1800’s identification largely relied upon “Photographic memory”.
 Bertillon developed a technique of multiple body measurements which later got named after him Bertillon-age.
Biometrics fingerprint identification
The science of fingerprint identification stands out among all other forensic sciences for many reasons as –
 Has served all governments worldwide to provide accurate identification of criminals.
 Establish the first forensic professional organization , IAI(International Association for Identification) in 1915.
 Worldwide , fingerprints harvested from crime “scenes lead to more suspect & generate more evidence in court than all other forensic techniques combined ”.
 It quickly & correctly identify two different people who look exactly alike.
Fingerprint matching
 Everyone is known to have unique , immutable fingerprints.
 A fingerprint is made up of a series of ridges and furrows on the surface of the finger.
 The uniqueness of a fingerprint can be determined by the pattern of ridges and furrows as well as the minutiae points .
 Minutiae points are local ridge characteristics that occur at either a ridge bifurcation or ridge ending.
 Fingerprint matching has two categories:- minutiae-based and correlation-based.
Fingerprint classification
 Fingerprint classification is a technique to assign a fingerprint into one of the several pre-specified types already established in the literature which can provide an indexing mechanism.
 To reduce the search time & computational complexity , it is desirable to classify these fingerprints in an accurate & consistent manner so that the input fingerprint is required to be matched only with a subset of the fingerprints in the database.
 To classify fingerprints an algorithm is used by which the fingerprints are classified into five classes , namely – whorl , right-loop , left-loop , arch ,tented-arch.
 The algorithm separates the no. of ridges present in 4 directions(0 deg , 45 deg , 90 deg, 135 deg)by filtering the central part of fingerprint with the bank of Gabor filters.
 This information is quantized to generate a Finger-Code which is used for classification.
Fingerprint enhancements
 A critical step in automatic fingerprint matching is to automatically & reliably extract minutiae from the input fingerprint images.
 The performance of a minutiae extraction algorithm relies heavily on the quality of the input fingerprint images.
 We have developed a fast fingerprint enhancement algorithm , which can adaptively improve clarity of ridge & furrow structure of input fingerprint images based on the estimated local ridge orientation & frequency.
Fingerprint types
 Latent Prints
 Patent Prints
 Plastic Prints
 Fingerprint capture & detection
Fingerprint detection
 The general structure of fingerprint scanner
 Advantages & disadvantages
 Acceptance
 Accuracy
 Ease of use
 Installation
 Training
 Uniqueness
 Security
 Acceptance
 Injury
 security
Fingerprint application
Biometrics iris recognition
 Iris recognition today combines technologies from several fields including , computer vision(CV) , pattern recognition , statistical interference , & optics . The goal of the technology is near-instant , highly accurate recognition of a person’s identity based on a digitally represented images of scanned eye.
 The tech. is based on the fact that no two iris patterns are alike.
 The iris is protected organ which makes identification possibilities life long.
 The iris can there for serve as a life long password which the person must never remember.
 Iris recognition system use small , high-quality cameras to capture a black & white high-resolution photograph of the iris.
 This technology is considered to be one of the safest , fastest , & most accurate , non invasive biometric technologies.
 They are used in passport , aviation security , access security , hospitals & national watch list.
 Iris recognition algorithm can be seen in more & more identification system relating to customs and immigration.
Iris recognition instruments
Advantages & disadvantages
 Highly protected
 Externally visible
 Variability
 Entropy
 Pre-natal morphogenesis
 Decidability index
 Image analysis & encoding time
 Changing pupil size confirms natural physiology
 Small target
 Moving target .. within another ..on yet another
 Located behind curved , wet , reflecting surface
 Obscured by eyelashes , lenses , reflections
 Partially occluded by eye leads often drooping
 Deforms non-elastically as pupil changes size
 Some -ve connotations
 Illumination should not be visible or bright
Future trends
 E-commerce
 Information security(info-sec)
 Authorization
 Building entry
 Automobile ignition
 Forensic application
 Computer network access
 Personal passwords