Presentation is loading. Please wait.

Presentation is loading. Please wait.

Modern Bio Metric Authentication BY : ADAM FLOOR 1.

Similar presentations


Presentation on theme: "Modern Bio Metric Authentication BY : ADAM FLOOR 1."— Presentation transcript:

1 Modern Bio Metric Authentication BY : ADAM FLOOR 1

2 Biometrics: Biometrics (ancient Greek: bios ="life", metron ="measure") refers to two very different fields of study and application. 1. used in biological studies, including forestry, is the collection, synthesis, analysis and management of quantitative data on biological communities such as forests. Biometrics in reference to biological sciences has been studied and applied for several generations and is somewhat simply viewed as "biological statistics". 2. Authentication is the act of establishing or confirming something (or someone) as authentic that is that claims made by or about the thing are true. 2

3 The Problem : Authentication as the reality shows, traditional methods of personal identification and authentication based on the use of passwords or physical media (in the form of pass, passport, driving license, electronic keys and cards), do not meet modern requirements for reliability in the determination of the individual. The password can be forgotten or intercept material carrier - to copy, lose or give to another person. Especially it does not allow the traditional access control systems to ensure an adequate level of reliability. As a result, companies are looking for more efficient ways of ensuring security. One way to solve this problem is to move to biometric identification & authentication systems 3

4 2 Bio metric approach for authentication 1. Physiological approach : ◦Physiological are related to the shape of the body and thus it varies from person to person: Fingerprints, Face recognition, hand geometry and iris recognition are some examples of this type of Biometric 2. Behavioral approach : ◦ Behavioral are related to the behavior of a person. Some examples in this case are signature, keystroke dynamics and of voice. Sometimes voice is also considered to be a physiological biometric as it varies from person to person. 4

5

6 Physiological approach Methods finger print : ◦A fingerprint is an impression of the friction ridges of all or any part of the finger ◦The traditional method uses the ink to get the finger print onto a piece of paper. This piece of paper is then scanned using a traditional scanner ◦ Now in modern approach, live finger print readers are used.These are based on optical, thermal, silicon or ultrasonic principles ◦It is the oldest of all the biometric techniques ◦Finger print matching techniques can be placed into two categories. Minutiae based and the other one is Correlation based. 6

7 Physiological approach Face recognition : ◦A facial recognition technique is an application of computer for automatically identifying or verifying a person from a digital image or a video frame from a video source. ◦ Facial metric technology relies on the manufacture of the specific facial features (positioning of eyes, nose and mouth and distances between these features). ◦ The face region is rescaled to a fixed pre-defined size, This normalized face image is called the canonical image ◦Then the facial metrics are computed and stored In a face template 7

8 Physiological approach IRIS Technology : o This recognition method uses the iris of the eye which is colored area that surrounds the pupil. o iris structure is featuring a complex pattern the Iris pattern is taken by a special gray scale camera, Once the image of eye is obtained then the software tries to locate the iris within the image, the software creates a net of curves covering the iris, based of the darkness of the points along the lines the software creates the iris code. o Tow influences have to take into account o The overall darkness of image – so the darkness threshold used to decide whether a given point is dark or bright cannot be static, it must be dynamically computed according to the overall picture darkness. o The size of the iris changes as the size of the pupil changes, Before computing the iris code a proper transformation must be done. o The matching software takes two iris codes and compute the hamming distance based on the number of different bits, the hamming distance score is compared with the security threshold to make the final decision 8

9 Physiological approach Hand Geometry : o Based of the fact the nearly every persons hand is shaped differently and that the shape of a person hand does not change after certain age. o These techniques include the estimation of length width thickness and surface area of the hand o There are 2 sub categories of optical scanners : o Devices that creates black and white bitmap image of the hand shape, this is easily done by using a source of light and a black and white camera, the bit map image is processed by the computer software, only 2D characteristics of hand can be used in this case. o complex hand geometry systems – they use special guide marking to portion the hand better and have both vertical and horizontal sensors of the hand shape measurements, so sensors from this category handle data of all 3D features. 9

10 Physiological approach Retina Geometry : o its based on the blood vessel pattern in the retina of the eye as the blood vessels at the back of the eye have a unique pattern, from eye to eye (and from person to person ). o Retina is not directly visible and so a coherent infrared light source is necessary to illuminate the retina. o the infrared energy is absorbed faster by blood vessels in the retina than by the surrounding tissue, the image of the retina blood vessel pattern is then analyzed. o a coupler is used to read the blood vessel pattern o a retina scan cannot be faked as it is currently impossible to forge a human retina, a retinal scans has an error rate of 1 in 10,000,000. 10

11 Behavioral approach Methods Speaker recognition : o Voice is also physiological trait because every person has different pitch, but voice recognition is mainly based on the study of the way a person speaks, commonly classified as behavioral o speaker authentication focuses on the vocal characteristics that produce speech and not on the sound or the the pronunciation of speech itself. o The vocal characteristics depend on the dimensions of the vocal tract, mouse, nasal cavities and the other speech processing mechanism of the human body. o Speaker recognition uses the acoustic features of speech that have been found to differ between individuals. o These acoustic patterns reflect both anatomy ( size and shape of the throat and moth ( Physiological ), and learned behavioral patterns (voice pitch, speaking style – behavioral ) o Three style of spoken input exsist : o Text independent – involves selection and enrollment of one or more voice passwords o Text prompted – used whenever there is concern of imposters o Text independent. 11

12 Behavioral approach Speaker recognition : o various technologies used to process and store voice prints include hidden Markov models, pattern matching algorithm, neural networks, and decision tree. o voice changes due to aging also need to be addressed by recognition systems. o The biometric is seen as non invasive. 12

13 Behavioral approach Signature verification technique : o The signature dynamics recognition is based on the dynamics of making the signature rather than a direct comparison of the signature itself afterwards. o the dynamics is measured as a means of the pressure, direction, acceleration and the length of the strokes, dynamic number of strokes and their duration. o The most obvious and important advantage of this is that a fraudster cannot glean any information on how to write the signature by simply looking at one that has been previously written. o There are various kinds of devices used to capture the signature dynamics : o Tablets – capture 2D coordinates and the pressure, but has major disadvantages normmaly the resulting digitalized signature looks different from the usual user signature. o special pens – able to capture movements in all three dimensions 13

14 Behavioral approach Keystroke dynamics : o keystroke dynamics is the process of analyzing the way a user types at ta terminal by monitoring the keyboard inputs thousands of times per second in an attempt to identify user based of habitual typing rhythm patterns – sucah as latency or duration. o unlike other biometric systems which may be expensive to implement, keystroke dynamics is almost free – the only hardware requires is the keyboard. o keystroke verification techniques can be classified as either static or continues : ◦ static approach analyze keystroke verification characteristics only at specific times, for example during the login sequence ◦Continues verification – can detect a substitution of the user after the initial verification, by monitoring the user typing behavior throughout the course of the interaction. 14

15 Evaluation o when it is time to use the biometric authentication, the degree of security is concerned. o there are various parameters with the help of which we can measure the performance of any biometric authentication techniques o false accept rate (FAR) & False match Rate (MAR) – the probability that the system incorrectly declares a successful match between the input pattern and a non matching pattern in the database, it measures the percent of invalid matches. o False reject Rate (FRR) – the probability that the system incorrectly declares failure of match between the input pattern and the matching template in the database. o Relative Operating Characteristic (ROC) – in general the matching algorithm perform a decision using threshold the RPC plot is obtained by graphing the values of the FAR and FRR. o Equal Error Rate (ERR) - The rate at which both accept and reject errors are equal,when quick comparison of tow systems is required the ERR is commonly used, 15

16 Methods Drawbacks o Finger Printing – the finger print bit map obtained from the reader is affected by the finger moisture as the moisture significantly influences the capacitance, this means that too wet or dry fingers do not produce bitmaps with sufficient. o Face recognition – the accuracy of face recognition systems improves with time, but it has not been very satisfying so far, there is a need to improve the algorithm for face location, these system also have problems to distinguish very similar person (twins ) and any significate change in hair or beard style requires re-enrollment o Iris – the artificial duplication of the iris is virtually impossible, the method only need to verify the liveness. o Hand Geometry – the hand must be placed accurately, hand geometry doesn’t produce a large data set, therefore give a large number of records, it may not be able to distinguish sufficiently one individual from another (why we need to card at the airport ? ) 16

17 Methods Drawbacks o Retina Geometry – the main drawback of the retina scan are its intrusiveness, the method of obtaining a retina scan is personally invasive – its done with a laser light, also the operation of retina scanner is not easy. o Speaker Recognition – the background noise causes a significant problem that decreases the accuracy, it is based on behavioral characteristics and as such can be negatively affected by the current physical condition and the emotion state. o Signature Verification - Person does not make a signature consistently the same way, so the data obtained from a signature of a person has to allow for quite some variability. The speed of writing is often the most important factor in the decision process, it is possible to forge a signature even if the resulting signature looks different that any person would notice. 17

18 Evaluation results 18

19 Evaluation results 19

20 References Review of modern biometric user authentication and their development prospects Biometric Authentication: A Review (Debnath Bhattacharyya, Rahul Ranjan, Farkhod Alisherov ) Keystroke dynamics as a biometric for authentication (Fabian Monrose, Aviel D.Rubin ) 20

21


Download ppt "Modern Bio Metric Authentication BY : ADAM FLOOR 1."

Similar presentations


Ads by Google