Biometrics

Paper Presentation On

BIOMETRICS INNOVATION-2k7

By Himanshu Madan Siddharth Shashidharan TY-ENTC COEP

2

ABSTRACT No two human beings are alike. Throughout history, man has developed various mechanisms to identify the unique characteristics that go to build each personality. These range from instinctive abilities, as demonstrated by a mother in distinguishing between her twins, to sophisticated tools used in classical forensic sciences. The hallmark of the twenty first century will be the application of cutting edge technology to delineate with microscopic precision, what man has hitherto deduced through observation and instinct. Today, biometrics is fast becoming a frontier science, having great relevance in the channels of commerce, banking and trade, security, safety and authorization. The applications of Biometrics are extensive but they can essentially be divided into the following main groups: (i) Commercial applications, such as computer network login, electronic data security, e-commerce, Internet access, ATM, cellular phones, PDA, medical records etc. (ii) Government applications, such as driver’s licenses, PAN and social security cards, border and passport control etc. (iii) Forensic applications, such as corpse identification, criminal investigation, terrorist identification, parenthood determination, missing children etc. The schemes often employed for such diverse applications include facial pattern recognition, fingerprinting and hand geometry, voice signature identification, retinal and iris scanning, DNA sequencing and signature identification among others. As technology advances, it opens up a plethora of avenues to exploit. Identification systems based on a person’s vein patterns, ear shape, body odour and body salinity. The result is a future that promises a confluence of different biometric technologies, integrated efficiently to deliver a reliable and secure system of ascertaining an individual’s identity.

3

Index

•

•

•

•

Physical Biometry •

Facial Recognition

4

•

Fingerprint Recognition

7

•

Iris Scan Biometry

9

•

Retinal Scan Biometry

11

•

Hand Geometry

12

•

DNA Fingerprinting

13

Behavioral biometry •

Dynamic Signature Recognition

14

•

Dynamic Keystroke Identification

15

•

Speaker Recognition

16

Future Biometry •

Vascular Pattern Authentication

18

•

Body Odour Identification

18

•

Body Salinity

18

•

Ear Shape Identification

19

Project Undertaken

20

4

Facial Recognition Over the last ten years or so, face recognition has become a popular area of research in computer vision and one of the most successful applications of image analysis and understanding. Most

facial

feature

identification

systems today only allow for two-dimensional frontal images of one's face. However, there are systems that allow for front and side views,

Facial recognition systems with eye detection

which in effect produce a three-dimensional mapping of one's face. Furthermore, realtime operating systems now use streaming videos for face recognition. Automatic facial recognition consists of four main processes: detection, capture, extraction, and recognition. Principal Component Analysis: Detection pertains to finding a human face and isolating it from the background and all other images. When a human face is detected, the facial recognition system captures the facial image using a video camera. Principal component analysis is a way of identifying patterns that are important aspects of the face and expressing this data in such a way as to highlight their similarities and differences.

(i) Original image (ii) Absolute difference from empty-room image summed over the three RBG channels (iii) Resulting foreground segments

Using the difference from a background image identifies the foreground. The background image can either be either static or the result of adaptive estimation. For the picture shown above, the algorithm subtracts the empty room image, sums the RGB

5 channels and digitizes the results. Skin colour segmentation is applied on the colournormalised foreground segments by using a human skin colour model to produce the skin likelihood map of the foreground. The likelihood map is then segmented into skin segments; some heuristics discard those segments that are very unlikely to be human faces.

(a) Skin colour likelihood map

(b) 8-way connectivity skin segments

Eye Detection: Detection of location of the eyes in a facial image is of paramount importance for an automated face recognizer. This represents the next stage in extracting a face from the original image. Firstly, the eye zone (eyes and bridge of the nose area) is detected in the candidate segments. As the second stage, we detect the eyes in the identified eye zone. The process uses similar algorithms as above estimate the brightness

(a) Eye zone determination. Top-right and bottomleft: face segment under consideration with and without detected eye zone. Top-left: mean brightness across rows. Bottom-right: mean brightness across columns in the horizontal stripe of the eye zone. (b) Detection of eyes in the eye zone.

6 co-efficients, with modern systems even allowing for a tolerable amount of tilt.

The eye detection is a pre-requisite required for estimating the features of the face. Subsequent procedures use probability-model based algorithms that cut out and characterize the features of the individual.

Frontal face verification: The verifier

is

often

a

two-stage

system, the first stage using DFSS (Distance

From

Free

Space)

measure followed by the second, which uses a two-class LDA (Linear

Discriminant

Analysis). The 100 normalised segments in ascending DFFS order. The segments are mostly frontal views, but some are profile faces.

7 The former is used to compute distances from a frontal face prototype. The LDA step dramatically reduces the number of false detections and thus enhances the performance. Facial recognition: An LDA classifier, as shown above, finally processes the normalized segments, and an identity tag is attached to each. The system can be trained to read and track movements of the face hence giving real time operation. After collecting the requisite

samples,

it

searches for a template stored in the database. If a match is found, the user’s face

is

subsequently

Block diagram depicting a facial recognition system.

verified or authenticated. Another being

applied

identification imaging.

technology in

facial

systems

is

that

is

feature thermal

Thermal imaging systems

employ an infrared camera to capture the pattern of blood vessels under the skin of one's face.

The inherent

advantage of this system is that it can be used in complete darkness and is not

Thermal imaging applied to a face.

as affected by facial changes and position.

Fingerprint Recognition Fingerprint is a reproduction of the fingertip epidermis, produced when the finger is pressed against a smooth surface. Scientific studies on fingerprint started during the 19th century establishing two fingerprint properties that are still accepted as true: high uniqueness and high permanence. These studies led to the use of fingerprints for criminal identification, first in Argentina in 1896, then at Scotland Yard in 1901, and other countries in the early 1900’s. Fingerprint recognition is a complex pattern

recognition

problem. Designing Figure 1. (a) Fingerprint ridges and valleys patterns; (b) Ridge bifurcation (black box) and ridge terminations (black circumferences)

8 algorithms capable of extracting salient features and matching them in a robust way is quite hard, especially in poor quality images. The most evident structural characteristic of a fingerprint is a pattern of interleaved ridges and valleys. Ridges vary in width from 100 μm for thin ridges, to 300 μm for thick ridges. Generally, the period of a ridge/valley cycle is about 500 μm. Ridges and valleys often run in parallel, and sometimes they can suddenly come to an end (termination), or can divide into two ridges (bifurcation). Ridge terminations and bifurcations are considered minutiae (small details). There are other types of minutiae in a fingerprint, but the most frequently used are terminations and bifurcations. Fig 1(a) shows a fingerprint, where it is possible to observe the ridges and valleys, and Fig 1(b) shows the ridge bifurcations and terminations found in the fingerprint area enclosed by the white rectangle. Automatic fingerprint matching approaches are usually categorized as: correlation-based matching, where two fingerprint images are superimposed and the correlation between corresponding pixels is computed for different alignments; minutiaebased matching, which consists of finding the alignment between the template and the input minutiae sets that results in the maximum number of minutiae pairing; and, ridge feature-based matching, which compares fingerprints in term of features extracted from the ridge pattern, such as: shape, orientation, and frequency. Minutiae-Based Matching: Most fingerprint matching systems are based on matching minutiae points between the query and the template fingerprint images. The matching of two minutiae sets is usually posed as a point pattern matching problem and the similarity between them is proportional to the number of matching minutiae pairs. The first stage of the minutiae-based technique is the

minutiae

extraction.

Figure2 shows a diagram of a minutiae extraction algorithm, composed by five components: orientation

field

estimation,

fingerprint area location, ridge extraction,

thinning,

minutiae extraction.

and

9 Minutiae-based matching problem can be formulated in the following way. Let T and I be the template and the input fingerprint minutiae sets, respectively. In general, each minutiae is described by its x, y location coordinates and its angle θ. A minutiae m j in I and a minutiae mi in T are considered

Figure 2:. Minutiae extraction algorithm components.

“matching”

if

the

spatial

displacement

between them is smaller than a given tolerance r0 and the direction difference between them is smaller than an angle tolerance θ0. Aligning the two fingerprints is a mandatory step of the fingerprint matching in order to maximized the number of matching minutiae. Correctly aligning two fingerprints requires geometrical transformations, such as: rotation, displacement, scale, and other distortiontolerant transformations. After the alignment, a final matching score is computed by using the maximum number of mated pairs.

Iris Scan Biometry The uniqueness of eye identification has been well documented. The iris is so unique that no two irises are alike, even among identical

(a) and (b) Input and Template minutiae sets; (c) Input andtwins, Template (d) in fingerprint the entirealignment; human population. Minutiae matching.

In actuality, identifying the iris and converting it

to mathematical code, the probability that two irises will produce the same mathematical code is approximately one in ten to the 78th power. The population of the earth is approximately ten to the tenth power.

LG’s eye scanner

Image Acquisition: Optical

platforms designed and

optimized for specific iris

recognition applications

allow image acquisition at distances

from 3.5" to nearly one

meter. In its simplest functional

configuration, an optical

unit acquires multiple images of the

presented iris through a

simple lens, a monochrome CCD

camera, and a frame

grabbing board. Multiple low level

LEDs operating in the 720

to 850 nm range provide illumination over the focal range of the camera. User alignment in the X, Y, and Z axes is aided by a combination of mirrors, audible verbal direction, and in some cases, zoom or auto-focus lenses. In some models, a range finder, initiates

10 the process automatically when a subject approaches within 18" of the unit. The iris contains many collagenous fibers, contraction furrows, coronas, crypts, color, serpentine vasculature, striations, freckles, rifts, and pits. Measuring the patterns of these features and their spatial relationships to each other provides other quantifiable parameters useful to the identification process. Iris Definition: The image that best meets the focus and detail clarity requirements of the system is then analyzed to locate the limbus (the outer boundary of the iris that meets the white sclera of the eye), the nominal pupillary boundary, and the center of the pupil. The precise location of the circular iris has now been defined and processing can take place. Field Optimization: A dynamic feature of the The pupil and the iris.

system automatically adjusts the width of the

pupillary boundary-to-limbus zone in real time to maximize the amount of iris analyzed, using algorithms that exclude areas covered by eyelids, deep shadow, specular reflection, etc... Elimination of marginal areas has little negative impact on the analysis process. In the previous figure, points Cp and Ci are the detected centers of the pupil and iris respectively. The intersection points of these wedges with the pupil and iris circles form a skewed wedge polygon p1 p2 p3 p4. The skewed wedge is subdivided radially into N blocks and the image pixel values in each block are averaged to form a pixel (j,k) in the unwrapped iris image, where j is the current angle and k is the current radius number. (a) Detected iris and pupil circles. (b) Iris extracted into 180 angle divisions, 73 radius divisions. (c) Iris extracted into 128 angle divisions, 8 radius divisions.

11 Image Analysis: The features of the iris are then analyzed and digitized into a 512 byte ‘IrisCode’ record, half of which describes the features, half of which controls the comparison process. During enrollment, this IrisCode record is stored in the database for future comparison. During a recognition attempt, when an iris is presented at a recognition point, the same process is repeated; however the resulting IrisCode record is not

Iris recognition technology

stored, but is compared to every file in the database.

Retinal Scan Biometry The true target for the retinal scan is the capillary pattern in the retina. The process relies on generating images of the retina using a low-intensity light source. In the 1930s retinal capillary patterns were suggested to be unique, but the technology used to exploit this information was developed much later. Although military and high-security use of photographic retinal scans began decades earlier, by 1985, retinal scan technology became available for computerized biometric identification and commercial security use. Retinal scans are just one of the biometric methods using the eye for personal identification. Modus Operandi: Retinal scans are based on the presence of the fine network of capillaries supplying the retina with oxygen and nutrients. These vessels absorb light and can be easily

visualized

with

proper

illumination. Retinal scans require Retinal imaging

close contact of user and scanner, a perfect alignment of the eye with a

12 scanner, and no movement of the eye. The examiner is required to keep the subject's eye within half an inch of the instrument. The subject must focus on a pinpoint of little green light (to properly align the eye) and avoid blinking. Retinal scans involve a low-intensity infrared light that is projected through to the back of the eye and onto the retina. Infrared light is used due to the fact that the blood vessels on the retina absorb the infrared light faster than surrounding eye tissue(s).

The infrared light with the retinal pattern is

reflected back to a video camera. The video camera captures the retinal pattern and converts it into data that is 35 bytes in size. Although retinal patterns are generally thought to be constant during a person's life, they can change in case of diabetes, glaucoma, retinal degenerative disorders or cataracts. Therefore, although retinal scans are nearly 100% accurate they cannot be used as a universal security measure without making allowances for normal changes.

Hand Geometry Hand geometry systems use an optical camera to capture two orthogonal two dimensional images of the palm and sides of the hand, offering a balance of reliability and relative ease of use. They typically collect more than 90 dimensional measurements, including finger width, height, and length; distances between joints; and knuckle shapes. Hand geometry technology posses one of the smallest reference templates in the biometric field, generally under ten bytes. The process involves matching a given hand to a person previously enrolled in the system. From the snapshots of the hand, the average feature vector is

Hand Geometry Authentication

computed. The given feature vector is then compared with the feature vector stored in the database associated with the claimed identity. F = (f1; f2; :::; fd) represents the d-dimensional feature vector in the database and Y = (y1; y2; :::; yd) is the feature vector of the hand whose identity has to be verified. The verification is positive if the distance between F and Y is less than a threshold value. Four distance metrics, absolute, weighted absolute, Euclidean, and weighted Euclidean, corresponding to the following four equations are explored:

13 d

∑

| Y j − Fj | < ε a

j =1

| Y j − Fj |

d

∑

σj

j =1

∑ (Y d

j =1 d

∑ j =1

< ε wa

− Fj ) < εe 2

j

(Y j − F j ) 2

σj

Pegs as shown aid in the calculation of Euclidean distances

< ε we

2 where σ j is the feature variance of the jth feature and εa , εwa , εe and εwe are threshold

values for each respective distance metric.

DNA Fingerprinting Deoxyribonucleic acid (DNA) is a nucleic acid that contains the genetic instructions for the development and functioning of living organisms. Although the structure of DNA is the same throughout all species of plants, animals and microorganisms, each individual organism looks different. This is due to the order in which DNA base pairs are sequenced. Sequences of DNA differ from person to person, but every cell within the same person contains the same sequence of DNA. As a laboratory procedure, DNA fingerprinting requires the following steps: Isolation of DNA: DNA must be recovered from the cells or

DNA strand

tissues of the body. Only a small amount of tissue - like blood, hair, or skin - is needed. Cutting, sizing, and sorting: Special enzymes called restriction enzymes are used to cut the DNA at specific places. For example, an enzyme called EcoR1, found in bacteria, will cut DNA only when the sequence GAATTC occurs. The DNA pieces are sorted according to size by a sieving technique called electrophoresis. The DNA pieces are passed through a gel made from seaweed agarose (a jelly-like product made from seaweed), which is the biotechnological equivalent of screening sand through progressively finer mesh screens.

14 Transfer of DNA to nylon: Distribution of DNA pieces is transferred to a nylon sheet by placing the sheet on the gel and soaking them overnight. Probing: Adding radioactive or colored probes to the nylon sheet produces a pattern called the DNA fingerprint. Each probe typically sticks in only one or two specific places A DNA Fingerprint

on the nylon sheet.

DNA fingerprint: The final DNA fingerprint is built by using several probes (5-10 or more) simultaneously. Thus, these fingerprints can be compared and matched with those residing in the database. This technology has been around for some time, especially in the field of criminal forensic sciences and parenthood determination. As extraction methods continue to advance, we shall soon see its application in commercial avenues as well.

Dynamic Signature Verification Any process or transaction that requires an individual's signature is a prime contender for signature identification. The major technological hurdle for signature identification involves the method of trying to differentiate between the parts of the signature that are habitual (consistent) and those that alter with each signing (behavioral). Therefore signature identification systems analyze two different areas of an individual's signature: the specific features of the signature and specific features of the process of signing one's signature.

Features that are taken into account and measured include

speed, pen pressure, directions, stroke length, and the points in time when the pen is lifted from the paper. Human signatures, despite overall consistencies do contain certain variations. It is thus imperative to train system to account for this in order to build a prototype for the database. Training: The system needs to extract a representation of the training set that will yield minimum generalization Warping) alignment

error. provides

of

two

DTW the

(Dynamic optimal

signatures.

The

prototype that represents the training set

Time

15 is computed as the mean of the aligned signatures. The individual residual distances between each of the signatures in the training set and this reference signature are collected in order to estimate the statistics of the alignment process. This statistics is subsequently used for classification. Verification: Once this mean or prototype signature is ready, the signature is segmented into a series of strokes, which are encoded to find a close matching between the segments. Test signatures can then be compared against template signatures and if the match is below a signer’s specific threshold, the signature is accepted.

Dynamic Keystroke Identification Signature characteristics Keystroke dynamics looks at the way a person types on a keyboard. Specifically, keyboard dynamics systems measure two distinct variables: keystroke duration, which is the amount of time you hold down a particular key, and keystroke latency, which is the amount of time between keys. These systems scan for inputs a thousand times per second. The user normally types out a string of data and his movements and traits are monitored by the system. The aforementioned features are extracted from the user's keystroke for the formation of a template and later for verification. Shown below is an example of the keystroke duration and latency observed for the word ‘IVAN’. The features extracted for formation of the pattern form

the

Features

Vector. For the above example,

Extracted features of the Keystroke Dynamics for the word IVAN

Features Vector = [Itp,VItl,Vtp ,AVtl ,Atp ,NAtl ,Ntp] Itp: Keystroke Duration of the key (I)

VItl: Keystroke Latency between (V) and (I)

The keystroke duration is composed solely of positive whole values. Keystroke Latency however can contain positive as well as negative values. The latter occurs when user presses the next key before the release of the current one.

16 Thus, a prototype is generated with the Mean (μ), minimum or maximum and standard deviation (σ), calculated for each feature (xi) of the pattern of size n, in accord with the following equations: Mean ( µ )=

1 N

n

∑ xi

Standard Deviation (σ)=

i =1

1 n ∑ | xi − µ i | N − 1 i =1

The Classifier is responsible for the process of authentication. It correlates the pattern to be verified with the template of the prototypes using the Distance Pattern between the two vectors, calculated as: D (pattern, prototype) =

1 N

| patteni − prototypei | σi i =1 n

∑

A favorable decision is made if this value is less than a predefined threshold.

Speaker Recognition Speaker recognition, which can be classified into identification and verification, is the process of automatically recognizing the speaker on the basis of individual information encoded in speech waves. In speaker identification, the correct speaker is determined from a given population. In this the test utterance is compared with the reference model of the registered population. Speaker verification is to determine if the speaker is who he or she claims to be. So the test utterance is compared only with the reference model of the claimed identity. Speaker identification can be text independent or text dependent. Among various types of speech features, LPCC (linear predictionbased cepstral coefficients) and MFCC (mel-frequency cepstral coefficients) have been found to be superior for speaker recognition. In LPCC, Linear prediction coefficients are obtained for each frame

using

Durbin

Recursive

method. These coefficients are then converted to cepstral coefficients. In MFCC, Fast Fourier Transform is computed for each frame and then weighted by a Mel-scaled filter bank. Speech Spectrograph

17 The filter bank outputs are then converted to cepstral parameters by applying the discrete cosine transformation. In text-independent speaker identification, given a set of registered speakers and a sample utterance, open-set speaker identification is defined as a twofold problem. Firstly, it is required to identify the speaker model in the set, which best matches the test utterance. Secondly, it must be determined whether the test utterance has actually been produced by the speaker associated with the best-matched model, or by some unknown speaker outside the registered set. Mathematically speaking, let N speakers are enrolled in the system and their statistical model descriptions are λ1, λ2,..., λN. If O denotes the feature vector sequence extracted from the test utterance, then the open-set identification can be stated as:

…………….(1) Where θ is a pre-determined threshold. In other words, O is assigned to the speaker model that yields the maximum likelihood over all other speaker models in the system, if this maximum likelihood score itself is greater than the threshold θ. Otherwise, it is declared as originated from an unknown speaker. It is evident from the above description that, for a given θ, three types of error are possible: • O, which belongs to λm, not yielding the maximum likelihood for λm. • Assigning O to one of the speaker models in the system when it does not belong to any of them. • Declaring O which belongs to λm, and yields the maximum likelihood for it, as originating from an unknown speaker.

18 These types of error are referred to as OSIE, OSI-FA and OSI-FR respectively (where OSI, E, FA and FR stand for open-set identification, error, false acceptance and false rejection respectively). Based on equation (1), it is evident that open-set identification is a two-stage process. For a given O, the first stage determines the speaker model that yields the maximum likelihood, and the second stage makes the decision to assign O to the speaker model determined in the first stage or to declare it as originating from an unknown speaker. Of course, the first stage is responsible for generating OSIE, whereas both OSI-FA and OSI-FR are the consequences of the decision made in the second stage.

Vascular Pattern Authentication Hemoglobin in the blood is oxygenated in the lungs and carries oxygen to the tissues of the body through the arteries. After it releases it to the tissues, the deoxidized hemoglobin returns to the heart through the veins. These two types of hemoglobin have different rates of absorbency. Deoxidized hemoglobin absorbs light at a wavelength of about 760 nm in the near-infrared region. When the palm is illuminated with nearinfrared light, the deoxidized hemoglobin in

Vascular Pattern

the palm veins absorbs it, thereby reducing the reflection rate and causing the veins to appear as a black pattern. Vein Commercial veinworks scannersin similar manner and the vein pattern is extracted by image authentication

19 processing and registered. The vein pattern of the person being authenticated is then verified against the pre-recorded pattern.

Body Odour Identification In the case of human recognition, the goal of an electronic nose is to identify an odorant sample and to estimate its concentration. It basically means signal processing and pattern recognition system. However, those two steps may be subdivided into preprocessing, feature extraction, classification, and decisionmaking. But first, a database of expected odorants must be compiled and the sample must be presented to the nose’s sensor array. Currently, a U.K. based company Mastiff Electronic Systems is said to be in development stages of a product that digitally sniffs the back of a computer user's hand to verify identity.

Body Salinity

ENose device

An existing system, developed jointly by MIT and IBM, works by exploiting the natural level of salinity, in the human body. An electric field passes a tiny electrical current (of the order of 1nA) through the body (salt is an effective conductor). Applications of this kind of biometric technology could include data transfer between communication devices carried on the body including watches, mobiles and pagers. Applications could also include "waking up" household appliances as one enters a room.

Ear Shape Identification Ear images can be acquired in a similar manner to face images, and a number of researchers have suggested that the human ear is unique enough to each individual to be of practical use as a biometric. There are two major parts to the system: automatic ear region segmentation and 3D ear shape matching. Starting with the multi-modal 3D+2D image acquired in a profile view, the system automatically finds the ear pit by using skin detection, curvature estimation and surface segmentation and classification. After the ear pit is detected, an active contour algorithm using both color and depth information is applied, and the contour expands to find the outline of the visible ear region.

20 The ear pit makes an ideal starting point. The Active Contouring algorithm grows until it finds the ear edge, and is robust in its ability to exclude earrings and occluding hair. When the active contour finishes, the outlined shape is Steps of Finding the Ear Pit: (a) Original 2D Color Images (b) After Skin Detection (c) Curvature estimation and segmentation (d) Ear Pit Vote Results (f) Ear Pit in Original cropped fromImage the 3D image, and the corresponding 3D data is then used as the ear image for matching. As is often the case with biometric technologies, this template is now stored in the database for further reference. This template is used to correlate the current photo of the person, and when a match is found, the person is identified.

Project Undertaken Active Contour Growing on A Real Image (a) Iteration = 25 (b) Iteration = 150

In

a

world

racing

towards

digitization, the prevalent issues of security

and

undergoing

commerce an

are

fast

unheralded

metamorphosis into the digital domain. We sense this provides an opportunity to work on the cutting edge of modern biometrics technology and also has tremendous potential commercially. It is with this notion in mind that we have developed an optical sensor based device that features an optical sensor circuit and utilizes its apparent versatility in creating a signature recognition and authentication tool. We have used a common optical mouse sensor circuit for two-dimensional sensing and tracking of motion, in this case, the customer’s signature. The information conveyed by the optical sensors is received and stored using a microcontroller. The

PS/2 mouse sensor circuit

21 signature obtained is then compared with various templates previously recorded. If a favorable match is obtained, the identification is authenticated. A block schematic for the same is shown below:

Optica l sensor

Processin g unit

Signature Templates

Optical signature i d e n t i f i c a t i o n s ys t e m .

Storage unit

Comparison

Identification