BIOMETRIC AVENUES FOR HUMAN IDENTIFICATION

ABSTRACT: -

In this paper we are going to present an advance technology of the biometry is the multi-biometric and its applications. At one end, there is a continuous and tremendous improvement in the lifestyle of humans while at the other end; the technological crimes are increasing rapidly. As there is a problem there must be a solution. The solution for the problem of illegal authentication is Biometrics. Biometrics is a means of using the physiological or behavioral characteristics of a person. Human identification performance reported so far using face or a finger image under certain conditions is good practice, however, there is still a great need for better performance in biometrics for use in video surveillance. One possible way to achieve improved performance is to combine information from multiple sources. Besides, such systems alleviate some of the problems that are faced by single biometrics-based systems like restricted degrees of freedom, spoof attacks, and unacceptable error rates. We present a prototype bimodal biometric identification system by merging face and finger images.

INTRODUCTION: -

Biometrics refers to the automatic identification of a person based on his or her physiological or behavioral characteristics. This identification method is preferred over traditional method involving passwords and PINs (personal identification numbers) for several reasons, including the person to be identified is required to be physically present at the point of identification and/or identification based on biometric techniques obviates the need to remember a password or carry a token. With the increased use of computers as vehicles of information technology, restricting access to sensitive/personal data is necessary. By replacing PINs, biometric techniques can potentially prevent unauthorized access to or fraudulent use of the following:

. ATMs

. Cellular phones

. Smart cards

. Desktop PCs

. Workstations

. Computer networks

PINs and passwords may be forgotten, and token-based identification methods such as passports and driver’s licenses may be forged, stolen, or lost. Thus, biometric systems of identification are enjoying a new interest. Various types of biometric systems are being used for real-time identification. The most popular are based on face recognition and fingerprint matching; however, other biometric systems use iris and retinal scans, speech, facial feature comparisons and facial thermo grams, and hand geometry. A biometric system is essentially a pattern-recognition system that makes a personal identification by determining the authenticity of a specific physiological or behavioral characteristic possessed by the user. An important issue in designing a practical system is to determine how an individual is identified. Depending on the context, a biometric system can be either a verification (authentication) or an identification system.

Biometrics Functionalities: -

The operation of a biometric identification system implicates in the domain of their methods of actuation, in other words, knowing the way in which a biometrical machine captures the analyzed individual's physical elements. The mechanism of a biometric identification system works with two main steps: registration and identification. Registration consists in storing the biological trait of an individual in a digital format, which will be used later to identify him/her. Once the individual is registered, when a new input is done, the identification process captures and converts the biological trait to the binary format and compares it to the stored one. The binary representation of a biological trait is called template. The generated template of the same individual can be not totally equal at different capture moments. This is due to noisy factors during the capture process (e.g. light, position, rotation, distortion. different sensors, etc). So, a biometric identification system has to work with statistics to

confirm a person’s identity .

There are two main functionalities within identification process: -

(i) Verification/authentication, which is the confirmation or denial of a person's claimed identity (“Am I who I claim I am?”). Usually, in this kind of functionality, Biometrics is combined with a traditional method, e.g., a person uses his/her personal magnetic card and then his/her finger to confirm that he/she is the real owner of the card; (ii) recognition/identification, which is the establishment of the identity from a set of known persons (“Who am I?”). In this case, after the input of the biometric data, the physical or behavioral trait of a person is compared to a number of database registers, until there is a matching register or the registers are over. The first functionality demands a combined traditional method, but requires less time to get a matching. Once the register exists, it is indexed and can be retrieved by the data from the traditional method (e.g., card number) then the biometric data in this same register are compared with inputted

one. Depending on the number of registers in the database and the admissible time for matching, one of the two functionalities is applied. Each approach has its own complexities and could probably be solved best by a specific biometric system, including the following:

. Physical biometrics:

¦ Fingerprint—Analyzing fingertip patterns

¦ Facial recognition/face location—Measuring facial characteristics

¦ Hand geometry—Measuring the shape of the hand

¦ Iris scan—Analyzing features of colored ring of the eye

¦ Retinal scan—Analyzing blood vessels in the eye

¦ vascular patterns—Analyzing vein patterns.

Fingerprint biometric system for

logon identification and authentication Iris recognition biometric system

Fingerprint Recognition:-.

Fingerprint recognition is one of the oldest biometric technologies, and its application in criminal identification, using eyesight, has been in use for more than 100 years. Today, computer software and hardware can perform the identification significantly more accurately and rapidly. Fingerprint technology is among the most developed biometric technologies, and its price is cost-effective enough to make its way into public use.

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. Figure 8 shows a diagram of a minutiae extraction algorithm, composed by five components: orientation field estimation, fingerprint area location, ridge extraction, thinning, and minutiae extraction.

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 è. A minutiae mj in I and a minutiae mi in T are considered “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 è0.

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 distortion-tolerant transformations. After the alignment, a final matching score is computed by using the maximum number of mated pairs.

Figure 9. (a) and (b) Input and Template minutiae sets; (c) Input and Template fingerprint alignment; (d) Minutiae matching.

Challenges in Fingerprint Identification:-

Despite the efficacy of human identification based on fingerprint matching techniques, the fingerprint identification still presents some challenges, such as: approximately 3% of fingerprints are not of good quality; no proven contact less fingerprint sensor technology is currently available; the new compact solid-state sensors capture only small portion of the fingerprint; fingerprint impression is often left on the sensor; fingerprints are not universal; fingerprint sensors can be different during registration and identification (interoperability).

Iris Recognition: -

The most numerous and dense degrees-of-freedom (forms of variability across individuals), which are both stable over time and easily imaged, are found in the complex texture of the iris of either eye. This protected internal organ, whose pattern can be encoded from distances of up to almost a meter, reveals about 266 independent degrees-of-freedom of textural variation across individuals.

The iris is a structure of the human eye, composed of elastic connective tissue, the trabecular meshwork, whose prenatal morphogenesis is completed during the 8th month of gestation. It consists of pectinate ligaments adhering into a tangled mesh revealing striations, ciliary processes, crypts, rings, furrows, a corona, sometimes freckles, vasculature, and other features (Figure 1).

Figure 1. Iris structures .

5.1 Daugman’s Approach:-

The approach proposed by Daugman , for iris recognition is composed of three main stages: (i) localization, (ii) extraction/encoding, and (iii) comparison. Figure 11 shows a diagram of Daugman’s approach.

Figure 11. Daugman’s Approach Stages

The localization stage uses an integro-differential operator to locate the borders of the iri(the inner and outer boundaries of the iris), based on the ascension of the gradient to adjust the circular contours. This operator essentially is a circular edge detector and returns a “spike” when a candidate circle shares the pupil (iris) center coordinates and radius. If the eyelids intrude, they are detected and excluded.

The extraction stage is done by demodulation with complex-valued 2D wavelets Then, a double-dimensionless coordinate system is defined which maps the tissue in a manner that is invariant to changes in pupillary constriction and overall iris image size, and hence also invariant to camera zoom factor and distance to the eye. The coordinate system compensates automatically for the stretching of the iris tissue as the pupil dilates. Figure 12 shows the “IrisCode” resulted from a detected iris.

Figure 12. Isolation of an iris for encoding, and its resulting “Iris Code”.

The detailed iris pattern is encoded into a 256-byte “Iris Code” by demodulating it with 2D Gabor wavelets, which represent the texture by phasors in the complex plane. Each phasor angle is quantized into just the quadrant in which it lies for each local element of the iris pattern, and this operation is repeated all across the iris, at many different scales of analysis. The comparison of a stored template with an inputted one is done by the calculation of the Hamming distance (HD) between two 256-byte iris codes.

Limitations of Iris: -

Although the iris is one of the most reliable Biometrics traits, it has some limitations:

(i) Capturing an iris image involves cooperation from the user;

(ii) Cost of high performance iris systems is relatively high;

(iii) Iris images may be of poor quality resulting in failures to enroll;

(iv) Up to 7% iris scans can fail, due to anomalies, such as watery eyes, long eyelashes or hard contact lenses;

(v) Iris can change over time (e.g., as a result of eye disease), leading to false rejects;

(vi) Contact lens or photograph of a person's iris pattern can be used to spoof some iris recognition systems (however, a Fourier filter applied to a fake image can easily reveal four points of spurious energy, when a natural iris does not have these spurious coherences).

Multibiometrics:--

A biometric system that relies only on a single biometric identifier often presents limitations, such as:

(i) Non-universality for that single trait;

(ii) Noise in sensed data, and

(iii) Intra-class variations.

So, by using multiple sources of biometric simultaneously it is possible to integrate

information to enhance matching performance, increase the population coverage by reducing failure to enroll rate, and difficult spoofing.

The possible scenarios for multibiometrics include: the use of multiple algorithms for the same biometric trait recognition, each one exploring different features; the use of multiple sensor systems (for instance, for fingerprints it could be used a solid-state or an optical sensor); the use of multiple units of the same biometrics (for instance, the identification system can use fingerprints from different fingers); the use of multiple impressions systems; and, finally, the use of multiple biometric traits simultaneously (face and iris, for instance). Figure 13 illustrates these scenarios for multibiometrics systems.

Figure 13. Scenarios of multibiometric systems.

This technique was tested on a subset of 10 users who provided biometric data over a period of two months (approximately 30 samples per user per biometric). Figure 3 illustrates the case where reducing the face weight improves verification accuracy. Our experimental results indicate that employing user-specific weights further improves matching performance.

Applications: -

Biometrics is a rapidly evolving technology that is being widely used in forensics, such as criminal identification and prison security, and that has the potential to be used in a large range of civilian application areas. Biometrics can be used to prevent unauthorized access to ATMs, cellular phones, smart cards, desktop PCs, workstations, and computer networks. It can be used during transactions conducted by telephone and Internet (electronic commerce and electronic banking). In automobiles, biometrics can replace keys with keyless entry devices.

CONCLUSION: -

Multibiometric systems alleviate a few of the problems observed in unit modal biometric systems. Besides improving matching performance, they also address the problems of non-universality and spoofing. Multibiometric systems can integrate information at various levels, the most popular one being fusion at the matching score level where the scores by the individual matchers are integrated. The simple sum rule results in improved matching performance, which can be further improved by employing user-specific biometric weights. User specific weights aid in reducing the false reject rate, thereby enhancing user convenience. It must be noted that deploying a multibiometric system introduces some overhead in terms computational demands and costs. Therefore, it important the cost versus performance trade-off carefully studied before deploying these systems. Researchers from the National Institute of Science and Technology (NIST) used commercially available biometric products recently to acquire and test multibiometric data pertaining to 1,000 users. This is an indication of the increased attention that multibiometric systems are receiving from the government (for various national identification programs currently under implementation such as the US-VISIT program) as well as from researchers (see Matt Turk’s article in this section).

c