Bio-metric Module

INTRODUCTION TO BIOMETRIC MODULE

What Are Biometrics?

àThe term "biometrics" is derived from the Greek words bio (life) and metric (to measure).

àFor our use, biometrics refers to technologies for measuring and analyzing a person's physiological or behavioral characteristics. These characteristics are unique to individuals hence

Can be used to verify or identify a person.

àThe term Biometrics is becoming highly important in computer security world. The human physical characteristics like fingerprints, face, hand geometry, voice and iris are known as biometrics.

    Fingerprints have been successfully used for over one hundred years in law enforcement and forensics to identify and apprehend criminals. But, as biometrics permeates our society, this recognition technology faces new challenges. The design and suitability of biometric technology for person identification depends on the application requirements. These requirements are typically specified in terms of identification accuracy, throughput, user acceptance, system security, robustness, and return on investment. The next generation biometric technology must overcome many hurdles and challenges to improve the recognition accuracy. These include ability to handle poor quality and incomplete data, achieve scalability to accommodate hundreds of millions of users, ensure interoperability, and protect user privacy while reducing system cost and enhancing system integrity. Human identification leads to mutual trust that is essential for the proper functioning of society.

         

HARDWARE SPECIFICATIONS:

PIN	NAME	SPECIFICATION
1	GND	GROUND
2	TXD	SERIAL SENDER
3	RXD	SERIAL RECEIVER
4	VCC	5V

We have been identifying fellow humans based on their voice, appearance, or gait for thousands of years. However, a systematic and scientific basis for human identification started in the 19^th century when Alphonse Bertillon introduced the use of a number of anthropomorphic Measurements to identify habitual criminals. The Bertillon system was short-lived: soon after it’s

Introduction, the distinctiveness of human fingerprints was established. Since the early 1900s, Fingerprints have been an accepted method in forensic investigations to identify suspects and Repeat criminals. Now, virtually all law enforcement agencies worldwide use Automatic Fingerprint Identification Systems (AFIS). With growing concerns about terrorist activities, Security breaches, and financial fraud, other physiological and behavioral human characteristics Have been used for person identification. These distinctive characteristics, or biometric traits, Include features such as face, iris, palm print, and voice. Biometrics is now a mature Technology that is widely used in a variety of applications ranging from border crossings. Voice biometric is appropriate in authentication applications involving Mobile phones since a sensor for capturing voice (microphone) is already embedded in the phone.

Fingerprint is the most popular biometric for accessing laptops, mobile phones and PDAs since low cost, small footprint fingerprint sweep sensors can be easily embedded in these devices. Some of the traits, for example, hand geometry, are more appropriate for verification applications whereas others like fingerprint, iris, and face have sufficient discriminating power to be applicable in large-scale identification applications. One of the unique applications of biometrics is in the negative identification, i.e., the person is not the one who has already been registered/enrolled in the system. The negative identification is required to prevent multiple enrolments of the same person which is critical for large scale biometric applications,

Some of the Popular Biometric Modalities:

(a) Face:       Humans have a remarkable ability to recognize fellow beings based on facial Appearance. So, face is a natural human trait for automated biometric recognition. Face Recognition systems typically utilize the spatial relationship among the locations of facial Features such as eyes, nose, lips, chin, and the global appearance of a face. The forensic and civilian applications of face recognition technologies pose a number of technical challenges Both for static mug-shot photograph matching (e.g., for ensuring that the same person is not Requesting multiple passports) to unconstrained video streams acquired in visible or Near-infrared illumination (e.g., in surveillance). An excellent survey of existing face Recognition technologies and challenges is available in the problems associated with Illumination, gesture, facial makeup, occlusion, and pose variations adversely affect the face Recognition performance. While face recognition is non-intrusive, has high user acceptance, and provides acceptable levels of recognition performance in controlled environments, robust face recognition in non-ideal situations continues to pose challenges.

(b) Fingerprint:    Fingerprint-based recognition has been the longest serving, most successful and popular method for person identification. There are numerous historical accounts which suggest that fingerprints have been used in business transactions as early as 500 B.C. in Babylon and later by Chinese officials to seal the official documents in the 3rd century B.C. Fingerprints consist of a regular texture pattern composed of ridges and valleys. These ridges are characterized by several landmark points, known as minutiae, which are mostly in the form of ridge endings and ridge bifurcations. The spatial distribution of these minutiae points is claimed to be unique to each finger; it is the collection of minutiae points in a fingerprint that is primarily employed for matching two fingerprints. In addition to minutiae points, there are sweat pores and other details (referred to as extended or level 3 features) which can be acquired in high resolution (1000 ppi) fingerprint images. These extended features are receiving increased attention since forensics experts seem to utilize them particularly for latent and poor quality fingerprint images. Nearly all forensics and law enforcement agencies worldwide utilize Automatic Fingerprint Identification Systems (AFIS).

 (c) Iris:        The iris is the colored annular ring that surrounds the pupil. Iris images acquired under infrared illumination consist of complex texture pattern with numerous individual attributes, e.g. stripes, pits, and furrows, which allow for highly reliable personal identification. The iris is a protected internal organ whose texture is stable and distinctive, even among identical

Twins (similar to fingerprints), and extremely difficult to surgically spoof. An excellent survey on the current iris recognition technologies and future research challenges is available in First invented by Daugman both the accuracy and matching speed of currently available iris recognition systems is very high. Iris recognition has been integrated in several large-scale personal identification systems (e.g., border crossing system in the United Arab Emirates  Several efforts are also being made to capture iris at a distance  However, relatively high sensor cost, along with relatively large failure to enrol (FTE) rate reported in some studies, and lack of legacy iris databases may limit its usage in some large-scale government applications.

(d) Palm print:      The image of a human palm consists of palmer friction ridges and flexion creases Latent palm print identification is of growing importance in forensic applications since around 30% of the latent prints lifted from crime scenes (from knifes, guns, steering wheels) are of palms rather than of fingers Similar to fingerprints, latent palm print systems utilize minutiae and creases for matching. While law enforcement and forensics agencies have always collected fingerprints, it is only in recent years that large palm print databases are becoming available. Based on the success of fingerprints in civilian applications, some attempts have been made to utilize low resolution palm print images (about 75 dpi) for access control applications, these systems utilize texture features which are quite similar to those employed for iris recognition. To our knowledge, palm print recognition systems have not yet been deployed for civilian applications (e.g., access control), mainly due to their large physical size and the fact that fingerprint identification based on compact and embedded sensors works quite well for such applications.

(e) Hand Geometry:       It is claimed that individuals can be discriminated based on the shape of their hands. Person identification using hand geometry utilizes low resolution (~20 ppi) hand images to extract a number of geometrical features such as finger length, width, thickness, perimeter, and finger area. The discriminatory power of these features is quite limited, and therefore hand geometry systems are employed only for verification applications (1:1 matching) in low security access control and time-and-attendance applications. The hand geometry systems have large physical size, so they cannot be easily embedded in existing security systems.

(f) Voice:     Speech or voice-based recognition systems identify a person based on their spoken words. The generation of human voice involves a combination of behavioral and physiological features. The physiological component of voice generation depends on the shape and size of vocal tracts, lips, nasal cavities, and mouth. The movement of lips, jaws, tongue, velum, and larynx constitute the behavioral component of voice which can vary over time due to person’s age and medical condition (e.g., common cold). The spectral content of the voice is analyzed to extract its intensity, duration, quality, and pitch information, which is used to build a model (typically the Hidden Markov Model) for speaker recognition. Speaker recognition is highly suitable for applications like tele-banking but it is quite sensitive to background noise and playback spoofing. Again, voice biometric is primarily used in verification mode.

(g) Signature:        Signature is a behavioral biometric modality that is used in daily business transactions (e.g., credit card purchase). However, attempts to develop highly accurate signature recognition systems have not been successful. This is primarily due to the large intra-class variations in a person’s signature over time. Attempts have been made to improve the signature recognition performance by capturing dynamic or online signatures that require pressure-sensitive pen-pad. Dynamic signatures help in acquiring the shape, speed, acceleration, pen pressure, order and speed of strokes, during the actual act of signing. This additional information seems to improve the verification performance (over static signatures) as well as circumvent signature forgeries. Still, very few automatic signature verification systems have been deployed.

(h) DNA: The DNA is an acronym for deoxyribonucleic acid which is present in nucleus of every cell in human body and therefore a highly stable biometric identifier that represents physiological characteristic The DNA structure of every human is unique, except from identical twins, and is composed of genes that determine physical characteristics (like eye or hair color). Human DNA samples can be acquired from a wide variety of sources; from hair, finger nails, saliva and blood samples. Identification based on DNA requires first isolating from source/samples, amplifying it to create multiple copies of target sequence, followed by sequencing that generates a unique DNA profile. The DNA matching is quite popular for forensic and law enforcement applications. However, it requires tangible samples and cannot yet be done in real time. Currently, not all the steps in DNA matching are automated and therefore results can be skewed if the process is not conducted properly or the DNA samples themselves get contaminated. In summary, the DNA matching process is expensive, time consuming and therefore not yet suitable for large scale biometrics applications for civilian usage.

(i) Hand Veins:     The pattern of blood vessels hidden underneath the skin is quite distinct in individuals, even among identical twins and stable over long period of time. The primary function of veins is to carry blood from one part of the body to another and therefore vascular pattern is spread throughout the body. The veins that are present in hands, i.e. palm, finger and palm dorsal surface, are easy to acquire (using near infrared illumination) and have been employed for the biometric identification The vein patterns are generally stable for adults (age of 20-50 years) but begin to shrink later due to decline in strength of bones and muscles. There are several diseases, like diabetes, atherosclerosis, or tumors, which can influence the vein patterns and make them thick or thin. Biometric authentication devices using finger and palm vein imaging are now available for some commercial applications to the best of our knowledge; there is no known large scale vascular biometric system. This could be primarily due to concerns about the system cost and lack of large scale studies on vein individuality and stability. On the plus side, these vascular systems are touch less which often appeals to the user.

Biometrics has long being touted as a powerful tool for solving identification and authentication issues for immigration and customs, physical security, and computer security. It involves measuring one or more unique physiological human characteristics the shape of a body, fingerprints, structure of the face, DNA, hand/palm geometry, iris patterns, and even odor/scent. Behavioral traits can also be used – typing rhythm, gait, and voice. These technologies have enormous promise because they can never be forgotten, lost or copied, unlike the current methods of cards and passwords. The potential for biometrics is ever increasing post 9/11. In addition to growing needs for fast, accurate and dependable security, biometric technologies have recently begun to enter into public consciousness due to high profile applications in entertainment media and day-to-day activities.

Increasing requirements for security in many sectors of our society have generated a tremendous interest in biometrics. This has also raised expectations from biometric technologies. These expectations can be summarized into five categories: performance, cost, user convenience, interoperability, and system security.

(i) Performance:   The recognition performance achievable from a biometric system is of utmost interest in the deployment of biometric systems. A biometric system is prone to numerous errors; failure to enroll (FTE), false accept rate (FAR), and false reject rate (FRR). The system performance is further characterized in terms of transaction time or throughput. The accuracy of a biometric system is not static, but it is data dependent and influenced by several factors:

(a) Biometric quality, which is related to the quality of sensed signal/image

(b) Composition of target user population (e.g., gender, race, age, and profession)

(c) Size of database (i.e., number of subjects enrolled in the system)

(d) Time interval between enrolment and verification data

(e) Variations in the operating environment (e.g., temperature, humidity, and illumination)

(f) Distinctiveness of biometric modality, and

 (g) Robustness of employed algorithms (namely, segmentation, feature extraction, and matching algorithms).

 (ii) Cost:     The cost of deploying a biometric system is often estimated from its direct and indirect components. The direct component includes hardware components (sensor, processor, memory) and the software modules (GUI and matcher). The sensor should be low cost and it should be easy to embed it in the existing security infrastructure. There are multifaceted components that constitute the indirect cost in the usage of biometric system. These include system installation, training/maintenance requirements, and most importantly, user acceptance. In the end, return on investment or the cost-benefit analysis is critical for making a case for biometric systems in most applications.

(iii) Interoperability:     As biometrics systems are being increasingly deployed in a wide range of applications, it is necessary that the system be interoperable among different biometrics technologies (sensors/algorithms/vendors). A biometric system can no longer operate under the assumption that the same sensor, same algorithms, or same operating conditions will always be available during its lifetime. The biometric system should be highly interoperable to authenticate individuals using sensors from different vendors and on varying hardware/software platforms. The system should employ usage/development/deployment of common data exchange facilities and the formats to exchange the biometric data/features between different vendors, from different geographical locations. This would significantly reduce the need for additional software development and bring all the associated advantages (cost savings and efficiency).

(iv) User Convenience:     A biometrics system should be user friendly. Any perceived health or hygienic concerns with the continuous usage of biometric sensors can influence user acceptance. Hygiene as well as security has been one of the motivations for developing touch less fingerprint sensors. Some biometric modalities are easier to acquire than others and require less user cooperation during data acquisition. Human factors and ergonomic issues will continue to play a major role in widespread deployment of biometric systems in non-government applications (such as physical and logical access control).

(v) Security:     Biometric systems are vulnerable to potential security breaches from spoof and malicious attacks. These systems should therefore offer a high degree of protection to various vulnerabilities resulting from intrinsic failures and adversary attacks [48]. One of the major system security concerns deals with biometric template security. The access protocols and the storage of biometric and other user specific data should be provided the highest level of security. Based on the above considerations, the second generation biometric systems should be easy to use, have low cost, be easy to embed and integrate in the target security application and be robust, secure, and highly accurate in their matching performance.

First Generation Biometrics:

 (a) Face recognition system (Smart Gate) at Sydney airport (b) iris recognition system at Amsterdam Schiphol airport (c) at Manchester airport (d) at UAE airport (e) fingerprint Recognition using index fingers at airports in Japan (f) ten fingerprint acquisition

Overview of biometric applications: