An Introduction to Biometric Recognition - A SEMINAR

 

1. INTRODUCTION

 

          The term biometric comes from two Greek words bios (life) and metrikos (measure). It is well known that humans intuitively use some body characteristics such as face, gait or voice to recognize each other. Since, today, a wide variety of applications require reliable verification schemes to confirm the identity of an individual, recognizing humans based on their body characteristics became more and more interesting in emerging technology applications.

           

2. Definition

 

             Biometric recognition or, simply, biometrics refers to the automatic recognition of individuals based on their physiological or behavioral characteristics.

 

               By using biometrics, it is possible to confirm or establish an individual’s identity based on “who she is,” rather than by “what she possesses” (e.g., an ID card) or “what she remembers” (e.g., a password).

 

3. Need for biometrics

        With the increased use of computers as vehicles of information technology, it is necessary to restrict access to sensitive/personal data. Traditionally, passwords and ID cards have been used to restrict access to secure systems but these methods can easily be breached and are unreliable. PINs and passwords may be forgotten and token-based methods of identification like passports and driver's licenses may be forged, stolen, or lost.  Biometric cannot be borrowed, stolen, or forgotten, and forging one is practically impossible. By replacing PINs, Biometric techniques can potentially prevent unauthorized access to or fraudulent use of ATMs, cellular phones, smart cards, desktop PCs, workstations, and computer networks. Thus biometric recognition is enjoying a renewed interest. The purpose of such schemes is to ensure that the rendered services are accessed only by a legitimate user and no one else.

4. Requirements to be satisfied by a biometric characteristic

 

          Any human physiological and/or behavioral characteristic can be used as a biometric characteristic as long as it satisfies the following requirements:

 

• Universality: each person should have the characteristic.
• Distinctiveness: any two persons should be sufficiently different in terms of the characteristic.
• Permanence: the characteristic should be sufficiently invariant (with respect to the matching criterion) over a period of time.
• Collectability: the characteristic can be measured quantitatively.

 

          However, in a practical biometric system (i.e., a system that employs biometrics for personal recognition), there are a number of other issues that should be considered, including:

 

          Performance, which refers to the achievable recognition accuracy and speed, the resources required to achieve the desired recognition accuracy and speed, as well as the operational and environmental factors that affect the accuracy and speed.

 

          Acceptability, which indicates the extent to which people are willing to accept the use of a particular biometric identifier (characteristic) in their daily lives.

 

          Circumvention, which reflects how easily the system can be fooled using fraudulent methods.

 

          A practical biometric system should meet the specified recognition accuracy, speed, and resource requirements, be harmless to the users, be accepted by the intended population, and be sufficiently robust to various fraudulent methods and attacks to the system.

 

5. BIOMETRIC SYSTEMS

 

          A biometric system is essentially a pattern recognition system that operates by acquiring biometric data from an individual, extracting a feature set from the acquired data, and comparing this feature set against the template set in the database. Depending on the application context, a biometric system may operate either in verification mode or identification mode.

 

          In the verification mode, the system validates a person’s identity by comparing the captured biometric data with her own biometric template(s) stored in the system database.  In such a system, an individual who desires to be recognized claims an identity, usually via a personal identification number (PIN), a user name, or a smart card, and the system conducts a one-to-one comparison to determine whether the claim is true or not (e.g., “Does this biometric data belong to Bob?”). Identity verification is typically used for positive recognition, where the aim is to prevent multiple people from using the same identity .

 

          In the identification mode, the system recognizes an individual by searching the templates of all the users in the database for a match. Therefore, the system conducts a one-to-many comparison to establish an individual’s identity (or fails if the subject is not enrolled in the system database) without the subject having to claim an identity (e.g., “Whose biometric data is this?”). Identification is a critical component in negative recognition applications where the system establishes whether the person is who she (implicitly or explicitly) denies to be. The purpose of negative recognition is to prevent a single person from using multiple identities. Identification may also be used in positive recognition for convenience (the user is not required to claim an identity). While traditional methods of personal recognition such as passwords, PINs, keys, and tokens may work for positive recognition, negative recognition can only be established through biometrics.

 

         The block diagrams of a verification system and an identification system are depicted in Fig. 1; user enrollment, which is common to both of the tasks, is also illustrated.

 

         The verification problem may be formally posed as follows: given an input feature vector X_Q (extracted from the biometric data) and a claimed identity I , determine if (I, X_Q) belongs to class w₁ or w₂ , where  w₁  indicates that the claim is true (a genuine user) and w₂ indicates that the claim is false (an impostor). Typically, X_Q is matched against X_I, the biometric template corresponding to user I, to determine its category. Thus

          Where S is the function that measures the similarity between feature vectors   X_Q  and  X_I , and  t  is a predefined threshold. The   value S (X_Q, X_I) is termed as a similarity or matching score between the biometric measurements of the user and the claimed identity. Therefore, every claimed identity is classified into  w₁  or  w₂  based on the variables X_Q, I , X_I  , t and function S. Note that biometric measurements (e.g., fingerprints) of the same individual taken at different times are almost never identical. This is the reason for introducing the threshold t.

              The identification problem, on the other hand, may be stated as follows. Given an input feature vector X_Q, determine the identity I_k, k Î{1, 2, ….., N, N+1}. Here I₁, I₂, ….., I_N are the identities enrolled in the system and           indicates the reject case where no suitable identity can be determined for the user. Hence

where X_Ik is the biometric template corresponding to identity I_k, and t is a predefined threshold.

          A biometric system is designed using the following four main modules (see Fig. 1).

 

1. Sensor module, which captures the biometric data of an individual. An example is a fingerprint sensor that images the ridge and valley structure of a user’s finger.
2. Feature extraction module, in which the acquired biometric data is processed to extract a set of salient or discriminatory features. For example, the position and orientation of minutiae points (local ridge and valley singularities) in a fingerprint image are extracted in the feature extraction module of a fingerprint-based biometric system.
3. Matcher module, in which the features extracted during recognition are compared against the stored templates to generate matching scores. For example, in the matching module of a fingerprint-based biometric system, the number of matching minutiae between the input and the template fingerprint images is determined and a matching score is reported. The matcher module also encapsulates a decision making module, in which a user’s claimed identity is confirmed (verification) or a user’s identity is established (identification) based on the matching score.
4. System database module, which is used by the biometric system to store the biometric templates of the enrolled users. The enrollment module is responsible for enrolling individuals into the biometric system database. During the enrollment phase, a biometric characteristic of an individual is first scanned by a biometric reader  to produce a digital representation of the characteristic. The data capture during the enrollment process may or may not be supervised by a human depending on the application. A quality check is generally performed to ensure that the acquired sample can be reliably processed by successive stages. In order to facilitate matching, a feature extractor to generate a compact but expressive representation called a template, further processes the input digital representation. Depending on the application, the template may be stored in the central database of the biometric system or be recorded on a smart card issued to the individual. Usually, multiple templates of an individual are stored to account for variations observed in the biometric trait and the templates in the database may be updated over time.

 

6. BIOMETRIC SYSTEM ERRORS

 

          Two samples of the same biometric characteristic from the same person  (e.g., two impressions of a user’s right index finger) are not exactly the same  due to imperfect imaging conditions (e.g., sensor noise and dry fingers), changes in the user’s physiological or behavioral characteristics (e.g., cuts and bruises on the finger), ambient conditions (e.g., temperature and humidity), and user’s interaction with the sensor (e.g., finger placement). Therefore, the response of a biometric matching system is the matching score S(X_Q, X_I) (typically a single number) that quantifies the similarity between the input(X_Q) and the template (X_I) representations. The higher the score, the more certain is the system that the two biometric measurements come from the same person. The system decision is regulated by the threshold t: pairs of biometric samples generating scores higher than or equal to t are inferred as mate pairs (i.e., belonging to the same person); pairs of biometric samples generating scores lower than are inferred as nonmate  pairs (i.e., belonging to different persons).

 

          A biometric verification system makes two types of errors:

1. Mistaking biometric measurements from two different persons to be from the same person (called false match) and
2. Mistaking two biometric measurements from the same person to be from two different persons (called false nonmatch).

          These two types of errors are often termed as false accept and false reject, respectively. There is a tradeoff between false match rate (FMR) and false nonmatch rate (FNMR) in every biometric system. In fact, both FMR and FNMR are functions of the system threshold t ; if t is decreased to make the system more tolerant to input variations and noise, then FMR increases. On the other hand, if t is raised to make the system more secure, then FNMR increases accordingly. The system performance at all the operating points (thresholds  t) can be depicted in the form of a receiver operating characteristic (ROC) curve. A ROC curve is a plot of FMR against  FNMR for various threshold values t [see Fig. 2].

 

          The accuracy requirements of a biometric system are very much application-dependent. For example, in some forensic applications such as criminal identification, one of the critical design issues is the FNMR rate (and not the FMR), i.e., we do not want to miss identifying a criminal even at the risk of manually examining a large number of potentially incorrect matches generated by the biometric system. On the other extreme, the FMR may be one of the most important factors in a highly secure access control application, where the primary objective is deterring  impostors (although we are concerned with the possible inconvenience  to the legitimate users due to a high FNMR). There are a number of civilian applications whose performance requirements   lie in between these two extremes, where both FMR and FNMR need to be considered. For example, in applications like bank ATM card verification, a false match means a loss of several hundred dollars while a high FNMR may lead to a potential loss of a valued customer. Fig. 2 depicts the FMR and FNMR tradeoffs in different types of biometric applications.

 

7. Overview of commonly used  Biometrics

 

          A number of biometric characteristics are in use in various applications (see Fig. 3). Each biometric has its strengths and weaknesses, and the choice depends on the application. No single biometric is expected to effectively meet the requirements of all the applications. In other words, no biometric is “optimal.” The match between a specific biometric and an application is determined depending upon the operational mode of the application and the properties of the   biometric characteristic. They involve two categories

 

1) Physiological Biometrics

2) Behavioral Biometrics.

1) Physiological Biometrics: In this category the recognition is based upon physiological characteristics. Some examples are: DNA, Fingerprint, Hand Geometry, Iris Recognition, Retinal Scanning, and Facial Recognition

A brief introduction to the commonly used biometrics is given below.

Fingerprint:

          Humans have been using fingerprints for personal identification and the matching accuracy using fingerprints has been shown to be very high. Fingerprint is a unique feature to an individual. The lines that create fingerprint pattern are called ridges and the spaces between the ridges are called valleys or furrows. It is through the pattern of these ridges and valleys that the unique fingerprint is matched for authentication and authorization.  Patterns have been extracted by creating an inked impression of the fingertip on paper. Today, compact sensors provide digital images of these patterns. Fingerprint recognition for identification acquires the initial image through live scan of the finger by direct contact with a reader device that can also check for validating attributes such as temperature and pulse. Since the finger actually touches the scanning device, the surface can become oily and cloudy after repeated use and reduce the sensitivity and reliability of optical scanners. Solid-state sensors overcome this and other technical difficulties because the coated silicon chip itself is the sensor. Solid-state devices use electrical capacitance to sense the ridges of the fingerprint and create a compact digital image. Fingerprints of identical twins are different and so are the prints on each finger of the same person.  Finally, fingerprints of a small fraction of the population may be unsuitable for automatic identification because of genetic factors, aging, environmental, or occupational reasons (e.g., manual workers may have a large number of cuts and bruises on their fingerprints that keep changing).

Iris:

          The iris is the annular region of the eye bounded by the pupil and the sclera (white of the eye) on either side. The visual texture of the iris is formed during fetal development and stabilizes during the first two years of life. The  complex iris texture carries very distinctive information useful for personal recognition.  Each iris is distinctive and, like fingerprints, even the irises of identical twins are different. It is extremely difficult to surgically tamper the texture of the iris. Further, it is rather easy  to detect artificial irises (e.g., designer contact lenses).  The iris as physical feature of a  human being can be used for biometric verification or identification through the process of iris recognition.

Face:

          Facial images are the most common biometric characteristics used by humans to make a personal recognition In particular, an automated face recognition system is capable of capturing   face images from a distance using video camera.  The most popular approaches to face recognition are based on the location and shape of facial attributes such as the eyes, eyebrows, nose, lips and chin, and their spatial relationships. While the verification performance of the face recognition systems that are commercially available is reasonable, they impose a number of restrictions on how the facial images are obtained, sometimes requiring a fixed and simple background or special illumination. These systems also have difficulty in recognizing a face from images captured from two drastically different views and under different illumination conditions. Face recognition has several advantages over other biometric technologies: it is natural, non-intrusive, and easy to use. To prevent a fake face or mold from faking out the system, many systems now require the user to smile, blink, or otherwise move in a way that is human before verifying.

DNA:

          Deoxyribonucleic acid (DNA) is the one-dimensional (1–D) ultimate unique code for one’s individuality —except for the fact that identical twins have identical DNA patterns. It is, however, currently used mostly in the context of forensic applications for person recognition.

2) Behavioral biometrics is traits that is learned or acquired over time as differentiated from physiological characteristics. Some examples are: Voice Recognition, Signature Recognition and  Keystroke Recognition

 

Signature:

          The way a person signs his name is known to be a characteristic of that individual. Signature requires contact with the writing instrument and  an effort on the part of the user. Signature recognition systems, also called dynamic signature verification systems, measure both the distinguishing features of the signature and the distinguishing features of the process of  signing. These features include pen pressure, speed, and the points at which the pen is lifted from the paper. Signatures are a behavioral biometric that change over a period of time and are influenced by physical and emotional conditions of the signatories. These behavioral patterns are captured through a specially designed pen and compared with a template of process patterns.

 

Voice:

          Voice is a behavioral biometrics. The features of an individual’s voice are based on the shape and size of the appendages (e.g., vocal tracts, mouth, nasal cavities, and lips) that are used in the synthesis of the sound. These characteristics of human speech are invariant for an individual, but the behavioral part of the speech of a person changes over time due to age, medical conditions (such as a common cold), and emotional state, etc. Voice is also not very distinctive and may not be appropriate for large-scale identification. A text-dependent voice recognition system is based on the utterance of a fixed predetermined phrase. A text-independent voice recognition system recognizes the speaker independent of what she speaks. A text-independent system is more difficult to design than a text-dependent system but offers more protection against fraud. A disadvantage of voice-based recognition is that speech features are sensitive to a number of factors such as background noise.

 

8. LIMITATIONS OF (UNIMODAL) BIOMETRIC SYSTEMS

 

          The successful installation of biometric systems in various civilian applications does not imply that biometrics is a fully solved problem. Single biometric systems are applicable in low to moderate security applications. As security needs increase and terrorists and criminals gain more expertise in biometric technologies, unimodal systems may not be sufficient. Multibiometric systems fuse together the data and features of unimodal systems and can provide higher levels of security. A well-planned and designed multibiometric system is potentially more accurate than the best unimodal system.  Biometric systems that operate using any single biometric characteristic have the following limitations.

 

 

1) Noise in sensed data: The sensed data might be noisy or distorted. A fingerprint with a scar or a voice altered by cold is examples of noisy data. Noisy data could also be the result of defective or improperly maintained sensors (e.g., accumulation of dirt on a fingerprint sensor) or unfavorable ambient conditions (e.g., poor illumination of a user’s face in a face recognition system). Noisy biometric data may be incorrectly matched with templates in the database (see Fig. 3) resulting in a user being incorrectly rejected.

 

2) Intra-class variations: The biometric data acquired from an individual during authentication may be very different from the data that was used to generate the template during enrollment, thereby affecting the matching process. This variation is typically caused by a user who is incorrectly interacting with the sensor (see Fig. 4) or when sensor characteristics are modified (e.g., by changing sensors—the sensor interoperability problem) during the verification phase. As another example, the varying psychological makeup of an individual might result in vastly different behavioral traits at various time instances.

3) Distinctiveness: While a biometric trait is expected to vary significantly across individuals, there may be large inter-class similarities in the feature sets used to represent these traits. This limitation restricts the discriminability provided by the biometric trait. Thus, every biometric trait has some theoretical upper bound in terms of its discrimination capability.

 

4) Nonuniversality: While every user is expected to possess the biometric trait being acquired, in reality it is possible for a subset of the users to not possess a particular biometric. A fingerprint biometric system, for example, may be unable to extract features from the fingerprints of certain individuals, due to the poor quality of the ridges (see Fig. 5). Thus, there is a failure to enroll associated with using a single biometric trait. It has been empirically estimated that as much as 4% of the population may have poor quality fingerprint ridges that are difficult to image with the currently available fingerprint sensors.

 

 

5) Spoof attacks: An impostor may attempt to spoof the biometric trait of a legitimate enrolled user in order to circumvent the system. This type of attack is especially relevant when behavioral traits such as signature  and voice  are used. However, physical traits are also susceptible to spoof attacks. For example, it has been demonstrated that it is possible (although difficult and cumbersome and requires the help of a legitimate user) to construct artificial fingers/fingerprints in a reasonable amount of time to circumvent a fingerprint verification system .

  

9.  MULTIMODAL BIOMETRIC SYSTEMS

 

          Single biometric systems are applicable in low to moderate security applications. As security needs increase and terrorists and criminals gain more expertise in biometrics technologies, unimodal systems may not be sufficient.Some of the limitations imposed by unimodal biometric systems can be overcome by using multiple biometric modalities (such as face and fingerprint of a person or multiple fingers of a person). Such systems, known as multimodal biometric systems , are expected to be more reliable due to the presence of multiple, independent pieces of evidence . Multibiometric systems fuse together the data and features of unimodal systems and can provide higher levels of security. These systems are also able to meet the stringent performance requirements imposed by various applications . Multimodal biometric systems address the problem of nonuniversality, since multiple traits ensure sufficient population coverage. Further, multimodal biometric systems provide antispoofing measures by making it difficult for an intruder to simultaneously spoof the  multiple biometric traits of a legitimate user. By asking the user to present a random subset of biometric traits (e.g., right index   and right middle fingers, in that order), the system ensures that a “live” user is indeed present at the point of data acquisition. Thus, a challenge-response type of authentication can be facilitated using multimodal biometric systems.

 

10. Applications:

 

1.     Biometrics is a rapidly evolving technology, which has been widely used in forensic applications such as corpse identification, criminal investigation, terrorist identification, parenthood determination and missing children.

2.     Biometrics can be used to prevent unauthorized access to ATMs, cellular phones, smart cards, desktop PCs, workstations, and computer networks.

3.     In automobiles, biometrics can replace keys with key-less entry and key-less ignition.

4.     The need for biometrics can be found in governments, in the military, and in commercial applications.

5.     Enterprise-wide network security infrastructures, government IDs,  investing and other financial transactions, retail sales, law enforcement, and health and social services are already benefiting from these technologies.

6.     Recent advancements in biometric sensors and matching algorithms have led to the deployment of biometric authentication in a large number of civilian applications.

11. Advantages  and disadvantages of  biometrics

 

Advantages:

• Current methods like password verification have many problems (one has to remember it all the time, password could be hacked, it may be forgotten).But biometrics need not  be remembered   and  also it is very difficult to steal   biometrics .
• One has to change passwords periodically to keep them secure. That’s a big problem for many people. But   biometrics are always with us and never change.
• One’s identity can be verified without resort to documents that may be stolen, lost or altered.
• Anyone else can pretend to be you, by using your password or duplicating a key. But with biometrics  no one can use your identity because biometric of every individual is unique.
• Biometrics introduces  incredible  convenience  for the users (as  users are no longer required to remember multiple, long and complex frequently changing  passwords)  while maintaining a sufficiently high degree of  accuracy  and  security.

• A physical key can typically only get you into a single door – or a number of identically-keyed doors, so you have to carry a large number of keys. A biometric can be used to identify you to any number of access systems.
•  While traditional methods such as passwords, keys and tokens may work for positive recognition, negative recognition can only be established through biometrics.

 

Disadvantages

• The fingerprint of those  people  working in chemical industries are often affected. Therefore these companies should not use the finger print mode of authentication.
• Identical twins have identical DNA patterns. Hence other authentication schemes should be used in such cases.
• Behavioral biometrics such as signatures can change over a period of time and are influenced by physical and emotional conditions of the signatories
• Retinal vasculature can reveal some medical conditions, e.g., hypertension, which is another, factor deterring the public acceptance of     retinal   scan-based biometrics. 

 

• A disadvantage of voice-based recognition is that speech features are sensitive to age of an individual, medical conditions such as cold, emotional condition and background noise.
• Biometrics is an expensive security solution.

 

12. CONCLUSION

 

          Reliable personal recognition is critical to many business processes. Biometrics refers to automatic recognition of   individuals based on their behavioral and/or physiological characteristics. The conventional knowledge-based and token-based methods do not really provide positive personal recognition because they rely on surrogate representations of the person’s identity (e.g., exclusive knowledge or possession). It is thus obvious that any system assuring reliable personal recognition must necessarily involve a biometric component. This is not, however, to state that biometrics alone can deliver reliable personal recognition component. In fact, a sound system design will often entail incorporation of many biometric and non biometric components (building blocks) to provide reliable personal recognition.

 

             Biometric-based systems also have some limitations that may have adverse implications for the security of a system. While some of the limitations of biometrics can be overcome with the evolution of biometric technology and a careful system design. The future probably belongs to multimodal biometric systems as they alleviate a few of the problems observed in unimodal biometric systems. Multimodal biometric systems can  integrate information at various levels, the most popular one being fusion at the matching  score level. Besides improving matching performance, they also address the problem of non-universality and spoofing. 

 

          There are a number of privacy concerns raised about the use of biometrics. A sound trade-off between security and privacy may be necessary; collective accountability/acceptability standards can only be enforced through common legislation.  Increasing interest in biometrics has led to rapid improvements in biometric technologies with better performance, faster transaction speeds, and lower costs. The advantages of using biometrics                  system design,to enhance security have been widely reported. There are various biometric projects underway around the world to strengthen security.

REFERENCES

 

• A. K. Jain, A. Ross, S. Prabhakar, "An Introduction to Biometric Recognition", IEEE Trans. on Circuits and Systems for Video Technology, Vol. 14, No. 1, pp 4-19, January 2004
• Kreismir Delac, Mislav Grigic, “A Survey of Biometric Recognition Methods” 46^th International Symposium Electronics in  Marine, ELMAR – 2004, 16-18 June 2004, Zadar, Croatia
• www.biometricscatalog.org