Babasaheb Naik College of Engineering, Pusad Topic:-Biometrics Human Recognition System
Babasaheb Naik College of Engineering, Pusad Topic:-Biometrics Human Recognition System
Babasaheb Naik College of Engineering, Pusad Topic:-Biometrics Human Recognition System
BABASAHEB NAIK COLLEGE OF ENGINEERING, PUSAD Topic:- BIOMETRICS HUMAN RECOGNITION SYSTEM
Page 1
CONTENTS
1. Abstract 2. Introduction 3. History of biometrics 4. Types of biometrics 5. Iris biometrics 6. Fingerprint biometrics 7. Advantages of biometrics 8. Disadvantages of biometrics 9. Conclusion 10.Reference
1. ABSTRACT
As the need for personal authentication increases, many people are turning to biometric authentication as an alternative to traditional security devices. Concurrently, users and vendors of biometric authentication systems are searching for methods to establish system performance. This paper presents a model that defines the parameters necessary to estimate the performance of fingerprint authentication systems without going through the rigors of intensive system testing inherent in establishing error rates. The model presented here was developed to predict the performance of the pore-based automated fingerprint matching routine developed internally in the research and development division at NSA. This paper also discusses the statistics of fingerprint pores and the efficacy of using pores, in addition to the traditionallyused minutiae, to improve system performance. In addition, this paper links together the realms of automated matching and statistical evaluations of fingerprint features. The result of this link provides knowledge of practical performance limits of any automated matching routine which utilizes pores or minutia features.
Page 2
2. INTRODUCTION
The IBIAs key focus is on the use of technology in determining identity. Biometrics, which is one of the technologies playing an increasingly important role in identity management, has begun to permeate our everyday lives. The associated technology is commonly embedded and operating well today within solutions that protect our national borders and ports; identify criminals and terrorists; and secure critical facilities, computers, and networks. Increasingly, we see applications in healthcare, the financial industry, and perhaps most significantly, in personal consumer devices. As the Committee is well aware, biometrics is not new or radical. People have used biometrics throughout recorded history to uniquely identify themselves, starting with the first handprint signatures of authors of paintings on cave walls 31,000 years ago. In fact, I think it is an injustice that that first caveman wasnt given prior-art credit by the patent office for what has evolved into modern hand geometry and palm print biometrics! (Note that in the last week, the FBI has added a national palm print capability to its Next Generation Identification system NGI.) The common thread from 31,000 years ago to today is that it matters who I am. In my personal relationships, and in my business transactions, it matters who I am, both to myself, and to the people with whom I have relationships or conduct transactions. However, in those first villages, people knew everyone intimately by their appearance, by their voices, by their behaviour, by their work products and by their handprint signatures. It was easy to transact business based on a confident understanding of identity.
Page 3
3. HISTORY OF BIOMETRICS
Branch and end points of epidermal ridges were used by Sir Francis Galton in 1872 to develop aprobabilistic model of fingerprint individuality, and they have been used since then in both forensic (Cummins and Midlo, 1943) and automated matching (Blue, Candela, Gruther, Chellapa, and Wilson, 1994; Hrechak and McHugh, 1990). These Galton features, or minutiae, contain unique information that enables their use in probabilistic analyses. Each Galton feature has a specific type, i.e., branch point or end point, a unique location on the fingerprint, and a specific orientation (Stoney and Thornton, 1986). The orientation can be defined for an end point, for example, as the approximate tangent angle to the ridge ending. Most probabilistic models to date have utilized Galton features exclusively; two of these models will be presented in this paper. The first model, published in 1977 by James Osterburg, et al at the University of Illinois, determines the probability of occurrence of a certain configuration of Galton features in a fingerprint. Two years later, a member of Osterburgs team, Stanley Sclove, published a paper presenting the occurrence of Galton features as a twodimensional Markov model. Both of these models can be adapted to use pores instead of Galton features. Pores have been used historically to assist in forensic matching. Although most matching methods have emphasized minutia comparisons and used pores as ancillary comparison features, the ability to match prints based on pore information alone has been documented (Ashbaugh, 1983; Locard, 1912; Stosz and Alyea, 1994). The concept of using pores to match prints has been essentially dormant during the rise of automated fingerprint recognition systems.
Page 4
4. TYPES OF BIOMETRICS
Biometric characteristics can be divided into two main categories: psychological and behavioural. Physiological are based on the shape of the body. Fingerprints are one of the physiological traits that have been used for more than 100 years. Other physiological traits are face recognition, hand geometry and iris recognition. Behavioural characteristics are related to the behaviour of a person. The signature is a widely used form of identification and verification. Other behaviour approaches are voice recognition and keystroke behaviour. Other biometrics being researched and developed are based on a persons way of walking, also known as their gait, retina, hand veins, ear recognition, facial thermo gram, DNA, odor and palm prints.
Types of biometrics
Physiological
Behavioral
Face
Keystroke
Iris
Signature
Fingerprint
Voice
Hand
Page 5
5. IRIS BIOMETRICS
18 years later
In 1994 National Geographic photographer Steve McCurry took a picture of a little Afghan girl called Sharbat Gula in refugee camp in Pakistan. Her photo (she had amazing green eyes) made it to National Geographic 100 best Pictures! McCurry later tried to trace and find the girl, until finally 17 years later he located a girl with those same haunting green eyes.
17 years passedhow to verify if this was the same girl? Hard-ship changed the girls appearance. But she had those same haunting green eyes The Explorer team got verification using U.S. FBI iris scanning technology. They used iris image from old taken photograph and compared to the new one. Iris code declared a match! This was indeed the same girl! Iris biometric made it possible to verify this. The iris is the colored portion of the eye surrounding the pupil. Its pattern results from a meshwork of muscle ligaments, and its color and contrast are determined by pigmentation.
Page 6
Biometric Advantages thought to be very unique, potentially more discriminate than fingerprints remains stable over an individuals lifetime for cooperating subjects, iris pattern is captured quickly in an image
Page 7
6. FINGERPRINT BIOMETRICS
Fingerprint scanning is very stable and reliable. It secures entry devices for building door locks and computer network access are becoming more common. Recently a small number of banks have begun using fingerprint readers for authorization at ATMs
Page 8
Page 9
7. ADVANTAGES OF BIOMETRICS
The primary advantage of biometric authentication methods over other methods of user authentication is that they really do what they should, i.e., they authenticate the user. These methods use real human physiological or behavioural characteristics to authenticate users. These biometric characteristics are (more or less) permanent and not changeable. It is also not easy (although in some cases not principally impossible) to change ones fingerprint, iris or other biometric characteristics. Users cannot pass their biometric characteristics to other users as easily as they do with their cards or passwords. Biometric objects cannot be stolen as tokens, keys, cards or other objects used for the traditional user authentication, yet biometric characteristics can be stolen from computer systems and networks. Biometric characteristics are not secret and therefore the availability of a users fingerprint or iris pattern does not break security the same way as availability of the users password. Even the use of dead or artificial biometric characteristics should not let the attacker in. Most biometric techniques are based on something that cannot be lost or forgotten. This is an advantage for users as well as for system administrators because the problems and costs associated with lost, reissued or temporarily issued tokens/cards/passwords can be avoided, thus saving some costs of the system management. Another advantage of biometric authentication systems may be their speed. The authentication of a habituated user using an iris-based identification system may take 2 (or 3) seconds while finding your key ring, locating the right key and using it may take some 5 (or 10) seconds.
Page 10
8. DISADVANTAGES OF BIOMETRICS
So why do not we use biometrics everywhere instead of passwords or tokens? Nothing is perfect, and biometric authentication methods also have their own shortcomings. First of all the performance of biometric systems is not ideal (yet?). Biometric systems still need to be improved in the terms of accuracy and speed. Biometric systems with the false rejection rate under 1% (together with a reasonably low false acceptance rate) are still rare today. Although few biometric systems are fast and accurate (in terms of low false acceptance rate) enough to allow identification (automatically recognising the user identity), most of current systems are suitable for the verification only, as the false acceptance rate is too high. The fail to enrol rate brings up another important problem. Not all users can use any given biometric system. People without hands cannot use fingerprint or hand-based systems3. Visually impaired people have difficulties using iris or retina based techniques. As not all users are able to use a specific biometric system, the authentication system must be extended to handle users falling into the FTE category. This can make the resulting system more complicated, less secure or more expensive. Even enrolled users can have difficulties using a biometric system. The FTE rate says how many of the input samples are of insufficient quality. Data acquisition must be repeated if the quality of input sample is not sufficient for further processing and this would be annoying for users. Biometric data are not considered to be secret and security of a biometric system cannot be based on the secrecy of users biometric characteristics. The server cannot authenticate the user just after receiving her correct biometric characteristics. The user authentication can be successful only when users characteristics are fresh and have been collected from the user being authenticated. This implies that the biometric input device must be trusted. Its authenticity should be verified (unless the device and the link are physically secure) and users liveness would be checked. The input device also should be under human supervision or tamper-resistant. The fact that biometric characteristics are not secret brings some issues that traditional authentication systems need not deal with. Many of the current biometric systems are not aware of this fact and therefore the security level they offer is limited. Some biometric sensors (particularly those having contact with users) also have a limited lifetime. While a magnetic card reader may be used for years (or even decades), the optical fingerprint reader (if heavily used) must be regularly cleaned and even then the lifetime need not exceed one year. Biometric systems may violate users privacy. Biometric characteristics are sensitive data that may contain a lot of personal information.
Page 11
Page 12
9. CONCLUSION
This technology not only offers convenience, but also promises greater safety and security. Biometrics is about using patterns, which are unique for each human individual, as a tool for identification As the saying goes Necessity is the mother of invention - with each passing day newer and newer technologies are emerging with in this field. Biometrics can be used for dozens of applications outside the scope of computer security. Facial recognition systems are often deployed at frequently visited places to search for criminals. Fingerprint systems (AFIS) are used to find an offender according to trails left on the crime spot. Infrared thermographs can point out people under influence of various drugs (different drugs react in different ways).
10.
1. 2. 3. 4. 5.
REFERENCE
Page 13