28-04-2011, 04:39 PM
[attachment=13041]
Abstract:
Biometrics comprises methods for uniquely recognizing humans based upon one or more intrinsic physical or behavioral traits. In information, in particular, biometrics is used as a form of identity access management and access control. It is also used to identify individuals in groups that are under surveillance. Biometrics are best defined as measurable and/or behavioral characteristics that can be employed to verify the identity of a person. They include fingerprints, retinal and iris scanning, hand-writing and geometry, voiceprints, facial recognition, DNA codes, and other techniques and features. Initially, these techniques were employed primarily in access control of high security facilities, however, they are now being deployed or proposed for use in a much broader range of public facing situations. In this talk, we will present, the highlights of some of these techniques as well as the challenges encountered in their selection and deployment.
Biometric characteristics can be divided in two main classes. First one is physiological & second one is behavioral. Physiological are related to the shape of the body. Examples include, but are not limited to fingerprint, face recognition, DNA, hand and palm geometry, iris recognition, which has largely replaced retina, and odor/scent. Behavioral are related to the behavior of a person. Examples include, but are not limited to typing rhythm, gait, and voice. Some researchers [1] have coined the term behaviometrics for this class of biometrics.
Introduction:
What are Biometrics?
Biometric technologies are automated methods for recognizing individuals based on biological and behavioral characteristics. Biometric technology involves the capture and storage of a distinctive, measurable characteristic, feature, or trait of an individual for subsequently recognizing that individual by automated means. Humans recognize each other according to their various characteristics. For example, friends, family, and co-workers recognize each other by faces and voices. Automated methods of recognizing a person based on a biological or behavioral characteristic is the basic tenet underlying biometrics.
Working of a biometric system:
A biometric system is essentially a pattern recognition system that recognizes a person by comparing the binary code of a uniquely specific biological or physical characteristic to the binary code of the stored characteristic. Samples are taken from individuals to see if there is similarity to biometric references previously taken from known individuals. The system then applies a specialized mathematical algorithm to the sample and converts it into a binary code and then compares it to the template sample to determine if the individual can be recognized.
B.D of biometric system
The main operations a system can perform are enrollment and test. During the enrollment, biometric information from an individual is stored. During the test, biometric information is detected and compared with the stored information. The first block (sensor) is the interface between the real world and our system; it has to acquire all the necessary data. The second block performs all the necessary pre-processing: it has to remove artifacts from the sensor, to enhance the input (e.g. removing background noise). In the third block features needed are extracted. A vector of numbers or an image with particular properties is used to create a template. A template is a synthesis of all the characteristics extracted from the source, in the optimal size to allow for adequate identifiability.
If enrollment is being performed the template is simply stored somewhere (on a card or within a database or both). If a matching phase is being performed, the obtained template is passed to a matcher that compares it with other existing templates, estimating the distance between them using any algorithm (e.g. Hamming distance). The matching program will analyze the template with the input. This will then be output for any specified use or purpose (e.g. entrance in a restricted area).
What is a Pattern?
By the time they are five years old, most children can recognize digits and letters. Small characters, large characters, handwritten, machine printed or rotated-all are easily recognized by the young. The characters may be written on a cluttered background, on crumpled paper or may even be partially occluded. We take this ability for granted until we face the task of teaching a machine how to do the same. Watanabe defines a pattern as opposite of a chaos; it is an entity, vaguely defined, that could be given a name. For example, a pattern could be a fingerprint image, a handwritten cursive word, a human face, or a speech signal.
Pattern Recognition:
The best pattern recognizers in most instances are humans, yet we do not understand how humans recognize patterns. Pattern recognition stems from the need for automated machine recognition of objects, signals or images, or the need for automated decision-making based on a given set of parameters. Despite over half a century of productive research, pattern recognition continues to be an active area of research because of many unsolved fundamental theoretical problems as well as a rapidly increasing number of applications that can benefit from pattern recognition.
A fundamental challenge in automated recognition and decision-making is the fact that pattern recognition problems that appear to be simple for even a 5- year old may in fact be quite difficult when transferred to machine domain.
A pattern
Consider the problem of identifying the gender of a person by looking at a pictorial representation. It is relatively straightforward for humans to effortlessly identify the genders of these people, but now consider the problem of having a machine making the same decision. hat distinguishing features are there between these two classes—males and females—that the machine should look at to make an intelligent decision? Of course, real-world pattern recognition problems are considerably more difficult then even the one illustrated above.
COMPONENTS OF A PATTERN RECOGNITION SYSTEM:
Data Acquisition: Acquiring of data from the real world. This part is basically done by the biometrics system. Adequacy ensures that a sufficient amount of data exists to learn the decision boundary as a functional mapping between the feature vectors and the correct class labels. There is no rule that specifies how much data is sufficient.
Preprocessing: An essential, yet often overlooked step in the design process is preprocessing, where the goal is to condition the acquired data such that noise from various sources are removed to the extent that it is possible. Various filtering techniques can be employed if the user has prior knowledge regarding the spectrum of the noise.
Feature Extraction: Both feature extraction and feature selection steps are in effect dimensionality reduction procedures. In short, the goal of feature extraction is to find preferably small number of features that are particularly distinguishing or informative for the classification process, and that are invariant to irrelevant transformations of the data.
Feature Selection: In feature selection, selection specifically means selectionof m features that provide the most discriminatory information, out of a possible d features, where m<d. In other words, feature selection, refer to selecting a subset of features from a set of features that have already been identified by a preceding feature extraction algorithm.
Abstract:
Biometrics comprises methods for uniquely recognizing humans based upon one or more intrinsic physical or behavioral traits. In information, in particular, biometrics is used as a form of identity access management and access control. It is also used to identify individuals in groups that are under surveillance. Biometrics are best defined as measurable and/or behavioral characteristics that can be employed to verify the identity of a person. They include fingerprints, retinal and iris scanning, hand-writing and geometry, voiceprints, facial recognition, DNA codes, and other techniques and features. Initially, these techniques were employed primarily in access control of high security facilities, however, they are now being deployed or proposed for use in a much broader range of public facing situations. In this talk, we will present, the highlights of some of these techniques as well as the challenges encountered in their selection and deployment.
Biometric characteristics can be divided in two main classes. First one is physiological & second one is behavioral. Physiological are related to the shape of the body. Examples include, but are not limited to fingerprint, face recognition, DNA, hand and palm geometry, iris recognition, which has largely replaced retina, and odor/scent. Behavioral are related to the behavior of a person. Examples include, but are not limited to typing rhythm, gait, and voice. Some researchers [1] have coined the term behaviometrics for this class of biometrics.
Introduction:
What are Biometrics?
Biometric technologies are automated methods for recognizing individuals based on biological and behavioral characteristics. Biometric technology involves the capture and storage of a distinctive, measurable characteristic, feature, or trait of an individual for subsequently recognizing that individual by automated means. Humans recognize each other according to their various characteristics. For example, friends, family, and co-workers recognize each other by faces and voices. Automated methods of recognizing a person based on a biological or behavioral characteristic is the basic tenet underlying biometrics.
Working of a biometric system:
A biometric system is essentially a pattern recognition system that recognizes a person by comparing the binary code of a uniquely specific biological or physical characteristic to the binary code of the stored characteristic. Samples are taken from individuals to see if there is similarity to biometric references previously taken from known individuals. The system then applies a specialized mathematical algorithm to the sample and converts it into a binary code and then compares it to the template sample to determine if the individual can be recognized.
B.D of biometric system
The main operations a system can perform are enrollment and test. During the enrollment, biometric information from an individual is stored. During the test, biometric information is detected and compared with the stored information. The first block (sensor) is the interface between the real world and our system; it has to acquire all the necessary data. The second block performs all the necessary pre-processing: it has to remove artifacts from the sensor, to enhance the input (e.g. removing background noise). In the third block features needed are extracted. A vector of numbers or an image with particular properties is used to create a template. A template is a synthesis of all the characteristics extracted from the source, in the optimal size to allow for adequate identifiability.
If enrollment is being performed the template is simply stored somewhere (on a card or within a database or both). If a matching phase is being performed, the obtained template is passed to a matcher that compares it with other existing templates, estimating the distance between them using any algorithm (e.g. Hamming distance). The matching program will analyze the template with the input. This will then be output for any specified use or purpose (e.g. entrance in a restricted area).
What is a Pattern?
By the time they are five years old, most children can recognize digits and letters. Small characters, large characters, handwritten, machine printed or rotated-all are easily recognized by the young. The characters may be written on a cluttered background, on crumpled paper or may even be partially occluded. We take this ability for granted until we face the task of teaching a machine how to do the same. Watanabe defines a pattern as opposite of a chaos; it is an entity, vaguely defined, that could be given a name. For example, a pattern could be a fingerprint image, a handwritten cursive word, a human face, or a speech signal.
Pattern Recognition:
The best pattern recognizers in most instances are humans, yet we do not understand how humans recognize patterns. Pattern recognition stems from the need for automated machine recognition of objects, signals or images, or the need for automated decision-making based on a given set of parameters. Despite over half a century of productive research, pattern recognition continues to be an active area of research because of many unsolved fundamental theoretical problems as well as a rapidly increasing number of applications that can benefit from pattern recognition.
A fundamental challenge in automated recognition and decision-making is the fact that pattern recognition problems that appear to be simple for even a 5- year old may in fact be quite difficult when transferred to machine domain.
A pattern
Consider the problem of identifying the gender of a person by looking at a pictorial representation. It is relatively straightforward for humans to effortlessly identify the genders of these people, but now consider the problem of having a machine making the same decision. hat distinguishing features are there between these two classes—males and females—that the machine should look at to make an intelligent decision? Of course, real-world pattern recognition problems are considerably more difficult then even the one illustrated above.
COMPONENTS OF A PATTERN RECOGNITION SYSTEM:
Data Acquisition: Acquiring of data from the real world. This part is basically done by the biometrics system. Adequacy ensures that a sufficient amount of data exists to learn the decision boundary as a functional mapping between the feature vectors and the correct class labels. There is no rule that specifies how much data is sufficient.
Preprocessing: An essential, yet often overlooked step in the design process is preprocessing, where the goal is to condition the acquired data such that noise from various sources are removed to the extent that it is possible. Various filtering techniques can be employed if the user has prior knowledge regarding the spectrum of the noise.
Feature Extraction: Both feature extraction and feature selection steps are in effect dimensionality reduction procedures. In short, the goal of feature extraction is to find preferably small number of features that are particularly distinguishing or informative for the classification process, and that are invariant to irrelevant transformations of the data.
Feature Selection: In feature selection, selection specifically means selectionof m features that provide the most discriminatory information, out of a possible d features, where m<d. In other words, feature selection, refer to selecting a subset of features from a set of features that have already been identified by a preceding feature extraction algorithm.
