Final+paper

Sartenejas, June 28th, 2009. ** Written by ** María Alejandra Fernández M. ** PATTERN RECOGNITION AND FINGERPRINT RECOGNITION **

** CONTENT ** ** 1. ** ** Introduction ** ** 1.1. ** Pattern Recognition's Definition. ** 1.2. ** Applications of Pattern Recognition. ** 1.3. ** Fingerprint: Definition, types and Characteristics. ** 2. ** ** The Aim: ** To identify and to compare fingerprints across Pattern Recognition Methods. ** 3. ** ** The Development: ** To give response to our aim, that is to say, to explain how it is possible to identify and to compare fingerprints with Pattern Recognition Methods. ** 4. ** ** Conclusion ** ** INTRODUCTION ** The Pattern Recognition is a basic attribute in the animal behavior. Also it is possible to define it as the science that is busy with the processes on engineering, computation and mathematics related to physical objects and/or abstract objects, with the intention of extracting information that allows to establish properties of or between sets of the above mentioned objects.

The stages of the Process of Pattern Recognition are: - Physical System (Reality). - Modeling by the not mathematical specialist. - Systems of Measurement. - Data obtained. - Validation of the data. - Definition of the model of Recognition who more is convenient to continue. - Mathematical Modeling. - Selection of variables. - Design of the classifier. - Test and validation of the classifier. - Application of the model. - Interpretation of results. - Feedback.

A system of complete Pattern Recognition consists of a sensor that gathers the observations to classify, a system of extraction of characteristics that transforms the information observed in numerical or symbolic values, and a system of classification or description that, based on the extracted characteristics, classifies the measurement.

The classification uses habitually one of the following procedures: statistical classification (or theory of the decision), Syntactic classification (or structural). The pattern statistical recognition is based on the statistical characteristics of the pattern, assuming that it has been generated by a probability system. The pattern structural recognition is based on the structural relations of the characteristics.

For the classification it is possible to use a set of learning, of which already the classification of the information is known "a priori" and is used to train to the system, being the resultant strategy known as "supervised learning". The learning can be "not supervised" also, the system does not have a set to learn to classify the information "a priori", but it is based on statistical calculations to classify the pattern.

Methods of pattern recognition are useful in many applications such as information retrieval, data mining, document image analysis and recognition, computational linguistics, forensics, biometrics and bioinformatics.

The object of interest for this Written Project is the application of pattern recognition techniques in fingerprint recognition.

“Fingerprint identification is one of the most well-known and publicized biometrics. Because of its uniqueness and consistency over time, fingerprints have been used for identification for over a century, more recently becoming automated (i.e. a biometric) due to advancements in computing capabilities. Fingerprint identification is popular because of the inherent ease in acquisition, the numerous sources (ten fingers) available for collection, and their established use and collections by law enforcement and immigration”. [|www.**biometric**coe.gov/Modalities/**Fingerprint**.htm] ”

THE FINGERPRINT:

“A smoothly flowing pattern formed by alternating crests (ridges) and troughs (valleys) on the palmer aspect of hand is called a palmprint. Formation of a palmprint depends on the initial conditions of the embryonic mesoderm from which they develop. The pattern on pulp of each terminal phalanx is considered as an individual pattern and is commonly referred to as a fingerprint. A fingerprint is believed to be unique to each person (and each finger). Fingerprints of even identical twins are different”. Handbook of image and video processing written by Alan Conrad Bovik.

Also, the fingerprint can be defined as the brand that leaves the yolk of the finger in an object on having touched it. Because of it, it is possible to obtain fingerprints purposely, on to having impregnated to the finger with a coloring matter. Fingerprint Identification refers to the automated method of verifying a match between two human fingerprints. Fingerprints are one of many forms of biometrics used to identify an individual and verify their identity.

There are two major classes of algorithms (minutia and pattern) and four sensor designs (optical, ultrasonic, passive capacitance, and active capacitance).

The analysis of fingerprints for matching purposes generally requires the comparison of several features of the print pattern. These include patterns, which are aggregate characteristics of ridges, and minutia points, which are unique features found within the patterns. It is also necessary to know the structure and properties of human skin in order to successfully employ some of the imaging technologies. Patterns: The three basic patterns of fingerprint ridges are the arch, loop, and whorl. An arch is a pattern where the ridges enter from one side of the finger, rise in the center forming an arc, and then exit the other side of the finger. The loop is a pattern where the ridges enter from one side of a finger, form a curve, and tend to exit from the same side they enter. In the whorl pattern, ridges form circularly around a central point on the finger. Scientists have found that family members often share the same general fingerprint patterns, leading to the belief that these patterns are inherited.

Approximately 5% of all the fingerprints are Arches, 30% are whorls and 65% are loops.

Minutia features: The major Minutia features of fingerprint ridges are: ridge ending, bifurcation, and dot. The ridge ending is the point at which a ridge terminates. Bifurcations are points at which a single ridge splits into two ridges. Dots are ridges which are significantly shorter than the average ridge length on the fingerprint.

Minutiae and patterns are very important in the analysis of fingerprints since no two fingers have been shown to be identical. In fact, identical twins have difference fingerprints.



The points that are seen in the image are the minutiae, these points have coordinates that allow to distinguish a specific fingerprint on the other, because the combination of these minutiae is unique, not repeated the same coordinate points in two difference fingerprints.

Image taken from: http://perso.wanadoo.fr/fingerchip/index.htm

SENSORS

A fingerprint sensor is an electronic device used to capture a digital picture of the fingerprint pattern. The captured picture is called a live scan. This live scan is digitally processes to create a biometric template which is stored and used for matching. This is an overview of some of the more commonly used fingerprint sensor technologies.

The Process: The method of analysis consists in a joining process.
 *  The image is processed to get it into a form suitable for computer reading.


 * Then we proceed to extract and characterize components inside the image, using an algorithm for automatic tracking of thin lines: The tracking algorithm is employed in the detection of features characteristic of the fingerprint, identifying and tracking the trajectory of the pixels with relation to vicinity and connectivity.


 * The thin lines are obtained by a skeleton algorithm over the regions of the fingerprint’s ridge.


 * Finally, the information is handled in mathematical form to obtain the recognition and interpretation of the fingerprint (with Non Parametric Statistical theory and Neuronal Networks).

References:

Wikipedia: § Richard O. Duda, Peter E. Hart, David G. Stork (2001)  // Pattern classification // (2ª edición), Wiley, New York,   [|ISBN 0471056693]. § Dietrich Paulus and Joachim Hornegger (1998)  // Applied Pattern Recognition // (2ª edición), Vieweg. [|ISBN 3-528-15558-2] § J. Schuermann:  // Pattern Classification: A Unified View of Statistical and Neural Approaches //, Wiley&Sons, 1996,  [|ISBN 0471135348] § Sholom Weiss and Casimir Kulikowski (1991)  // Computer Systems That Learn //, Morgan Kaufmann. [|ISBN 1-55860-065-5] Others Websites: o [] o [] o []