Fingerprint Identification By: Travis R. Gault Overview � Introduction � Introduction � Features of interest � Features of interest � Feature Encoding � Feature Encoding � Implementations in Industry � Implementations in Industry � Conclusions � Conclusions � Lab Overview � Lab Overview � Steps for Classroom Implementation � Steps for Classroom Implementation � References � References Introduction � Fingerprints have been used for centuries for � Fingerprints have been used for centuries for identification purposes identification purposes � Much like irises, each fingerprint is unique to � Much like irises, each fingerprint is unique to individuals individuals � Even identical twins have different � Even identical twins have different fingerprints fingerprints 1
Introduction � There are three fundamental principles of � There are three fundamental principles of fingerprints [3]. fingerprints [3]. 1. A fingerprint is an individual characteristic and no 1. A fingerprint is an individual characteristic and no two fingers have identical ridge characteristics two fingers have identical ridge characteristics 2. A fingerprint will remain unchanged during an 2. A fingerprint will remain unchanged during an individual’s lifetime. individual’s lifetime. 3. Fingerprints have general ridge patterns, making 3. Fingerprints have general ridge patterns, making it possible to systematically classify them. it possible to systematically classify them. Features of Interest � Global Features - are the characteristics that any � Global Features - are the characteristics that any human can see with the naked eye human can see with the naked eye � Basic Ridge Patterns � Basic Ridge Patterns � Pattern Area � Pattern Area � Delta � Delta � Type Lines � Type Lines � Ridge Count � Ridge Count � Local Features - or “Minutia Points” are the unique � Local Features - or “Minutia Points” are the unique characteristics of fingerprint ridges that are used for characteristics of fingerprint ridges that are used for positive identification. positive identification. � It’s possible to have the same global features, but � It’s possible to have the same global features, but the local features remain unique . the local features remain unique . Features of Interest � Pattern Area - is the part of the fingerprint that � Pattern Area - is the part of the fingerprint that contains all the global features. However, some contains all the global features. However, some local features may be found outside the pattern local features may be found outside the pattern area. area. Images taken from [1]. Images taken from [1]. 2
Features of Interest � Core Point - is the approximate center of the � Core Point - is the approximate center of the fingerprint, and is used as the reference point for fingerprint, and is used as the reference point for reading/classifying the print. reading/classifying the print. � More specifically it is defined as the topmost point on � More specifically it is defined as the topmost point on the innermost upwardly curving ridgeline the innermost upwardly curving ridgeline � The figure below, taken from [2], shows some � The figure below, taken from [2], shows some fingerprints and their core point locations fingerprints and their core point locations Features of Interest � Type Lines - are the two innermost ridges � Type Lines - are the two innermost ridges that start parallel, diverge, and tend to that start parallel, diverge, and tend to surround the pattern area. surround the pattern area. Type Lines Features of Interest � Delta - is the point on the first bifurcation, � Delta - is the point on the first bifurcation, abrupt ending ridge, meeting of two abrupt ending ridge, meeting of two ridges, dot, fragmentary ridge, or any ridges, dot, fragmentary ridge, or any point on a ridge at or nearest the center of point on a ridge at or nearest the center of divergence of two type lines, located at or divergence of two type lines, located at or directly in front of their point of directly in front of their point of divergence. divergence. 3
Features of Interest � Ridge Count - is the number of ridges � Ridge Count - is the number of ridges between the delta and the core. between the delta and the core. � This is done by drawing an imaginary line � This is done by drawing an imaginary line from the Delta to the Core and each ridge from the Delta to the Core and each ridge that touches this line is counted. that touches this line is counted. Features of Interest � In the figure below, taken from [4], the circle � In the figure below, taken from [4], the circle is the core, the triangle is the delta, the is the core, the triangle is the delta, the square is a minutiae-ridge ending and the square is a minutiae-ridge ending and the diamond is a minutiae-ridge bifurcation. The diamond is a minutiae-ridge bifurcation. The orange line is the ridge count line. orange line is the ridge count line. Features of Interest � Local Features � Local Features � Ridge Ending - ridge ends � Ridge Ending - ridge ends � Ridge Bifurcation - divides into � Ridge Bifurcation - divides into branches branches � Ridge Divergence - diverging of two � Ridge Divergence - diverging of two parallel lines parallel lines � Dot or Island - small ridge � Dot or Island - small ridge � Enclosure - divides and reunites � Enclosure - divides and reunites � Short Ridge - like a dot/island, but � Short Ridge - like a dot/island, but larger larger � Image taken from [5]. � Image taken from [5]. 4
Features of Interest � Basic Ridge Patterns � Basic Ridge Patterns � Loop - is the most common (~ 65% of all prints) � Loop - is the most common (~ 65% of all prints) � Arch - more open curve than a loop � Arch - more open curve than a loop � Whorl - ridge that makes a complete circle (~ 30% � Whorl - ridge that makes a complete circle (~ 30% of all prints) of all prints) Feature E ncoding � Manual � Manual � Human experts use a combination of visual, textural, � Human experts use a combination of visual, textural, minutiae cues and experience for verification minutiae cues and experience for verification � Still used in the final stages of law enforcement applications � Still used in the final stages of law enforcement applications � Image based � Image based � Utilizes only visual appearance. � Utilizes only visual appearance. � Requires the complete image to be stored (large template � Requires the complete image to be stored (large template sizes) sizes) � Taken from [5]. � Taken from [5]. Feature E ncoding � Texture based � Texture based � Treats the fingerprint as an oriented texture image � Treats the fingerprint as an oriented texture image � Less accurate than minutiae based matchers since most � Less accurate than minutiae based matchers since most regions in the fingerprints carry low textural content regions in the fingerprints carry low textural content � Minutiae based � Minutiae based � Uses the relative position of the minutiae points � Uses the relative position of the minutiae points � The most popular and accurate approach for verification � The most popular and accurate approach for verification � Resembles manual approach very closely. � Resembles manual approach very closely. � From a software perspective, the minutia are also used to � From a software perspective, the minutia are also used to align the images for database comparisons. align the images for database comparisons. 5
Recommend
More recommend