30-07-2012, 01:29 PM
Seminar on Fingerprint Recognition
[attachment=29512]
An impression of the friction ridges, from the surface of a finger-tip.
Fingerprints are unique to each individual and they do not change over time.
Well known fingerprint distinctiveness, persistence, ease of acquisition and high matching accuracy rates
Makes it most reliable biometric technologies.
Operating Modes:
Verification mode: System verifies an individual's identity by comparing the input fingerprint with the individual's own template(s) stored in the database.
Identification mode: System identifies an individual by searching the templates of all the users in the database for a match.
Fingerprint Matching
Main approaches proposed for fingerprint matching can be classified into three categories :
Correlation-based matching : the template & query fingerprint images are spatially correlated to estimate the degree of similarity between them
Minutiae-based matching: consists of finding the alignment between the query and template minutia points
Ridge feature-based matching: Rely on various features of fingerprint ridge pattern such as ridge shape, texture information, local orientation and frequency
Objective:
A system, which can perform the latent fingerprint matching automatically, does not exist.
Fingerprint data can be analyzed using GA clustering method.
It is possible bcoz of ability of GAs to solve complex optimization problems
Using GA clustering, it can be possible to identify the hot spots in the latent finger print
Clustering is a statistical approach
Allows us to recognize patterns within a set of unlabeled data containing information on a number of variables
To estimate the optimum search strategy
Two neural networks can be trained
In order to learn the search strategy obtained from GA-clustering analysis
Trained neural networks can predict an optimum search strategy based on experts’ experiences
[attachment=29512]
An impression of the friction ridges, from the surface of a finger-tip.
Fingerprints are unique to each individual and they do not change over time.
Well known fingerprint distinctiveness, persistence, ease of acquisition and high matching accuracy rates
Makes it most reliable biometric technologies.
Operating Modes:
Verification mode: System verifies an individual's identity by comparing the input fingerprint with the individual's own template(s) stored in the database.
Identification mode: System identifies an individual by searching the templates of all the users in the database for a match.
Fingerprint Matching
Main approaches proposed for fingerprint matching can be classified into three categories :
Correlation-based matching : the template & query fingerprint images are spatially correlated to estimate the degree of similarity between them
Minutiae-based matching: consists of finding the alignment between the query and template minutia points
Ridge feature-based matching: Rely on various features of fingerprint ridge pattern such as ridge shape, texture information, local orientation and frequency
Objective:
A system, which can perform the latent fingerprint matching automatically, does not exist.
Fingerprint data can be analyzed using GA clustering method.
It is possible bcoz of ability of GAs to solve complex optimization problems
Using GA clustering, it can be possible to identify the hot spots in the latent finger print
Clustering is a statistical approach
Allows us to recognize patterns within a set of unlabeled data containing information on a number of variables
To estimate the optimum search strategy
Two neural networks can be trained
In order to learn the search strategy obtained from GA-clustering analysis
Trained neural networks can predict an optimum search strategy based on experts’ experiences