Biometric identification using global discretezation
Biometrics is the science and technology that involves the measurement and analysis of the human body’s biological data. Biometrics involves the extraction a feature set from the obtained data. The feature set is then compared against the template set stored the database. Identification of people mu...
Saved in:
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Asian Research Publishing Network
2017
|
Subjects: | |
Online Access: | http://eprints.utm.my/id/eprint/76650/1/SitiMariyamShamsuddin2017_BiometricIdentificationusingGlobalDiscretezation.pdf http://eprints.utm.my/id/eprint/76650/ https://www.scopus.com/inward/record.uri?eid=2-s2.0-85026760638&partnerID=40&md5=17a9fd0450ae10cf3296ef077ab0e09d |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Universiti Teknologi Malaysia |
Language: | English |
Summary: | Biometrics is the science and technology that involves the measurement and analysis of the human body’s biological data. Biometrics involves the extraction a feature set from the obtained data. The feature set is then compared against the template set stored the database. Identification of people must demonstrate reliability and accurately especially in the domains of business transactions and in the access to confidential information. The currently available fingerprint biometric Identification concentrates on feature extraction and task of classification for authorship identification. In fingerprint, the random representation may cause degradation to the performance of classification. Thus, prior to the classification task, certain standards should be present to denote these unique features. In relation to this, the application of the discretization technique would be beneficial. Hence, a new framework for fingerprint biometric identification is proposed. This paper particularly shows the outcome of discretization process on fingerprint samples to attain individual identification. In this paper, the new proposed framework and classic framework were compared using samples. Based on the results, classification accuracies of 90% were obtained when using discretization process with fingerprint biometric identification. |
---|