Presentation 2012-03-02
A study on segmentation of fingerprint image using linear prediction
Tomoki YARA, Keiichi FUNAKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In the ubiquitous information society, biometrics authentication attracts attention and fingerprint identification is commonly used due to its convenience. The fingerprint identification based on Linear Prediction (LP) has been proposed, in which one line of data among X-axis or Y-axis is analyzed by LP and the identification is realized by a DP matching based on the spectrum distance. In recent years, the fingerprint identification system with large amount of fingerprint database through a network is being utilized. The fingerprint database provides a lot of fingerprint images. As a result, a large amount of storage is required. Since fingerprint image provides a blank as a background. The blank provides no meaning for the identification. If segmentation method can remove the blank, the storage size can be reduced. In this study, we examined the segmentation method based on spectral distance between adjacent frames using LP analysis. In the experiments, we use bad fingerprint image, large blank and small blank image in the fingerprint database of FVC2000 and FVC2002.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Fingerprint image / Linear prediction / Segmentation method
Paper # SIS2011-70
Date of Issue

Conference Information
Committee SIS
Conference Date 2012/2/23(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Smart Info-Media Systems (SIS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A study on segmentation of fingerprint image using linear prediction
Sub Title (in English)
Keyword(1) Fingerprint image
Keyword(2) Linear prediction
Keyword(3) Segmentation method
1st Author's Name Tomoki YARA
1st Author's Affiliation Graduate School of Engineering and Sciene, University of Ryukyus()
2nd Author's Name Keiichi FUNAKI
2nd Author's Affiliation C&N Center, University of the Ryukyus
Date 2012-03-02
Paper # SIS2011-70
Volume (vol) vol.111
Number (no) 457
Page pp.pp.-
#Pages 6
Date of Issue