Share Email Print

Proceedings Paper

Design of biometrics identification system on palm vein using infrared light
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Image obtained by the LED with wavelength 740nm and 810nm showed that the contrast gradient of vein pattern is low and palm pattern still exist. It means that 740nm and 810nm are less suitable for the detection of blood vessels in the palm of the hand. At a wavelength of 940nm, the pattern is clearly visible, and the pattern of the palms is mostly gone. Furthermore, the pre-processing performed using smoothing process which include Gaussian filter and median filter and contrast stretching. Image segmentation is done by getting the ROI area that would be obtained its information. The identification process of image features obtained by using MSE (Mean Suare Error) method ,LBP (Local Binary Pattern). Furthermore, we will use a database consists of 5 different palm vein pattern which will be used for testing the tool in the identification process. All the process above are done using Raspberry Pi device. The Obtained MSE parameter is 0.025 and LBP features score are less than 10-3 for image to be matched.

Paper Details

Date Published: 11 November 2016
PDF: 7 pages
Proc. SPIE 10150, Second International Seminar on Photonics, Optics, and Its Applications (ISPhOA 2016), 101501K (11 November 2016); doi: 10.1117/12.2248505
Show Author Affiliations
Muhammad Syafiq, Institut Teknologi Sepuluh Nopember (Indonesia)
Aulia M. T. Nasution, Institut Teknologi Sepuluh Nopember (Indonesia)

Published in SPIE Proceedings Vol. 10150:
Second International Seminar on Photonics, Optics, and Its Applications (ISPhOA 2016)
Agus M. Hatta; Aulia M. T. Nasution, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?