Hermite/Laguerre Neural Networks for Classification of Artificial Fingerprints from Optical Coherence Tomography

Author

Peterson, Leif E. ; Larin, Kirill V.

Author_Institution

Center for Biostat., Methodist Hosp. Res. Inst., Houston, TX

fYear

2008

fDate

11-13 Dec. 2008

Firstpage

637

Lastpage

643

Abstract

We used forward (FNN), Hermite(HNN), and Laguerre (LNN) neural networks to classify real and artificial fingerprints based on images obtained from optical coherence tomography (OCT). Use of a self-organizing map (SOM) after Gabor edge detection of OCT images of fingerprint and material surfaces resulted in the greatest classification performance when compared with moments based on color, texture, and shape. The FNN and HNN performed similarly; however, the LNN performed the worst at a low number of hidden nodes but overtook performance of the FNN and HNN as the number of hidden nodes approached n=10.

Keywords

edge detection; fingerprint identification; image classification; image colour analysis; image texture; medical image processing; optical tomography; self-organising feature maps; Gabor edge detection; Hermite neural networks; Hermite/Laguerre neural networks; OCT images; artificial fingerprints; forward neural networks; image classification; image color; image texture; optical coherence tomography; self-organizing map; Artificial neural networks; Biomedical optical imaging; Biometrics; Fingerprint recognition; Machine learning; Mirrors; Optical computing; Optical fiber networks; Optical materials; Tomography; Gabor edge detection; Hermite neural network; Laguerre neural network; artificial fingerprint; classification; optical coherence tomography;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Applications, 2008. ICMLA '08. Seventh International Conference on

Conference_Location

San Diego, CA

Print_ISBN

978-0-7695-3495-4

Type

conf

DOI

10.1109/ICMLA.2008.36

Filename

4725042